Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 122 appraisals
Clinical spine surgery
An Introduction to Machine Learning for the Practicing Spine Surgeon
The applications of new and emerging technologies in spine surgery are constantly expanding. Specifically, machine learning algorithms have seen a rise in utilization in clinical research, allowing for interpretation of large datasets that have the capability of experiential learning. The goal of this work is to present a guide for surgeons to better understand model design, key takeaways, and common pitfalls related to machine learning to ensure accurate and appropriate interpretation of analytical findings in their practice.
2 Aug 2026
Read appraisal →Brain and behavior
Machine Learning-Based Prediction of Poor Outcomes in Intracerebral Hemorrhage: A Systematic Review and Meta-Analysis
BACKGROUND: Spontaneous intracerebral hemorrhage (ICH) is associated with high risks of mortality and disability, yet early and accurate outcome prediction remains challenging. This study systematically evaluated the performance of machine learning (ML) models in predicting key adverse outcomes (hematoma expansion [HE], poor functional outcome, mortality) in ICH, aiming to provide consolidated evidence for future research and clinical translation. METHODS: We systematically searched PubMed, Embase, Web of Science, and Cochrane Library up to September 2025. Studies developing and validating ML models for predicting HE, poor functional outcome (modified Rankin Scale 3-6), or mortality in adults with spontaneous ICH were included. Pooled concordance index (C-index), sensitivity, and specificity were calculated using a random-effects or bivariate model. RESULTS: Eighty-three studies (involving at least 136,840 patients) were included. Meta-analysis of model performance, derived predominantly from internal validation set, demonstrated that models integrating both clinical and radiomics features achieved the highest discriminative performance across key prognostic prediction tasks: predicting HE (pooled C-index 0.822, 95% confidence interval [CI] 0.789-0.855), poor functional outcome (C-index 0.850, 95% CI 0.830-0.869), and mortality (C-index 0.860, 95% CI 0.809-0.911). These findings should be interpreted with caution, as true external validation remains sparse. Logistic regression exhibited performance comparable to more complex ML algorithms. CONCLUSIONS: ML models, particularly integrated clinical-radiomics models, demonstrate strong performance for the prediction of outcomes in ICH. They hold significant potential to enhance risk stratification and guide personalized management, pending further validation in diverse cohorts.
1 Aug 2026
Read appraisal →Neurosurgical review
Development and external validation of a machine learning model for predicting postoperative hydrocephalus in 1,073 posterior fossa tumor patients
Postoperative hydrocephalus is a common complication following posterior fossa tumor resection, affecting 7-40% of patients. Although preoperative cerebrospinal fluid (CSF) diversion may be required in selected patients with hydrocephalus, decisions remain individualized in routine neurosurgical practice. We therefore developed and externally validated a model to provide supplementary preoperative risk stratification using routinely available variables. We retrospectively analyzed 1,073 patients following resection of posterior fossa tumors (PFTs) treated at five tertiary centers between 2013 and 2024, dividing them into a development cohort (n = 854) and an external validation cohort (n = 219). We initially screened 30 perioperative variables from the multicenter dataset and then selected a clinically implementable model restricted to variables available before tumor resection. Feature importance was ranked using Shapley additive explanations (SHAP), and seven distinct machine learning (ML) algorithms were evaluated. Model performance was comprehensively measured using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, precision-recall curves, and decision curve analysis. The final clinically implementable model included three preoperative variables: Evans index, tumor-fourth ventricle relationship, and preoperative cerebrospinal fluid diversion status. In the external validation cohort, the support vector machine model showed good external discrimination, with an area under the receiver operating characteristic curve of 0.877, accuracy of 81.3%, sensitivity of 80.8%, and specificity of 81.7%. Logistic regression achieved comparable discrimination. Calibration assessment suggested dataset shift between the development and external validation cohorts, indicating that absolute predicted probabilities should be interpreted cautiously in populations with different baseline risks. A concise three-variable preoperative model showed good external discrimination for clinically relevant postoperative hydrocephalus after posterior fossa tumor resection. The model may support preoperative risk communication and postoperative surveillance planning, but should not be used as a stand-alone indication for cerebrospinal fluid diversion. Prospective validation and local recalibration are warranted before routine clinical implementation.
31 July 2026
Read appraisal →Biomedical physics & engineering express
Automated ventricular and midline segmentation in cranial ultrasound with metrology
Ultrasound imaging through sonolucent cranial implants is an emerging modality for post-neurosurgical monitoring of the adult brain, but quantitative interpretation remains challenging due to speckle, attenuation, shadowing, and the difficulty of consistently delineating thin anatomical landmarks. We present a deep learning system developed atLongeviti Neuro Solutionsfor segmenting key intracranial structures-the ipsilateral and contralateral lateral ventricles and the cranial midline-in coronal-plane adult cranial ultrasound images from patients withLongeviti ClearFit®Acoustic Brain Interface (ABI)TMimplants. The dataset comprises 457 proprietary, de-identified ultrasound frames with known pixel spacing, annotated in CVAT with ventricle and midline labels. We benchmark multiple encoder-decoder segmentation architectures and address severe class imbalance using class-weighted optimization with Dice and midline-focused focal-Tversky terms, followed by horizontal-flip test-time averaging. The best-performing configuration achieved a foreground macro Dice of 0.856 on a held-out test set, with Dice values of 0.926, 0.921, and 0.720 for the contralateral ventricle, ipsilateral ventricle, and midline, respectively. Finally, predicted masks are converted into geometry-based metrology overlays by estimating maximal perpendicular ventricle spans and ventricle-to-midline distances. These outputs provide standardized, millimeter-calibrated measurement visualizations for downstream review and future clinical validation.
28 July 2026
Read appraisal →Journal of neural engineering
A roadmap to navigate the future of neural engineering
A group of leaders in neural engineering collaborated to develop a roadmap to navigate the future of neural engineering. We covered a range of themes, including brain machine interfaces, neural modeling, artificial intelligence and machine learning, neural interfaces, neural imaging, augmented rehabilitation, and neuromaterials. For each topic we reviewed the current status, identified current and future challenges, and speculated on the emerging and necessary advances in science and technology to meet these challenges. Neural engineering will continue to yield the approaches and insights that advance the diagnosis and treatment of nervous system disorders, as well as provide new understanding of neural function.
28 July 2026
Read appraisal →Cerebellum (London, England)
Advancing Cerebro-cerebellar Network Imaging with Ultra-high Field (7T) MRI: Progress and Future Challenges
Ultra-high field (UHF) MRI (≥ 7T) is increasingly used to study the cerebro-cerebellar networks, offering substantial gains in signal-to-noise ratio and blood oxygen level dependent (BOLD) sensitivity that enable submillimeter functional and structural imaging. These advantages are particularly relevant for the cerebellum, whose tightly folded cortex and small deep nuclei have historically been difficult to resolve in vivo. In this targeted review, we synthesize recent progress in UHF-MRI applied to cerebro-cerebellar network mapping and critically examine the methodological challenges that accompany these developments. We highlight how UHF-MRI has enabled more precise delineation of cerebellar functional territories, improved visualization of the dentate nucleus and its connectivity, and facilitated integration of cerebellar nodes into whole-brain network models. We also discuss the technical challenges, including RF-field inhomogeneity, susceptibility-induced distortions, and the trade-off between spatial resolution and signal strength. These issues are compounded in the cerebellum due to its anatomical location and fine-scale organization, increasing the risk of spatial biases and misinterpretation if not carefully addressed. Beyond acquisition, we identify key gaps in analysis methodologies, including the need for cerebellum-specific preprocessing pipelines, segmentation tools that preserve mesoscale anatomy, and frameworks that treat the cerebellum and cerebrum as a unified system. We also discuss emerging opportunities, such as neurostimulation, integration with postmortem imaging and deep learning-based methods that may help bridge microstructural and in vivo findings. Overall, we argue that while UHF-MRI holds transformative potential for cerebellar systems neuroscience, translational progress will depend on rigorous methodological standardization and awareness of its limitations.
27 July 2026
Read appraisal →Neurosurgical review
Prognostic value of automated pupillometry in traumatic brain injury: a systematic review and meta-analysis
Traumatic brain injury (TBI) remains a major global cause of mortality and long-term disability. Early prognostication is critical for guiding management decisions. Quantitative pupillometry (QP), using automated devices such as the NeurOptics NPi-200/300, enables bedside measurement of pupillary reactivity through indices like the Neurological Pupil Index (NPi), constriction velocity (CV), and dilation velocity (DV). We conducted a PRISMA-compliant systematic review and meta-analysis to evaluate the prognostic value of QP in adults with TBI. Observational studies of quantitative pupillometry within 72 h of traumatic brain injury in adult ICU patients were included. Studies limited to mild TBI were excluded, although mixed-severity cohorts were eligible. Primary outcomes were mortality and poor functional outcome at 3-6 months (GOS ≤ 3 or mRS ≥ 3). Secondary analyses assessed differences in pupillometry metrics according to intracranial hypertension defined by direct ICP measurements (> 20-25 mmHg) or proxy markers reflecting ICP-directed interventions. Odds ratios were pooled for dichotomous outcomes and mean differences for continuous outcomes using random-effects models, with heterogeneity quantified by I². Four studies (n = 354) reported mortality data. Abnormal quantitative pupillary metrics (most commonly NPi < 3 or absent reflexes) were associated with increased odds of in-hospital death (OR 1.84, 95% CI 1.01-3.35; I² = 84%). Five studies (n = 384) assessed functional outcomes, showing significantly greater odds of poor outcome among patients with abnormal pupillary metrics (OR 3.64, 95% CI 1.63-8.10; I² = 39%). Three studies (n = 190) evaluated intracranial pressure, demonstrating lower NPi values in patients with intracranial hypertension compared with those without elevated ICP, though this difference did not reach statistical significance (MD - 1.05, 95% CI - 2.65 to 0.54). Early quantitative pupillometry is associated with increased mortality and worse functional outcomes in TBI in observational studies. Lower quantitative pupillary metrics were also observed in the presence of intracranial hypertension. Despite substantial heterogeneity, these findings support its potential as a prognostic tool. Further standardization, validation and controlled studies are needed to refine its clinical application.
21 July 2026
Read appraisal →Journal of neural engineering
Dynamic functional graph-Laplacian priors integrated with optimization for EEG source localization
Objective. Electroencephalography (EEG) source localization is an ill-posed inverse problem in which conventional methods often rely on static anatomical or smoothness assumptions and may neglect task-related dynamic functional interactions. This study aims to develop a dynamic graph-regularized EEG source localization framework that incorporates time-varying functional connectivity directly into inverse reconstruction and improves source-space motor imagery (MI) decoding.Approach. We propose DynaGraph-alternating direction method of multipliers (DG-ADMM), a source localization framework that combines linearly constrained minimum variance (LCMV) beamforming, region-of-interest-level dimensionality reduction, dynamic phase synchronization analysis, graph-Laplacian regularization, and efficient optimization. Initial source estimates are obtained using a LCMV beamformer. Region-level source signals are then extracted using principal component analysis and sliding-window phase-locking values with surrogate-based statistical testing are used to construct reliable dynamic functional graphs. The resulting graph Laplacian is mapped back to source space and embedded as a structured prior in an ADMMs optimization problem.Main results. Experiments on the MNE sample dataset showed that DG-ADMM produced spatially concentrated and physiologically plausible source patterns. On the PhysioNet MI dataset, the proposed framework achieved a binary left-versus-right MI classification accuracy of 93.52%, outperforming representative deep learning baselines. In a 320-dataset synthetic benchmark covering single-source, double-source, correlated-source, and dynamic-source conditions at two signal-to-noise ratios, DG-ADMM achieved the lowest mean center-of-mass localization error in five of eight conditions and showed its clearest advantage for dynamic sources.Significance. The results demonstrate that dynamic functional connectivity can serve as an informative graph-structured prior for EEG inverse reconstruction. DG-ADMM provides an interpretable and computationally feasible strategy for improving spatial focus, temporal consistency, and source-space decoding performance in EEG-based brain-computer interfaces.
21 July 2026
Read appraisal →Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer
Patient experiences of tissue donation and digital consent support in primary craniospinal tumour research.
PURPOSE: Requests for tissue donation for research are often made at times of heightened vulnerability, particularly around diagnosis and surgery. This study explored patient experiences of tissue donation discussions, perspectives on consent, and the acceptability of digital decision support in primary craniospinal tumour research. METHODS: A UK national online cross-sectional survey was conducted with 50 adults with a primary brain tumour or spinal sarcoma. The survey was developed with patient and public involvement; six patient contributors reviewed the initial questionnaire before launch. Descriptive statistics summarised closed responses, and open-text comments were grouped descriptively to contextualise quantitative findings. Reporting was informed by STROBE guidance. RESULTS: Just over half of participants reported being invited to donate tissue for research (26/50, 52%). Respondents strongly preferred tissue donation to be discussed at or after a clinic appointment, and none selected the day of surgery as the preferred time. Among invited respondents, most reported that information was easy to understand (22/26, 85%), that they had an opportunity to ask questions (23/25, 92%), and that they had sufficient time to consider the decision (23/26, 88%). Sixteen of 26 invited respondents (62%) discussed the decision with family or friends; among invited respondents who had not done so, 7/10 (70%) would have liked the opportunity. Interest in a secure digital adjunct was high (46/49, 94%). CONCLUSION: Overall experience was generally positive, but the data identify specific, practical opportunities to strengthen consent support in rare craniospinal tumour pathways, including appropriate timing, clear and revisitable information, opportunities for question-asking, and resources that support family-inclusive decision-making.
19 July 2026
Read appraisal →Neurosurgical review
Stereotactic radiosurgery for treatment-refractory obsessive-compulsive disorder: a systematic review of targets, targeting methods, lesion geometry, and clinical outcomes.
BACKGROUND: Stereotactic radiosurgery (SRS) is a noninvasive option for carefully selected patients with treatment-refractory obsessive-compulsive disorder (OCD), but the literature is heterogeneous in targets, targeting methods, lesion geometry, and outcomes. METHODS: PRISMA-guided systematic review of PubMed, Scopus, and Web of Science. Full-text human studies of radiosurgical capsulotomy for treatment-refractory OCD were included. Narrative synthesis was performed across technical and clinical domains. When ≥3 comparable studies reported the same endpoint, exploratory random-effects single-arm meta-analyses were performed. RESULTS: Twenty-one OCD-specific studies were included (1999-2024). The anterior limb of the internal capsule (ALIC), particularly the ventral ALIC, was the dominant target. Technique and dose reporting varied across cohorts, with commonly reported maximum doses spanning approximately 120-180 Gy, often using 4-mm collimation and single- or double-shot paradigms. Earlier reports primarily used anatomical MRI/coordinate-based targeting, whereas newer studies increasingly incorporated lesion mapping, tractography, and network-based analyses. Eleven cohorts were eligible for quantitative pooling. The pooled clinical response rate was 57.1% (95% CI, 49.1%-64.9%; I²=21.7%), and pooled remission was 36.8% (95% CI, 26.9%-47.9%; I²=0%). Severe delayed radiation-related injury was uncommon but present (6.4%, 95% CI, 3.1%-12.8%; I²=0%). Mechanistic studies suggested that lesion topography and pathway engagement may be more important than lesion size alone. CONCLUSIONS: SRS is a meaningful option for treatment-refractory OCD. The ventral ALIC remains the principal target, but outcomes likely depend on precise target identification and lesion placement. Standardized reporting and prospective evaluation of pathway-informed targeting are needed.
19 July 2026
Read appraisal →BMJ open
Current evidence on radiofrequency denervation for chronic low back pain: a systematic review and meta-analysis
OBJECTIVE: To assess the effects of radiofrequency (RF) denervation for chronic low back pain (LBP) from facet joint, sacroiliac joint, discogenic and non-specific pain. DESIGN: Systematic review and meta-analysis. DATA SOURCES: We searched Medline, Embase, Cochrane Library, CINAHL, PsycINFO, ClinicalTrials.gov and WHO ICTRP up to 18 February 2025 for randomised controlled trials (RCTs). STUDY SELECTION, DATA EXTRACTION AND SYNTHESIS: Pairs of reviewers independently selected studies, extracted data and assessed risk of bias (Cochrane RoB 2). Meta-analyses with clinically homogeneous studies were performed and certainty of evidence was assessed using Grades of Recommendation, Assessment, Development and Evaluation. RESULTS: 55 RCTs (n=4394) were included; many outcomes were at some risk of bias. Low to moderate certainty evidence suggested small improvements in pain and function with RF denervation versus sham for facet joint pain, sacroiliac, discogenic and non-specific chronic LBP. None exceeded predefined minimally clinically important between-group differences, suggesting limited clinical relevance. CONCLUSIONS: RF denervation showed small improvements in pain and function compared with sham, steroid injection or standard care, but the effects did not reach clinically meaningful thresholds and the certainty of evidence was very low to moderate. Additional research is needed to clarify the effects of RF denervation and guide clinical decision-making. PROSPERO REGISTRATION NUMBER: CRD42023460743.
18 July 2026
Read appraisal →Nature communications
Sensory-guided human-machine joint learning accelerates the acquisition of motor imagery brain computer interface control
Brain-computer interfaces (BCIs) offer the potential to restore function and augment human capabilities. However, non-invasive electroencephalography (EEG)-based BCIs still face challenges in learning efficiency and control precision, particularly for naïve users performing complex tasks. Here, we present a sensory-guided joint learning framework that integrates human motor learning with adaptive machine learning to improve BCI training and performance. In 31 BCI-naïve participants, the framework enabled rapid skill acquisition, achieving average online discrete accuracies of 86.0% for one-dimensional (1D) and 77.5% for two-dimensional (2D) motor imagery tasks, along with continuous control accuracies of 77.5% (1D) and 66.9% (2D). Mechanistically, tactile guidance reduced user exploration and accelerated neural adaptation, while sample reweighting aligned decoder updates with human learning trajectories. By coupling reinforcement-driven neural plasticity with adaptive algorithmic optimization, this framework advances BCI training from passive calibration to active human-machine joint learning, enabling practical and scalable neural interfaces for communication and rehabilitation.
17 July 2026
Read appraisal →NeuroImage
Rapid multi-parametric quantitative MRI via deep learning-based synthetic-to-real reconstruction and 3D SSFP-MOLED imaging
Multi-parametric quantitative magnetic resonance imaging (mqMRI) holds significant clinical potential through multi-parametric tissue characterization, yet its adoption is hindered by prolonged scan time and sensitivity to non-ideal signal conditions, especially in high-resolution whole-brain protocols. To address these challenges, we propose a novel signal encoding method integrating phase-modulated three dimensional steady-state free precession with multiple overlapping-echo detachment (3D SSFP-MOLED). This method simultaneously encodes six physiological parameters (M0, T1, T2, T2*, B1+, ΔB0) into k-space by controlling overlapping echo detachment in signal acquisition. A physics-constrained synthetic data pipeline was developed to simulate MR signal evolutions with realistic field variations (ΔB0, B1+ inhomogeneities), enabling robust training of network for real-time parameter mapping. Whole-brain parametric maps (1×1×2 mm³ resolution) can be delivered within 3 minutes with only 2x parallel acquisition acceleration. Validation was performed on phantom, healthy volunteers, and clinical cases with tumors/hemorrhage. Experimental results show that our method can achieve rapid multi-parametric quantitation with high accuracy and reproducibility. By synergizing adaptive signal encoding, physics-informed synthetic training, and reproducible deep learning reconstruction, this work establishes a new paradigm for efficient and reliable mqMRI in clinical signal processing applications.
17 July 2026
Read appraisal →Neurosurgical review
Mechanical thrombectomy for pediatric large-vessel occlusion: a systematic review and meta-analysis with post hoc analysis
OBJECTIVE: To investigate the outcome of pediatric large vessel occlusion (LVO) treated with mechanical thrombectomy (MT). INTRODUCTION: Pediatric LVO is a rare subtype of ischemic stroke. In adults, MT is recommended; however, the efficacy and safety of MT in pediatric LVO are less explored. The available studies are mostly observational studies; yet, these studies show inconsistent findings. METHOD: This review adhered to the PRISMA 2020 guideline. Studies comparing MT with medical management in pediatric with LVO were included. The primary endpoint was the favourable outcome. The mortality rate was sought as well. Subgroup analysis compared MT with intravenous thrombolysis (IVT) and conservative management. Post hoc exploratory analyses comprised Bayesian inference and trial sequential analysis (TSA). RESULT: Six studies comprising a total of 230 MT-treated and 206 non-MT patients were included. In the primary analysis, favourable outcome did not differ significantly between the MT and medical management groups (OR 1.83; 95% CI 0.97-3.43), while supported by exploratory Bayesian inference (OR 1.75; 95% CrI 1.05-2.67; BF10 5.05). Subgroup analysis showed favourable outcomes of MT over IVT (OR 2.39; 95% CI 1.19-4.79) and conservative treatment (OR 2.22; 95% CI 1.41-3.51), although the Bayesian model did not support these findings. The available evidence was insufficient to detect or exclude a difference in mortality between MT and medical management (OR 1.32; 95% CI 0.45-3.89). TSA indicated that the required information size was not reached and that additional trials are needed to reach the minimum sample requirements. CONCLUSION: In this synthesis of observational data, the MT may be associated with favourable outcome in pediatric LVO, however, these findings are hypothesis-generating only. Adequately powered prospective studies are needed before MT can be recommended for pediatric LVO. CLINICAL TRIAL NUMBER: not applicable.
13 July 2026
Read appraisal →Journal of neuro-oncology
Feasibility evaluation of tumor treating fields for brainstem gliomas
PURPOSE: Tumor treating fields (TTFields) are FDA-approved for supratentorial glioblastoma, but feasibility in infratentorial tumors remains poorly defined. This simulation study evaluated TTFields dose in brainstem gliomas using patient-specific modeling with scalp-only transducer arrays. METHODS: MRI and CT imaging from seven patients with brainstem gliomas were used for TTFields planning with MAXPOINT® (Novocure, Switzerland). Clinical target volume (CTV) was defined as enhancing tumor on T1 post-contrast MRI (Gross tumor volume, GTV) plus a 3 mm peritumoral expansion. The platform optimized scalp-only array layouts, and finite element calculations generated maps of local minimum field intensity (LMiFI, V/cm) and local minimum power density (LMiPD, mW/cm³). Values were compared against a standard, unplanned layout using one-sided paired t-tests, with LMiFI ≥ 1.0 V/cm as a therapeutic reference. RESULTS: MAXPOINT-optimized layouts achieved significantly higher LMiFI than the standard layout across all regions (all p ≤ 0.019). GTV median LMiFI was 1.1 vs. 1.0 V/cm (p = 0.019). CTV median LMiFI was 1.1 vs. 1.0 V/cm (p = 0.002). Brainstem median LMiFI was 1.3 vs. 1.1 V/cm (p = 0.002). Posterior fossa showed the largest difference: median LMiFI 1.5 vs. 1.2 V/cm (p < 0.001). All optimized LMiFI values met or exceeded the therapeutic reference. LMiPD was also significantly higher with MAXPOINT® across all regions (all p ≤ 0.006). CONCLUSION: This simulation study demonstrates that patient-specific modeling can achieve favorable TTFields intensities in brainstem gliomas using scalp-only arrays, supporting prospective clinical evaluation for infratentorial tumors.
8 July 2026
Read appraisal →Journal of global health
Leapfrogging medical infrastructure: a novel bilateral exchange model driven by digital medicine in Kazakhstan.
The geographic maldistribution of highly specialised neurosurgical care in Central Asia, particularly Kazakhstan, presents a critical challenge driven by medical education pipeline constraints and brain drain. Traditional assistance models relying on short-term missions or conventional hardware donations are insufficient to bridge this fundamental infrastructural gap. We present a novel 'Bilateral Medical Exchange Model' established between Showa Medical University in Japan and top Kazakh medical institutions. By utilising advanced digital medicine - specifically, high-performance computing-driven artificial intelligence and 3D extended reality visualisation - as the primary diplomatic catalyst, this framework successfully engaged both grassroots clinicians and top-tier government officials. We highlight how targeting these technologies toward localised capacity building and edge-computing infrastructure circumvents traditional barriers. While long-term clinical outcomes remain to be systematically evaluated, this technology-driven diplomatic approach provides a foundational, hypothesis-generating framework for bridging the digital divide, integrating digital innovation with decentralised education to ultimately improve equitable patient outcomes in transitioning economies.
6 July 2026
Read appraisal →Medical physics
Gamma Knife treatment planning using knowledge-based reinforcement learning
BACKGROUND: Inverse planning is often used for Gamma Knife radiosurgery, allowing clinicians to mathematically specify desired clinical objectives and dose limits. The objectives are controlled by weights that are manually tuned to find the desired trade-off, which varies from case to case. Automation of this process can reduce clinical workload and improve consistency in plan quality. PURPOSE: To train a deep reinforcement learning agent using a reward function that incorporates the clinical metrics from past plans into its scoring criteria. The metric trade-off from the clinical plan is scored higher than all others, guiding the agent to produce plans with similar trade-offs. METHODS: An agent was trained to adjust the two priority weights (i.e., digital slider bars) in the clinical inverse planner. The agent consists of a neural network that receives the metrics and dose distribution of the current plan and the target and organ-at-risk masks as inputs. These methods were demonstrated on a dataset of 204 single-target metastases and a dataset of 71 acoustic neuroma cases. The cases were split into training, validation, and testing sets of size 123/41/40 and 42/14/15 for the metastases and acoustic neuromas, respectively. RESULTS: On the metastases test dataset, the agent achieved a significantly higher (p = 0.0136) average plan score (3.925 ± 0.130) compared to the default slider plans (3.874 ± 0.147). On the acoustic neuromas test dataset, the agent achieved a higher (p = 0.4493) average plan score (4.035 ± 0.177) compared to the default slider plans (3.995 ± 0.365). The higher plan scores are reflected in the four plan quality metrics: the agent's plans, on average, had metrics more similar to the clinical plans, compared to the default slider plans, for both test datasets. CONCLUSIONS: The proposed reward function enabled the agent to learn to find plans that aligned with historical planning decisions. Future work will investigate providing the agent with additional inputs that can explain the variability in planning decisions, which would further improve its performance.
4 July 2026
Read appraisal →PloS one
Deep learning based two-way feature depiction model for brain tumor detection
Brain tumors are one of the most fatal disorders that cause one of the highest mortalities in the world. Gliomas are the most common primary brain tumors originating from glial cells in the central nervous system. Traditionally, a tissue sample is extracted and examined for its genetic and characteristic properties. This method is invasive, painful, and takes a longer period to produce results. Various automatic Deep learning (DL) based schemes have been presented for the brain glioma detection, but they lack due to poor explainability, lower generalization, poor feature depiction, class imbalance problem and lower detection rate. This paper presents a deep learning based brain tumor detection using two way feature depiction model (TWFDM) that combines the 2D-Deep Convolution Neural Network (DCNN) and 1D-DCNN. The 2D-DCNN accepts the raw MRI images and the 1D-DCNN accepts the handcrafted local binary pattern (LBP), gray level cooccurrence matrix (GLCM), and Histogram of Oriented Gradient (HOG) features. Furthermore, improved particle swarm optimization (IPSO) is used for feature selection to minimize the computational complexity of the TWFDM system. The proposed TWFDM achieves an overall accuracy of 96.25%, a recall of 96.34%, a precision of 96.31%, and an F1-score of 96.32% on the Brain MRI dataset for four-class classification, representing an important improvement over traditional techniques.
3 July 2026
Read appraisal →Medical image analysis
A review of deep learning-based Unsupervised Anomaly Detection in brain MRI
The manual assessment of brain Magnetic Resonance Imaging (MRI) scans can be labor-intensive and time-consuming for radiologists. Deep Learning methods have demonstrated the potential to aid this process. However, their effectiveness relies on the availability of large, annotated data sets. Unsupervised Anomaly Detection (UAD) presents a promising alternative, offering the potential to identify and localize anomalies without per-pixel annotations. Instead, a normative distribution is learned using healthy data, enabling the identification of abnormalities as deviations. This allows UAD methods to detect abnormalities that were unseen during training. This appealing feature has led to numerous studies proposing innovations and novel approaches. In this work, we provide a review of the literature and systematically collect and compare the proposed approaches. We observe that UAD has made significant advancements in brain MRI analysis. However, individual approaches are often evaluated in different contexts, i.e., changes in acquisition parameters, pre- and post-processing, and anomaly scoring. This variability makes it challenging to assess which models perform best, underscoring the need for comprehensive comparative studies concerning the specific context of MRI scans. Our collection, featuring public data sets, research studies, and open implementations, is available at our GitHub repository https://github.com/FinnBehrendt/Unsupervised-Anomaly-Detection-in-Brain-MRI.
1 July 2026
Read appraisal →Brain topography
Local Field Potential Recordings Using Deep Brain Stimulation: A Practical Workflow and Open-Source Signal Processing Pipeline
Deep brain stimulation (DBS) systems with electrophysiological recording capabilities offer a unique opportunity to chronically record local field potentials (LFP) from implanted electrodes, enabling real-time monitoring of subcortical neural dynamics and the development of adaptive neuromodulation strategies. However, translating raw LFP into clinically relevant biomarkers remains challenging due to numerous technical considerations. To address this, we share both a practical guide for conducting LFP experiments and BrainWave-DBS, an open-source pipeline that implements the workflow and supports analysis of patient-derived LFP data. The pipeline covers data import, preprocessing, spectral analysis, and visualization, offering a reproducible framework for LFP analysis. Furthermore, we demonstrate the functionality of the pipeline using a representative Parkinson's disease dataset and highlight key technical insights gained through this work. By improving access to neural signal acquisition and analysis, our goal is to foster broader adoption of this technology, which could advance closed-loop neuromodulation of deep brain structures.
29 June 2026
Read appraisal →Biomedical physics & engineering express
Challenges and strategies in fusion of probes and imaging equipment for neural imaging
Recent years have seen significant progress in imaging technology, which has deepened our understanding of the brain. However, challenges remain in detecting nanoscale structures like the extracellular space and mapping complex neural networks. Various chemical probes have been developed to improve the imaging precision of microstructures and functional imaging. Yet, the integration of imaging technologies and probes stays underdeveloped. Differences in disciplinary paradigms, unclear quantitative and qualitative relationships, and a lack of optimized cross-functional orchestration are the main causes of this problem. In this paper, we propose potential strategies to achieve deep integration of probes and equipment for high-quality imaging. Specifically, we advocate for three main approaches: (1) designing imaging sequences driven by probe properties, (2) constructing quantitative dose-effect models, and (3) leveraging artificial intelligence for system optimization. Importantly, these strategies establish an adaptable framework that will facilitate the seamless integration of emerging probe and equipment technologies in future brain science research. Ultimately, this enhanced integration promises to advance our knowledge of brain function and structure.
29 June 2026
Read appraisal →Journal of neuro-oncology
Endovascular treatment of tumor-related dural sinus stenosis, venous outflow obstruction, and secondary intracranial hypertension: a systematic review of the literature.
INTRODUCTION: Tumors involving dural venous sinuses can lead to venous outflow obstruction and secondary intracranial hypertension. While surgical resection can decompress the sinus, such procedures carry significant risks. With the success of endovascular interventions for idiopathic intracranial hypertension (IIH), venous sinus stenting (VSS) and angioplasty have emerged as potential treatments for tumor-related sinus stenosis. However, evidence remains limited and dispersed. This systematic review aimed to synthesize the available literature on the safety and efficacy of endovascular treatment for tumor-related venous sinus obstruction. METHODS: A systematic search of PubMed, Embase, and Web of Science was conducted from database inception to November 2025. Eligible studies included any report describing endovascular treatment (VSS and/or angioplasty) for tumor-related venous sinus obstruction, whether due to tumor invasion or compression, or even stenosis following surgery or radiotherapy. Data on patient demographics, tumor characteristics, procedural details, and outcomes were extracted and summarized descriptively. RESULTS: Twenty studies comprising 57 patients were included. Most patients were female (65%) with a mean age of 48 years. Meningioma represented the most common underlying tumor (75%). The majority of obstructions resulted from tumor compression or invasion (86%), and most patients underwent VSS alone (74%), while the rest underwent VSS and angioplasty (23%). No periprocedural complications were reported. Mean trans-stenotic pressure gradient decreased by 10 ± 9 mmHg post-treatment and mean lumbar opening pressure decreased by 11 ± 12 cmH2O. Clinical improvement was reported in 63% of patients, including resolution or improvement of papilledema in 94% and vision changes in 94%. Repeat intervention was required in 28% of cases, and only about half of patients achieved further improvement after reintervention. CONCLUSION: Endovascular therapy for tumor-related venous sinus stenosis appears safe and effective, leading to meaningful pressure reduction and symptomatic improvement in two-thirds of patients. These findings support VSS as a viable adjunct or alternative to surgery in selected patients. Nonetheless, the certainty of evidence remains very low, and current data cannot establish definitive conclusions.
28 June 2026
Read appraisal →Physics in medicine and biology
Domain-specific adaptation for MR image synthesis with text-guided diffusion
Objective.Deep learning in medical imaging is severely constrained by data scarcity. Data synthesis offers a promising solution, but existing generative models have difficulty in restoring pathological texture features when trained on small-scale datasets. To address this, we propose a domain-specific, partition-based parallel text-guided latent diffusion model (LDM) for medical image synthesis.Approach.Each LDM operates on a defined image domain and is fine-tuned to reproduce specific texture characteristics. Diseased regions are identified from segmentation masks, while healthy regions are further subdivided using Voronoi-grayscale adaptation, enabling localized texture preservation. The fine-tuned LDMs independently synthesize corresponding image partitions, which are subsequently merged and denoised to form complete synthetic images with paired segmentation masks.Main results.We evaluated the approach on glioma MRI data, achieving a Fréchet Inception Distance of 13.65, demonstrating high perceptual realism. Texture fidelity was further supported by SSIM of 0.9674 and radiomic feature distribution analysis, both confirming close alignment between real and synthetic images. In a blinded visual Turing test, three radiologists achieved an average sensitivity of only 25.5% when identifying synthetic MRI slices, resulting in a 74.5% deception rate, and 41% of the synthetic samples were universally misclassified as real by all experts. In downstream experiments, U-Net trained on the synthetic-augmented dataset improved DSC by 14% on average.Significance.These results demonstrate that the proposed domain-specific adaptation framework can generate perceptually plausible, structure-preserving synthetic MRI slices in data-constrained environments, while improving downstream segmentation performance. The method therefore shows potential as an augmentation-oriented tool for AI model development, clinical teaching, assisted diagnosis, and rare-disease research.
25 June 2026
Read appraisal →Journal of neural engineering
Recalibration of implantable brain-computer interfaces to enable long-term independent use - a systematic review
Background.Implantable brain-computer interfaces (iBCIs) decode neural signals to generate command signals for effector devices to restore lost functions, such as movement or speech. However, maintaining device performance over time requires recalibration of decoding algorithms due to inherent instability in neural signals.Objective.To systematically review recalibration procedures in iBCIs for patients with motor impairments, focusing on the clinical implications of recalibration requirements and strategies which can enable long-term, independent use.Approach.A systematic search was conducted across EMBASE, MEDLINE, and CINAHL databases to identify studies involving recalibration of iBCIs. Data on recalibration frequency, duration, staff requirements, and location were extracted and analyzed.Main results.Recalibration practices varied widely amongst studies and were typically performed according to predetermined study protocols, rather than practical need following deteriorating device performance. Common practices include manual recalibration requiring a specialist research team, semi-automatic recalibration which could be performed by a non-specialist caregiver, and automatic recalibration methods whereby patients did not require assistance. Devices utilizing electrocorticography (ECoG) recording arrays generally required less frequent recalibration compared to those using microelectrode arrays (MEAs). Extended independent use was more frequently reported with ECoG-based iBCIs.Significance.Reducing recalibration frequency or complexity can improve patient autonomy, which is crucial for enhancing long-term independent iBCI use in home and clinical settings. ECoG iBCIs typically have a low recalibration burden due to inherent signal stability. Conversely, MEA iBCIs typically involve a higher recalibration burden, though recent studies have reduced this by incorporating spectral data and continuously updating models. Despite this progress, recalibration procedures are often not fully defined in iBCI studies, and where they are, they usually relate to the study protocol rather than the clinically meaningful recalibration requirement due to worsening device performance. Future studies should continue to develop user-friendly recalibration procedures and outline the clinically relevant recalibration requirements where possible.
24 June 2026
Read appraisal →Journal of robotic surgery
Robot-Assisted versus non-robotic frame-based deep brain stimulation: a systematic review and meta-analysis of targeting accuracy and clinical outcomes
Deep brain stimulation (DBS) outcomes depend on accurate lead placement. Robot-assisted DBS (RA-DBS) has been increasingly adopted, yet its advantages over conventional non-robotic frame-based DBS (NRA-DBS) regarding targeting accuracy, operative efficiency, and clinical outcomes remain debated.To compare RA-DBS versus NRA-DBS for targeting accuracy and clinical outcomes in patients undergoing DBS for movement disorders.This meta-analysis and systematic review was registered in PROSPERO (CRD420261336001) and adhered to PRISMA. Patients with mobility disorders treated with RA-DBS versus frame-based NRA-DBS were included in comparative studies (RCTs and prospective/retrospective cohorts). Targeting accuracy measures (such as target point error, vector error, and radial error) and extreme targeting outliers were the main results. Operative time measurements, perioperative problems (such as cerebral bleeding), and motor improvement (UPDRS-III) were secondary outcomes. Fixed-effects or random-effects models based on heterogeneity were used to compute pooled odds ratios (OR) and weighted mean differences (MD) with 95% confidence intervals (CI). Nine high-quality comparative studies encompassing 495 patients (227 RA-DBS vs. 268 NRA-DBS) were synthesized. RA-DBS significantly minimized target point error (MD = -0.31 mm, 95% CI: -0.61 to -0.01; P = 0.04) and significantly reduced the incidence of clinically significant targeting outliers (OR = 0.15, 95% CI: 0.04 to 0.51; P = 0.002). Comprehensive three-dimensional vector error was marginally lower in the RA-DBS cohort (MD = -0.70 mm; P = 0.05), whereas two-dimensional radial error and total operating room time, surgical duration, anesthesia time, perioperative complications, and 12-month UPDRS-III motor improvements were statistically equivalent between groups. Subgroup analyses revealed that the spatial precision advantage of RA-DBS was geographically robust across East Asian and Western cohorts, whereas chronological efficiency was heavily dependent on the specific robotic platform used.Compared with conventional frame-based stereotaxy, robot-assisted DBS significantly enhances target point precision and reduces electrode deviations. However, these technical accuracy advantages do not translate into overall clinical superiority, as both approaches yield comparable operative efficiency, perioperative safety, and mid-term motor symptom relief.
23 June 2026
Read appraisal →Journal of robotic surgery
Telesurgery and remote surgery research: a bibliometric analysis of scientific growth, collaboration, and thematic evolution
Telesurgery and remote surgery have gained relevance in surgical innovation due to advances in robotics, telepresence, artificial intelligence, and high-speed communication networks. Despite this progress, the global evolution, collaborative structure, and thematic development of this field remain insufficiently characterized. A bibliometric study was conducted using records retrieved from Web of Science. Publications on telesurgery and remote surgery published up to 2025 were included. Bibliographic data were processed and analyzed using the bibliometrix package in R. Bibliometric indicators, citation metrics, country productivity, journal output, author contributions, collaboration networks, and keyword-based thematic patterns were assessed. A total of 476 publications on telesurgery were included, distributed across 290 journals. Scientific production showed sustained growth, with an annual growth rate of 20.59%, a mean document age of 6.06 years, and peak output in 2024. The average citation count was 28.54 citations per document. The United States and China were the leading contributors, with 151 and 120 publications, respectively, and also acted as the main hubs in the international collaboration network. The most cited studies focused on telerobotic systems for minimally invasive surgery, telerobotic neurovascular interventions, and ultra-reliable low-latency communications. Keyword analysis showed a progressive shift from early clinical feasibility and surgical applications toward connectivity, latency, robotic systems, extended reality, blockchain, and artificial intelligence. These trends indicate the transition of telesurgery from a clinically exploratory field to a technology-driven research domain. Telesurgery and remote surgery constitute a rapidly expanding and technologically driven research field. Future progress will require stronger international collaboration, real-world clinical validation, standardized outcome assessment, and strategies to reduce technological inequities across regions.
23 June 2026
Read appraisal →Journal of neuro-oncology
AI for prognosis and treatment stratification in glioblastoma neurosurgery: a systematic review.
BACKGROUND: Glioblastoma (GBM) remains one of the most lethal adult primary brain tumors, and neurosurgical decision-making increasingly depends on integrating imaging, molecular, perioperative, and post-treatment data. Artificial intelligence (AI) methods have been proposed for several clinically relevant GBM tasks, but the literature remains heterogeneous and difficult to translate into practice. METHODS: We performed a PROSPERO-registered systematic review of AI, machine learning, and deep learning studies using MRI-derived and/or multimodal perioperative data in GBM for prognosis, risk stratification, treatment-response assessment, post-treatment classification, recurrence/progression prediction, and molecular prediction. Risk of bias was assessed using PROBAST-informed criteria. RESULTS: Thirty studies were included. Survival-focused tasks predominated (20/30, 66.7%), with radiomics plus conventional machine learning as the most common model family (13/30, 43.3%), followed by deep learning (8/30, 26.7%) and hybrid deep learning plus radiomics approaches (4/30, 13.3%). Validation was predominantly internal, and external validation was uncommon (5/30, 16.7%). CONCLUSIONS: AI shows promise for prognosis and treatment stratification in GBM neurosurgery, but current evidence is limited by heterogeneity, incomplete external validation, and inconsistent methodological reporting. CLINICAL TRIAL NUMBER: Not applicable.
20 June 2026
Read appraisal →Progress in biomedical engineering (Bristol, England)
Advancement of deep learning models with whole slide image in diagnosis, subtyping and prognosis for glioma.
Gliomas are heterogeneous primary central nervous system tumors with diverse molecular subtypes and variable prognosis. A paradigm shift in histopathology is underway as samples are digitized into whole-slide images (WSIs). Deep learning (DL) shows great potential for glioma diagnosis, subtyping, grading, and prognosis. This review summarizes recent advances in WSI-based DL models, covering data preprocessing, model architectures, and translational performance. Model evolution has progressed from CNNs (e.g. ResNet, capturing local features via convolution) to Transformers (e.g. Vision transformer, modeling global dependencies via self-attention), hybrid architectures, and large language model. Typical pipelines include quality control, stain normalization, patch extraction, feature integration, and prediction. Public datasets such as The Cancer Genome Atlas and Clinical Proteomic Tumor Analysis Consortium serve as key resources. On various datasets (public and institutional), a glioma-specific model ResNet-50 achieved AUC 0.983 for subtype classification; a Vision Transformer model reached AUC 0.960 for molecular typing; a hybrid model, ROAM, attained AUC 0.990; and the pan-cancer hybrid model called CHIEF achieved AUC 0.9397 for diagnosis. Attention heatmaps and Shapley Additive exPlanations provide interpretability by linking model outputs to histologic regions. Novel multimodal fusion integrates genomic, proteomic, radiologic, and clinical data to enhance prediction and uncover biological relevance. Future research may focus on enhancing model generalizability and predictive accuracy via advanced architectures, developing lightweight models for resource-limited settings to facilitate clinical translation.
20 June 2026
Read appraisal →Journal of neuro-oncology
Symptomatic radiation necrosis following intracranial brachytherapy: a systematic review and meta-analysis
PURPOSE: To estimate the pooled incidence of symptomatic radiation necrosis (RN) following intracranial brachytherapy and explore associations between clinical and technical variables and RN risk. METHODS: PubMed, Embase, Web of Science, and the Cochrane Library were searched from 1954 - 2024 in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Eligible human studies reported symptomatic RN after intracranial brachytherapy. RN ascertainment was secondarily classified as clear, partial, or unclear based on reproducibility of diagnostic criteria. A random-effects generalized linear mixed model was used to pool incidence rates, with subgroup analyses by tumor type, implant technique, isotope, dose rate, and prior radiation. Study quality was assessed using National Institutes of Health tools. RESULTS: Eighty-three studies encompassing 3,666 patients were included. The pooled incidence of symptomatic RN was 5.67% (95% CI: 3.84%-8.29%; I2 = 75.7%). RN ascertainment was clear in 25 studies, partial in 43, and unclear in 15. In sensitivity analyses, pooled symptomatic RN incidence was 8.71% among studies with clear RN definitions and 7.48% among studies with clear or partial definitions. Subgroup RN rates were 3.72% for low-grade gliomas, 8.44% for high-grade gliomas, 2.07% for brain metastases, and 8.98% for meningiomas. Isotope-specific rates were 5.83% for Iodine-125, 7.61% for Iridium-192, and 2.07% for Cesium-131. No statistically significant subgroup differences were observed. CONCLUSIONS: Symptomatic RN occurs in approximately 5.7% of patients following intracranial brachytherapy, within the range reported for other focal radiation therapies. Subgroup findings were not statistically significant and should be interpreted in the context of clinical and methodological heterogeneity.
13 June 2026
Read appraisal →Current pain and headache reports
Artificial Intelligence in Neuropathic Pain: From Mechanisms to Neuromodulation and Regenerative Strategies
PURPOSE OF REVIEW: Neuropathic pain remains challenging due to its heterogeneous mechanisms and variable treatment response. This narrative review evaluates recent advances in artificial intelligence (AI) and machine learning (ML) for patient phenotyping, treatment selection, outcome prediction, neuromodulation, and regenerative therapies. RECENT FINDINGS: ML-based phenotyping integrates genomic, neuroimaging, sensory, and behavioral data. Multimodal automatic pain assessment is approaching clinical deployment, supported by recent expert consensus. Large language models have been benchmarked against multidisciplinary teams for spinal cord stimulation (SCS) candidate selection. Real-world cohort data confirm sustained 24-month SCS benefit. AI is increasingly applied to regenerative interventions, including pulsed radiofrequency, which is now linked to epigenetic remodeling of dorsal root ganglion pathways. Most studies remain single-center and retrospective. AI may enable mechanism-based stratification, individualized neuromodulation programming, and rational integration of regenerative therapies in the treatment of neuropathic pain. Robust prospective validation, transparent reporting, and ethical safeguards are required before approaching translational maturity in selected settings.
13 June 2026
Read appraisal →Biomedical physics & engineering express
Enhancing brain tumor classification with a simplified CNN through hyperparameter optimization
Brain tumors remain a major public health challenge because of their high mortality rate and the need for timely and accurate diagnosis. Magnetic resonance imaging (MRI) is widely used for brain tumor assessment, yet conventional diagnostic workflows still depend largely on the subjective interpretation of radiologists, which may lead to inter-observer variability. In this context, deep learning approaches-particularly convolutional neural networks (CNNs)-have gained increasing attention for automated medical image analysis, as they are capable of learning discriminative features directly from imaging data and improving classification accuracy. Nevertheless, the performance of CNN-based models is strongly influenced by the choice of hyperparameters, whose optimization remains a non-trivial task due to complex and non-linear interactions within the network.This study investigates the impact of different hyperparameter optimization strategies on the performance of a simplified CNN model for brain tumor classification from MRI images. Three widely used optimization methods, Genetic Algorithms (GA), Bayesian Optimization (BO), and HyperBand-are considered and systematically compared. To emphasize efficiency and practical applicability, the CNN architecture is deliberately kept lightweight, aiming to reduce computational complexity while preserving sufficient modeling capacity. Experiments are carried out on a publicly available brain MRI dataset that includes glioma, meningioma, pituitary tumor, and healthy subjects.To account for performance variability and ensure statistical reliability, each optimized model is evaluated over ten independent runs using different random initializations. The reported results therefore include both the mean performance values and the corresponding standard deviations. The experimental analysis shows that the GA-based approach achieves a mean accuracy of 96.41%±0.36%, while BO improves this performance to 97.37%±0.30%. Among the evaluated strategies, HyperBand yields the highest average accuracy of 97.73%±0.48%, indicating its ability to consistently identify effective hyperparameter configurations for the proposed CNN architecture.
13 June 2026
Read appraisal →Journal of neuro-oncology
Laser interstitial thermal therapy (LITT) for brain metastases: a systematic review and pooled analysis of Efficacy/Safety and the role of combination treatments
PURPOSE: Laser interstitial thermal therapy (LITT) has been used for brain metastases (BM), particularly for recurrent lesions and radiation necrosis after stereotactic radiosurgery (SRS). As SRS is increasingly used, differentiating tumor recurrence from radiation necrosis has become a frequent clinical problem. Recently, LITT has also been combined with other treatments to improve outcomes. However, prior reviews have primarily focused on LITT monotherapy and have provided limited evaluation of emerging multimodal strategies. We aim to summarize the current literature on LITT for BM, with particular attention to local control, safety, factors associated with outcomes, and the potential role of combination treatment strategies. METHODS: PubMed, Scopus, and Web of Science were searched following PRISMA guidelines. We included studies reporting local control outcomes following LITT for BM or radiation necrosis secondary to previously treated BM. We used a combination of the following terms: ("laser interstitial thermal therapy" OR "LITT" OR "laser ablation") AND ("brain" OR "cerebral" OR "intracranial") AND ("metastases" OR "metastasis"). Graphical data were extracted using WebPlotDigitizer. A proportional meta-analysis was conducted to estimate pooled LTC rates at 6 and 12 months following treatment. RESULTS: A total of 254 studies were identified after duplicate removal, of which 30 met the inclusion criteria. These included 26 studies on LITT monotherapy and 4 on combination therapies, comprising 972 patients. Median age ranged from 51 to 69 years and median tumor volume from 2.2 to 8.5 cm. SRS was the most common prior treatment. Among patients treated with LITT monotherapy, pooled 6- and 12-month LTC rates were 74.4% and 67.9%, respectively. In subgroup analyses, corresponding rates were 74.0% and 67.9% for brain tumor metastases, and 76.6% and 65.7% for radiation necrosis. Studies of combination therapy reported local control rates of 76% for LITT+SRT (stereotactic radiotherapy), 94.7% for LITT+ICB (immune checkpoint blockade), and 100% at 12 months in both studies for LITT+cSRS (consolidation SRS). Transient neurological deficits were the most common adverse events, whereas permanent deficits were less frequent and procedure-related complications were reported in 20 patients. Significant predictive factors for better local control included greater extent of ablation, smaller pre-treatment tumor volume, pathology consistent with radiation necrosis and post-LITT chemotherapy. CONCLUSIONS: Current evidence suggests that LITT may provide favorable local control with an acceptable safety profile in selected patients, and combination approaches may further improve outcomes. However, the available evidence remains largely retrospective and heterogeneous, and further prospective studies are needed to better define the role of LITT and combination treatment strategies.
12 June 2026
Read appraisal →Journal of neural engineering
Computational neuroelectrophysiology and artificial intelligence for drug-resistant epilepsy: recent advances, current challenges, and future directions
Drug-resistant epilepsy (DRE) affects approximately 30% of epilepsy patients, with surgical cure rates below 70%. This challenge drives a fundamental paradigm shift from localizing a discrete epileptogenic zone toward characterizing and modulating the dysfunctional brain networks that initiate and propagate seizures. This review critically synthesizes how computational neuroelectrophysiology and artificial intelligence (AI) converge to propel this shift. We chart the trajectory from quantifying local biomarkers, including high-frequency oscillations and excitation-inhibition balance metrics, to mapping the topological properties of epileptic networks through functional and effective connectivity. The integration of these network features with AI techniques, particularly spatiotemporal deep learning architectures, has demonstrated significant potential for enhancing both the localization of the epileptogenic network and the prediction of postoperative outcomes. However, the translation of this network-centric paradigm into clinical practice remains constrained by several challenges, including spatial sampling bias, the inherent label instability of surgical outcomes, and the 'black-box' interpretability crisis. Future directions must emphasize EEG foundation models, causal AI, and the development of interactive multimodal AI agents. The convergence of mechanism-driven network models and data-driven AI frameworks promises a new era of personalized, network-guided therapy for DRE.
11 June 2026
Read appraisal →Neurosurgical review
Rho-associated kinase inhibitors in cerebral cavernous malformations: a preclinical systematic review
Cerebral cavernous malformations (CCMs) are vascular abnormalities characterized by clusters of dilated capillaries. They are most associated with loss-of-function mutations in three genes (Ccm1, Ccm2, and Pdcd10/Ccm3). In capillary endothelial cells, mutations activate the Rho-associated coiled-coil-containing protein kinase (ROCK), leading to non-heme iron deposition and lesion formation, thereby contributing to CCM pathophysiology. To address this, ROCK inhibitors are being explored as potential stabilizing therapies in CCM. By reviewing the existing literature, this study aims to provide a descriptive evaluation of their effects on non-heme iron deposition and lesion formation in murine models. This systematic review followed the PRISMA 2020 guideline and was registered in PROSPERO (CRD420251048073). PubMed, Embase, Web of Science, and Scopus were searched from inception to 2 February 2026. Eligible studies included in vivo murine CCM models with mutations in the Ccm1, Ccm2, and Pdcd10/Ccm3 genes. Studies had to evaluate direct ROCK inhibitors, such as fasudil and BA-1049, or indirect modulators of the RhoA/ROCK pathway, such as statins, regardless of dosage, route, or duration, and provide molecular evidence of RhoA/ROCK pathway modulation. The primary outcome was lesion burden, and the secondary outcomes included non-heme iron deposition and ROCK activity. Systematic searches identified 389 records, of which 4 studies were included, demonstrating that fasudil, a ROCK inhibitor, consistently reduced non-heme iron deposition and lesion burden in preclinical CCM models in mice. In Ccm1+/-Msh2-/- mice, fasudil reduced non-heme iron deposition and stage 2 lesions; in Ccm2+/-Msh2-/- mice, fasudil reduced non-heme iron deposition and lesion burden. One study demonstrated that BA-1049 caused a dose-dependent reduction in non-heme iron deposition and lesion burden. Studies have shown that ROCK pathway modulation reduces non-heme iron deposition and lesion burden. Further clinical investigations involving patients with CCM are essential to verify whether these experimental benefits can be reproduced in clinical settings.
9 June 2026
Read appraisal →Gene
Utilization of next generation sequencing from glioma patient liquid biopsy to determine survival prognostics: A systematic review
Glioma is a malignant cancer that affects the central nervous system. Early detection of glioma is still difficult due to the hard-to-reach location of the cancer. The use of next generation sequencing is one of the new developments that can be used for diagnosis, however the use of this modality for prognosis is still rarely discussed. This systematic review aims to determine the benefits of using next generation sequencing (NGS) on the assessment of ctDNA or cfDNA concentration, progression free survival (PFS), and overall survival (OS). This systematic review was made using data from six databases, namely PubMed, PMC, ProQuest, Google Schoolar, ScienceDirect, and SCOPUS, and was compiled based on guidelines from PRISMA. Fourteen studies were included in this systematic review with a total of 663 glioma patients. The results of ctDNA measurements generated through the NGS method with liquid biopsy samples show that the higher the grading and sampling when the tumor progresses can increase the ctDNA value. When assessing ctDNA concentrations at baseline when samples were taken, most studies showed a worse prognosis for PFS and OS survival time. However, the grouping of patients in the current studies is still highly variable so further studies with standardized ctDNA cut off values are needed for more precise determination of prognosis.
7 June 2026
Read appraisal →Brain structure & function
Automated interictal epileptic spike detection from simple and noisy annotations in MEG data
In drug-resistant epilepsy, presurgical evaluation can be considered for suitable candidates. Magnetoencephalography (MEG) has been shown to be an effective exam to inform the localization of the epileptogenic zone through the localization of interictal epileptic spikes. Manual detection of these pathological biomarkers remains a fastidious task due to the high dimensionality of MEG recordings, and inter-rater agreement has been reported to be only moderate. Current automated methods are unsuitable for clinical practice, either requiring extensively annotated data or lacking robustness on non-typical data. Considering a database of 82 patients, we demonstrate that deep learning models can be used for detecting interictal spikes in MEG recordings, even when only temporal and single-expert annotations are available, which represents real-world clinical practice. We propose two model architectures: a feature-based artificial neural network (ANN) and a convolutional neural network (CNN), evaluated against a state-of-the-art model to classify short time windows of signal. In addition, we employ an interactive machine learning strategy to iteratively improve our data annotation quality using intermediary model outputs. Both proposed models outperform the state-of-the-art model (F1-scores: CNN = 0.46, ANN = 0.44) when tested on 10 holdout test patients. The interactive machine learning strategy demonstrates that our models are robust to noisy annotations. Overall, results highlight the ability of our models to analyze complex and imperfectly annotated data. Our method of interactive machine learning offers great potential for faster data annotation, while our models represent useful and efficient tools for automated interictal spikes detection.
1 June 2026
Read appraisal →Neurosurgical review
Bilateral decompressive craniectomy in pediatric patients: A systematic review.
Traumatic brain injury (TBI) and other acute neurological insults remain leading causes of pediatric morbidity and mortality. In cases where elevated intracranial pressure (ICP) is refractory to maximal medical therapy, decompressive craniectomy (DC) may be considered as a salvage intervention. Although bilateral, bifrontal, bitemporal, and cruciate decompressive approaches are used in selected patients with diffuse cerebral edema or bihemispheric swelling, their role, timing, complications, and outcomes remain poorly defined in pediatric populations. Following PRISMA guidelines, PubMed, Scopus, Embase, and PubMed Central were searched for English-language studies reporting bifrontal, bitemporal, bilateral, or cruciate decompressive craniectomy in pediatric or young adult patients, defined a priori as age ≤ 21 years, with refractory intracranial hypertension from traumatic or non-traumatic etiologies. Studies were included only if the cohort met this age criterion or if pediatric/young adult outcomes could be separately extracted. Mixed-age studies without extractable pediatric/young adult data were excluded from the primary synthesis. Data regarding demographics, operative technique, timing, mortality, complications, ICP response, and functional outcomes were extracted and synthesized qualitatively because of clinical and methodological heterogeneity. Five studies met eligibility criteria for the primary pediatric/young adult synthesis, including one small randomized pilot trial and four observational cohorts. The available evidence was heterogeneous with respect to indication, ICP threshold, timing of surgery, operative technique, and outcome measurement. Bitemporal, bifrontal, bilateral, and cruciate decompressive strategies were reported primarily in selected patients with severe traumatic brain injury or diffuse cerebral swelling. Several larger pediatric decompressive craniectomy cohorts included only small bilateral or bifrontal subgroups, and outcomes were not always stratified by technique. Reported mortality, functional recovery, hydrocephalus, subgaleal collections, and need for reoperation varied across studies. Early decompression was associated with ICP reduction and favorable outcomes in limited reports, including one small randomized trial, but the evidence remains insufficient to determine comparative efficacy, optimal timing, or superiority of one bilateral decompressive approach. Bilateral, bifrontal, bitemporal, and cruciate decompressive craniectomy have been reported as feasible salvage strategies for carefully selected pediatric and young adult patients with refractory intracranial hypertension. However, current evidence is sparse, heterogeneous, and often not technique-specific. Therefore, definitive conclusions regarding efficacy, optimal timing, or superiority of one bilateral approach cannot be made. Prospective multicenter studies with standardized age definitions, ICP thresholds, operative taxonomy, complication reporting, and long-term neurocognitive outcomes are needed.
1 June 2026
Read appraisal →Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology
Concurrent de novo glioblastoma and meningiomatosis: a case report and systematic review of clinical, molecular, and topographical characteristics
INTRODUCTION: The co-occurrence of glioblastoma (GBM) and meningioma in a single patient is an exceptionally rare clinical phenomenon, often associated with prior irradiation or genetic syndromes. This study presents a unique case of concurrent de novo GBM and meningiomatosis and provides a systematic review of the literature to characterize this rare association. CASE PRESENTATION AND METHODS: A 78-year-old female with a known history of untreated meningiomatosis presented with refractory seizures and aphasia. Imaging revealed multiple stable extra-axial lesions and a new, distinct intra-axial right temporal lesion. The patient underwent a temporal lobectomy with gross total resection. Histopathology confirmed WHO grade 4 GBM (IDH-wildtype). Following multidisciplinary review, she completed adjuvant radiotherapy. At 6-month follow-up, she remained clinically stable with no recurrence. A systematic review was conducted, identifying 34 cases of concurrent GBM and meningioma. Data regarding demographics, topography, molecular profiles, and survival were analyzed. RESULTS: The median age was 63 years (range 30-86), with a slight male predominance (52.9%). Tumors were synchronous in 88.2% of cases. Topographically, 47.1% were "collision" or adjacent tumors, while 32.3% occurred in different hemispheres. Most meningiomas were WHO grade I (79.4%), while 97.1% of glial tumors were grade 4 GBM. Molecular analysis revealed classic independent drivers: 22q loss/NF2 mutations in meningiomas and 10q loss/EGFR amplification in GBMs. Median overall survival was 7 months (range 0.5-24 months), with modern trimodal therapy (Stupp protocol) showing a trend toward extended survival compared to older cohorts (Fig. 1). CONCLUSION: The coexistence of GBM and meningioma appears mostly coincidental, driven by distinct molecular pathways rather than a common progenitor. Despite the benign nature of the associated meningioma, prognosis is dictated by the aggressive GBM component. Early surgical intervention and modern adjuvant therapy remain essential for optimizing survival in these complex cases.
31 May 2026
Read appraisal →Journal of neuro-oncology
Predicting progression-free survival in glioblastoma with neuroimaging and machine learning
PURPOSE: Glioblastoma (GBM) is the most prevalent and aggressive form of malignant glioma. Reliable estimation of progression-free survival (PFS) prior to medical intervention could strengthen clinical decision-making and improve patient care. Here, we utilize machine learning (ML) to predict PFS in GBM patients using resting state network (RSN) connectivity before medical intervention. METHODS: GBM patients (N = 45, mean age 62.1 ± 10.3 years, mean PFS 9.5 ± 5.6 months, 62.2% male) were retrospectively recruited from Washington University Medical Center. All patients completed structural neuroimaging and resting-state functional MRI before surgery. Deep neural networks were trained on resting-state functional connectivity to predict PFS. Feature selection identified the 15 strongest predictive features prior to training. RESULTS: Sex (p = 0.0037), overall survival (p = 0.0003), MGMT promoter methylation status (p = 0.0064), presentation of weakness (p = 0.0037), and presentation of memory impairment (p = 0.045) were significantly associated with PFS. Tumor frequency and spatial correlation analyses associated dorsal attention, visual, frontal-parietal, and default mode networks with shorter PFS. Conversely, right-temporal lobe tumors were associated with better outcomes. RSN spatial maps revealed widespread alterations in association networks in GBM patients relative to controls. MRMR feature selection identified thalamic and association network connectivity, including somatomotor, ventral and dorsal attention, and default mode/parietal memory as the strongest predictors of PFS. Using leave-one-out validation, the model predicted PFS with an RMSE of 1.26 months, MAE of 1.08 months, and R² of 0.96 (p < 0.001). CONCLUSIONS: Our findings indicate that GBM alters functional brain organization on a widespread scale, and these global effects are informative of patient outcomes.
31 May 2026
Read appraisal →Journal of neuro-oncology
Intramedullary or invasive characteristics of spinal melanocytomas: a PRISMA compliant systematic review and pooled case analysis
PURPOSE: Primary meningeal melanocytomas (MMs) of the spinal cord are rare lesions. Even rarer are intramedullary and invasive variants. These intramedullary lesions may exhibit more aggressive behavior than their "benign" classification appreciates. The role of adjuvant radiotherapy (aRT) in this context remains uncertain. METHODS: This study is a PRISMA-compliant systematic review with a pooled-case analysis, including two recent institutional cases included as illustrative examples. RESULTS: Sixty-three reports were identified of primary intramedullary or invasive MMs. Among 56 patients with available recurrence data, 8 of 30 patients (26.7%) experienced recurrence after gross-total resection (GTR) and in 8 of 22 (36.4%) after near-total or subtotal resection (NTR/STR), with no significant difference between groups (two-sided Fisher's exact, P = 0.548). No recurrence was observed among three patients who received aRT upfront post GTR, compared with 8 of 27 (29.6%) who did not receive radiation (two-sided Fisher's exact, P = 0.545); however, this subgroup was markedly underpowered and should be interpreted as hypothesis-generating only. Nine patients developed metastatic disease or progression, including one post biopsy. Of the eight who underwent resection at index surgery, 2 (25%) had undergone GTR and 6 (75%) STR. CONCLUSIONS: These findings suggest that the designation of MMs as benign lesions may underestimate the oncologic potential of intramedullary or invasive disease. Consideration of aRT on an individualized basis for patients with intramedullary or invasive disease is reasonable, regardless of extent of resection.
30 May 2026
Read appraisal →Pituitary
The hook effect in macroprolactinomas: tumor size thresholds, prolactin patterns, and clinical consequences - a systematic review.
PURPOSE: The immunoassay "hook effect" may cause spuriously low prolactin (PRL) measurements in patients with macroprolactinomas, leading to misdiagnosis and inappropriate management. This systematic review aimed to determine the tumor size threshold and distribution at which the hook effect has been documented, characterize the pre-dilution PRL pattern, quantify the magnitude of PRL underestimation, and assess the clinical consequences of unrecognized hook effect. METHODS: PubMed, Embase, Scopus, Google Scholar, and Web of Science were searched for articles published between January 2000 and August 2025. Studies reporting individual patient data with confirmed hook effect (pre- and post-dilution PRL, tumor size, and confirmation by serial dilution) were included. Quality was assessed using the JBI Critical Appraisal Checklist for Case Reports. Data were synthesized using individual patient data (IPD) quantitative methods. The review was registered on PROSPERO (CRD420261375863) and reported per PRISMA 2020 guidelines. RESULTS: Twenty-three patients from 14 studies across 9 countries were included, with a median maximum tumor diameter of 48.0 mm (IQR 35.5-55.0; range 22-100 mm); the smallest confirmed hook-effect tumor diameter measured 22 mm, reported in two independent cases, and 9 of 23 cases (39.1%) occurred in tumors below the conventional giant adenoma threshold (≥ 40 mm). Median pre-dilution PRL was 100.0 ng/mL (IQR 62.0-164.5), while median post-dilution PRL was 6,460.0 ng/mL (IQR 3,608.5-16,657.5), yielding a median fold increase of 64.7× (IQR 46.8-141.5). Pre-dilution PRL ranged from 26 to 200 ng/mL in 82.6% of cases (95% CI: 62.9-93.0%), values often misattributed to stalk effect. Unrecognized hook effect led to unnecessary surgery in 55.6% of cases with documented clinical outcomes. The hook effect was documented across multiple immunoassay platforms. CONCLUSIONS: Pre-dilution PRL values often overlap with the range attributed to stalk effect, and serial dilution testing should be considered for pituitary macroadenoma with PRL disproportionately low relative to tumor size, regardless of whether the tumor meets the giant adenoma threshold to prevent misdiagnosis, unnecessary surgical intervention and delayed initiation of dopamine agonist therapy.
30 May 2026
Read appraisal →Journal of neuro-oncology
Predicting late radiation-associated neurocognitive and endocrine toxicity in patients with brain tumors
PURPOSE: Neurocognitive and endocrine dysfunction are potential complications of cranial irradiation. However, risk factors are poorly understood, impeding accurate prognostication and exploration of potential preventive interventions. The objective of this study was to evaluate the prognostic value of various vascular and genotypic risk factors for the development of radiation-related toxicities. METHODS: This single-institution retrospective cohort study included patients with metastatic and malignant primary brain tumors who received cranial irradiation as part of their initial tumor-directed therapy. Demographic and treatment characteristics were collected, as well as putative vascular and genotypic risk factors. Univariate, multivariate, and machine-learning analyses were performed using five pre-specified measures of radiation-related toxicity. The primary outcome was change in mini-mental status exam (MMSE). RESULTS: Eighty patients (53% male, mean age 55.7, 53% primary and 44% metastatic brain tumors) were included. Elevated homocysteine and ApOE4 genotype were the strongest predictors of MMSE decline in the multivariate model (OR 3.96 [6.5-200, p < 0.001 and 2.85 [1.92-27.6], p = 0.004). Elevated homocysteine was associated white matter change on MRI and both physician and patient assessment. ApoE4 allele was associated with new endocrine deficiency, and physician assessment. An online nomogram provides risk predictions for each of the five late toxicity outcomes: ( https://afranklin22.shinyapps.io/PRMMSERadiationRiskFactors/ ) CONCLUSION: Two pre-treatment laboratory values (elevated homocysteine and ApOE genotype) were strongly associated with post-radiation neurocognitive and endocrine dysfunction using a variety of domains. Our predictive algorithm can aid clinicians in stratifying baseline risk and should be validated in prospective trials and with additional metrics of ND.
30 May 2026
Read appraisal →Neurosurgical review
Modified tubular retractor for deep brain tumour resection: enhanced surgical outcomes in resource-constrained settings
Tubular retractors permit minimally invasive access to deep-seated intracranial tumours; however, limitations in visualisation and manoeuvrability reduce their suitability for lesions ≥ 3 cm, particularly in resource-limited centres. We evaluated a modified, low-cost tubular retractor incorporating enhanced visualisation and ergonomic features, comparing its performance with Leyla spatula-based retraction and traditional syringe-derived tubular systems. A prospective comparative cohort of 105 patients with deep brain tumours ≥ 3 cm was analysed. Patients underwent Leyla retraction (Group 1, n = 38), conventional tubular systems (Group 2, n = 32), or a modified tubular retractor (Group 3, n = 35). Outcomes included intraoperative visualisation, retractor stability, manoeuvrability, extent of resection, complications, and three-month Glasgow Outcome Scores. Owing to non-normal distribution, continuous variables were analysed using non-parametric tests and binary logistic regression. The modified tubular retractor demonstrated greater stability, broader visualisation, and enhanced instrument handling compared with conventional tubular systems. Gross total resection was achieved in 91.4% with the modified device, 78.9% with Leyla-based retraction, and 28.9% with traditional tubular systems. Logistic modelling identified retractor type (OR 2.59, p = 0.035), intraoperative visualisation (OR 2.01, p = 0.036), and histopathology (OR 1.41, p = 0.036) as independent predictors of residual tumour. The modified retractor group exhibited fewer complications, shorter ICU stays, and superior functional outcomes (GOS ≥ 4 in 91%). The modified tubular retractor demonstrated favourable operative handling and outcome trends for deep-seated tumours ≥ 3 cm, with improved visualisation, stability, and ergonomic access compared with conventional systems. However, limitations related to non-randomised design, learning-curve effects, advanced mapping, fluorescence integration, and supramaximal resection warrant cautious interpretation pending multicentre long-term validation.
29 May 2026
Read appraisal →Science advances
MR-AIV reveals in vivo brain-wide fluid flow with physics-informed AI
The circulation of cerebrospinal and interstitial fluid plays a vital role in clearing metabolic waste from the brain, and its disruption has been linked to neurological disorders. However, directly measuring brain-wide fluid transport, especially in the deep brain, has remained elusive. Here, we introduce magnetic resonance artificial intelligence velocimetry (MR-AIV), a framework featuring a specialized physics-informed architecture and optimization method that reconstructs three-dimensional fluid velocity fields from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). MR-AIV unveils brain-wide velocity maps while providing estimates of tissue permeability and pressure fields, quantities inaccessible to other methods. Applied to the brain, MR-AIV reveals a functional landscape of interstitial and perivascular flow, quantitatively distinguishing slow diffusion-driven transport [∼0.1 micrometers per second (μm/s)] from rapid advective flow (∼3 μm/s). This approach enables new investigations into brain clearance mechanisms and fluid dynamics in health and disease, with broad potential applications to other porous medium systems, from geophysics to tissue mechanics.
29 May 2026
Read appraisal →The New England journal of medicine
Decompression with or without Duraplasty for Chiari I and Syringomyelia
BACKGROUND: In children with Chiari type I malformation and syringomyelia, neurosurgical posterior fossa decompression (PFD) provides clinical improvement, but whether duraplasty (incising the dura and placing a dural graft) improves outcomes is unclear. METHODS: We conducted a multicenter, cluster-randomized, controlled trial of PFD with duraplasty (PFD-D) as compared with PFD alone. Persons 21 years of age or younger with cerebellar tonsillar ectopia of at least 5 mm and a maximum syrinx diameter of 3.0 to 9.9 mm were enrolled at 38 centers. Centers were cluster-randomized: all the participants within each center underwent the same intervention. The primary outcome was surgical complications within 6 months. Secondary outcomes were clinical improvement, syrinx reduction, and repeat decompression at 10 to 24 months and the change in overall health-related quality of life at 6 to 24 months. RESULTS: A total of 162 participants were included in the trial, of whom 78 were assigned to undergo PFD-D and 84 to undergo PFD alone. The percentage of participants with complications within 6 months was 14% with PFD-D and 6% with PFD (adjusted odds ratio, 2.59; 95% confidence interval [CI], 0.86 to 7.84; P = 0.11). At 24 months, the percentage of participants with clinical improvement was 58% with PFD-D and 46% with PFD; the mean (±SD) syrinx reduction was 3.08±2.33 mm and 1.22±1.79 mm, respectively; and the percentage of participants with repeat decompression was 3% and 14%. Changes in health-related quality of life were similar in the two groups. CONCLUSIONS: The percentage of participants with surgical complications did not differ significantly between those who underwent PFD-D and and those who underwent PFD alone. Larger trials are needed to determine the relative benefits and risks of these two procedures. (Funded by the Patient-Centered Outcomes Research Institute and others; ClinicalTrials.gov number, NCT02669836.).
29 May 2026
Read appraisal →Clinical & experimental metastasis
Local control and dose selection for lung cancer brain metastases treated with radiosurgery: an artificial intelligence model
Clinical and radiological outcomes after Stereotactic radiosurgery (SRS) for lung cancer brain metastases are heterogeneous, and prescription dose selection is often guided by experience rather than individual patient and tumor specific features. A data-driven approach that links dose to quantitative local control and adverse effect predictions could improve planning and follow-up strategies. We performed a retrospective single-center cohort study of lung cancer brain metastases treated with GKRS at the University of Pittsburgh Medical Center (2014-2024). Using routinely available clinical, tumor, and dosimetric variables, we trained a tumor-level Random Survival Forest to predict Local Control and Dose Selection for Lung Cancer Brain Metastases after GKRS treatment. Internal validation used leakage-resistant patient-level grouped cross-validation. Performance was assessed using Harrell's concordance index (C-index) and integrated Brier score (IBS). A connected dose-sweep decision layer evaluated predicted local control across a clinically feasible margin dose grid and selected the dose associated with the most favorable predicted profile at prespecified horizons. The survival model demonstrated good internal performance (C-index 0.83; IBS 0.15). A baseline dose imitation model predicted historical margin dose with low error (OOF MAE 1.59 Gy). The integrated decision layer generated individualized local control trajectories and returned horizon-specific local control probabilities and model-based prescription dose recommendations. An Artificial Intelligence framework integrating time-to-event prediction with outcome-linked dose sweeping can provide individualized GKRS decision support for lung cancer brain metastases by delivering quantitative local control forecasts and model-based dose recommendations.
28 May 2026
Read appraisal →Scientific reports
Uncertainty estimation and probabilistic skull shape reconstruction using bayesian neural networks
3D shape reconstruction is an active area of research and a fundamental problem in computer vision, with growing applications in the medical domain, where it enables the recovery of missing or fine anatomical structures. Numerous approaches have been proposed for medical shape reconstruction, emphasizing accurate and anatomically plausible reconstructions. However, 3D shape reconstruction remains an inherently ill-posed problem, meaning (1) both neural network-based methods and conventional shape modeling approaches naturally introduce uncertainty in their predictions, and (2) multiple anatomically plausible reconstructions exist for a given partial or low-resolution input. While the uncertainty aspects have been widely explored in general computer vision, they remain relatively under-explored in the context of medical shape reconstruction. In this paper, we developed a 3D Bayesian U-Net and investigated its use for uncertainty estimation and probabilistic reconstructions across three key tasks: cranial reconstruction, facial reconstruction, and skull shape super-resolution. Our findings show that the Bayesian model is able to produce a range of anatomically plausible skull reconstructions while capturing natural skull variations arising from the learned weight uncertainty. Notably, these variations are primarily expressed through differences in bone thickness, which aligns with anatomical expectations, particularly relevant in real-world applications like cranial implant design. Additionally, we propose a principled framework to study the relationship between weight uncertainty and reconstruction uncertainty by analyzing the learned posterior distribution of the weights, demonstrating that our Bayesian U-Net achieves comparable reconstruction performance to a deterministic U-Net baseline while providing reliable uncertainty estimates. Our study also reveals a clear cross-task uncertainty pattern, where tasks with stronger structural constraints, like super-resolution, yield lower predictive uncertainty, while less constrained tasks, like facial reconstruction, result in higher uncertainty. Refer to the project page for more visual results https://git.zib.de/jli/uncertainty-aware-skull-reconstruction/ .
28 May 2026
Read appraisal →Journal of neuro-oncology
Clinical utility of liquid biopsy in distinguishing true progression from radiation necrosis and pseudoprogression in malignant brain tumor.
BACKGROUND: Distinguishing true tumor progression from pseudoprogression (PsP) and radiation necrosis (RN) following radiotherapy or radiosurgery for intracranial tumors remains a significant clinical challenge. Conventional imaging modalities, including MRI and PET, often lack sufficient diagnostic accuracy, while histopathological confirmation, although definitive, is invasive and not always feasible. Liquid biopsy (LB) has emerged as a promising noninvasive diagnostic approach. METHODS: A systematic review was conducted across PubMed, Embase, Scopus, and Cochrane databases. A total of 964 records were identified, including PubMed (n = 322), Embase (n = 280), Scopus (n = 297), and Cochrane (n = 65), along with three clinical trials identified from trial registers. After removal of 157 duplicates using Covidence, 807 studies were screened by title and abstract. Of these, 749 were excluded, and 58 articles underwent full-text review. Ultimately, 11 studies met the inclusion criteria and were included in the analysis. RESULTS: A diverse range of LB-based biomarkers has been investigated, including immune cell-based markers (e.g., HLA-DRneg/low and VNN2+ CD14+ monocytic myeloid-derived suppressor cells), immune-related proteins (e.g., CXCL11 and MUC-16), circulating tumor cells, cell-free DNA, mitochondrial DNA, B1-SINE elements, microvesicles, and RNA analytes. Plasma was the most used biofluid, with limited evaluation of urine and cerebrospinal fluid. Analytical techniques varied widely, including flow cytometry, PCR-based assays, immunostaining-FISH, and multiplex protein platforms. Several biomarkers showed statistically significant differences among RN, PsP, and tumor recurrence; however, these findings were largely derived from small, heterogeneous cohorts with inconsistent reporting of diagnostic performance metrics. Composite indices, such as the DR-VNN2 index (DVI) and the Necrosis Prediction Index (NPI), showed potential for improving diagnostic differentiation. CONCLUSIONS: LB-based biomarkers show promise for differentiating RN and PsP from tumor recurrence; however, current evidence is limited by small sample sizes, methodological heterogeneity, and lack of standardized diagnostic criteria. Larger prospective studies and validation of composite biomarker models are required to establish their clinical utility. CLINICAL TRIAL NUMBER: Not Applicable.
26 May 2026
Read appraisal →Neurosurgical review
The role of preoperative thrombocytic factors on survival in patients with glioblastoma: a meta-analysis and synopsis of the literature
Glioblastoma (GBM) is the most common malignant primary brain tumour and is associated with poor prognosis. Platelet-related factors have been linked to outcomes in GBM, but evidence remains inconsistent. This review evaluates their prognostic value for survival. We conducted a systematic review and meta-analysis of studies on preoperative thrombocytic factors in GBM. PubMed, MEDLINE, and Embase were searched from inception to January 2025 using MeSH terms. Eligible studies included observational cohort studies of adults (≥ 16 years) with WHO grade 4 diffuse astrocytoma (GBM), ≥ 30 participants, and ≥ 3 months' follow-up after resection. Random-effects meta-analysis using restricted maximum likelihood with Hartung-Knapp adjustment was used to pool hazard ratios (HRs) of high vs. low parameters on overall survival (OS). Study quality was assessed with the Newcastle-Ottawa Scale. 21 studies were included. 13 (n = 2609) reported HRs of high vs. low platelet: lymphocyte ratio (PLR, median threshold = 150), with high PLR significantly associated with worse OS (pooled HR = 1.46, 95% CI [1.23, 1.74]). Eight studies (n = 1921) assessed platelet count (PC, median threshold = 208*109/L), showing high PC was a borderline predictor of worse OS (pooled HR = 1.38, 95% CI [1.00, 1.90]). Four studies (n = 1234) examined mean platelet volume (MPV, median cut-off = 9.05 fL), which qualitatively demonstrated worse OS in patients with high MPV or high MPV: PC ratio. One study assessed platelet distribution width (PDW, threshold = 14.7 fL), finding worse OS in the high PDW group. High preoperative PLR is associated with poor prognosis in GBM, while high PC demonstrates borderline increased risk, which may help refine risk stratification and guide future mechanistic studies.
25 May 2026
Read appraisal →Neuroscience
MSCMH-Net: A multi-scale channel-mixing hybrid network for whole-brain segmentation
Whole-brain segmentation constitutes a fundamental task in medical image analysis, providing quantitative assessment of fine-grained brain regions and serving as a cornerstone for both clinical practice and neuroscience research. Despite its importance, the task is inherently challenging given the numerous brain regions, pronounced inter-class heterogeneity, and sophisticated inter-class spatial dependencies. Accurate whole-brain segmentation requires not only precise delineation of local features but also comprehensive modeling of long-range dependencies and global contextual information. To tackle these challenges, we propose the Multi-Scale Channel-Mixing Hybrid Network (MSCMH-Net), a CNN-MLP hybrid framework integrating convolutional and MLP modules at multiple hierarchical levels. The framework leverages the strengths of CNNs to capture local features and spatial structures, while employing MLPs to model long-range dependencies and global contextual information. For integrating global and local information, a channel-mixing module incorporating an exponential moving average (EMA) fusion strategy is employed. A composite dataset of 106 brain MR scans was used, including 36 from MICCAI-2012, 30 from ADNI and 40 from OASIS. Ground truth labels were annotated and double-checked by experts. Comprehensive experiments conducted on the composite dataset validate that MSCMH-Net achieves competitive results relative to existing approaches.
25 May 2026
Read appraisal →Lancet (London, England)
Endovascular thrombectomy for patients with large-core ischaemic stroke presenting up to 24 h after onset (ATLAS): a systematic review and individual patient data meta-analysis with central imaging adjudication
BACKGROUND: Patients with extensive ischaemic change are often excluded from endovascular thrombectomy. We aimed to synthesise the evidence from recent trials in these patients by performing a systematic review and individual patient data meta-analysis to estimate treatment benefit, including within clinical and imaging subgroups. METHODS: In this systematic review and meta-analysis, we searched PubMed and Embase for randomised trials published between March 1, 2018, and March 1, 2025, that evaluated efficacy and safety of endovascular thrombectomy compared with medical management in patients with large-core ischaemic stroke (based on an Alberta Stroke Program Early CT Score [ASPECTS] of ≤5 or estimated ischaemic core ≥50 mL) presenting within 24 h of onset. Individual patient-level data from all eligible trials were obtained. A central imaging core laboratory readjudicated ASPECTS and reanalysed ischaemic core volume. A two-stage meta-analysis with random-effects model was used to evaluate the distribution of 90-day modified Rankin Scale (mRS) scores (the primary outcome) using adjusted pooled generalised odds ratios (aGenORs). Missing data were handled by multiple imputation. Safety outcomes were all-cause mortality within 90-day follow-up and neurological worsening within 24-48 h of randomisation, reported as adjusted pooled relative risk (aRR); and symptomatic intracerebral haemorrhage within 36 h of randomisation (reported as risk difference). Subgroup analyses based on clinical and imaging characteristics were done, including subgroups defined by ischaemic core volume, ASPECTS, and time window from onset to randomisation. The meta-analysis was registered with PROSPERO (CRD420251058584). FINDINGS: We included 1886 patients (944 assigned to endovascular thrombectomy and 942 assigned to medical management) from six trials. Baseline characteristics were similar between treatment groups. At day 90, the distribution of mRS scores was improved in patients in the endovascular thrombectomy group (median score 4 [IQR 3-6]; n=940) versus those in the medical management group (5 [4-6]; n=931; aGenOR 1·63 [95% CI 1·42-1·88], p<0·0001). The endovascular thrombectomy group also had reduced mortality (292 [31·1%]) compared with the medical management group (347 [37·3%]; aRR 0·82 [95% CI 0·70-0·97], p=0·022). No significant differences were observed in symptomatic intracranial haemorrhage (ten [1·1%] of 944 vs nine [1·0%] of 942 patients; pooled unadjusted risk difference -0·17 percentage points [95% CI -1·01 to 0·67], p=0·69) or neurological worsening (197 [22·0%] of 896 patients vs 161 [17·9%] of 899; aRR 1·19 [0·87-1·62], p=0·27). Improved functional outcomes with endovascular thrombectomy were consistent across clinical and imaging subgroups, except for those with an estimated ischaemic core volume of 150 mL or greater, in whom point estimates favoured endovascular thrombectomy, particularly in the early time window (0-6 h), but wide 95% CIs limited interpretation. INTERPRETATION: Endovascular thrombectomy was associated with improved functional outcomes and reduced mortality versus medical management in patients with large-core ischaemic stroke presenting within 24 h of onset. With the exception of very extensive ischaemic changes (core volume ≥150 mL) presenting beyond 6 h, where evidence remains limited, benefit was sustained across ASPECTS and ischaemic core strata for patients presenting up to 24 h after onset. FUNDING: None.
24 May 2026
Read appraisal →Neurosurgical review
The safety and efficacy of perioperative nefopam for analgesia in spine surgery: A systematic review and meta-analysis of randomised controlled trials
OBJECTIVE: Moderate-to-severe pain is common after spine surgery. While opioids remain standard analgesia, their adverse effects have prompted opioid-sparing strategies. This systematic review evaluates the safety and efficacy of nefopam, a non-opioid and non-NSAID, as adjuvant perioperative analgesia in spine surgery. METHODS: Medline, Embase, Scopus and Cochrane databases were searched from inception to May 9, 2025. RevMan V5.4 was used to analyse mean differences (MD) or standardised mean differences (SMD) and 95% confidence intervals (CIs) for continuous outcomes and risk ratios (RR) with 95% CIs for dichotomous outcomes. The GRADE framework was used to assess the certainty of evidence. RESULTS: Seven randomised controlled trials (n = 553) were included. Nefopam did not reduce 24-hour morphine use (MD -1.47 mg; 95% CI: -3.86 to 0.92 mg; GRADE moderate), 24-hour incisional pain (SMD, -0.01; 95% CI -0.22 to 0.20; GRADE moderate), 48-hour incisional pain (SMD, -0.24; 95% CI -0.50 to 0.02; GRADE low), 24-hour neuropathic pain (SMD, -0.19; 95% CI -0.49 to 0.10; GRADE low), 72-hour neuropathic pain (SMD, -0.33; 95% CI -1.02 to 0.36; GRADE very low), or length of stay (MD, 0.08days; 95% CI -0.73 to 0.88days; GRADE Low). There were no significant differences in drug-related adverse effects (sedation (RR 1.30), nausea/vomiting (RR 1.03), dizziness (RR 1.14), and urinary retention (RR 2.36)), (GRADE: very low to low). CONCLUSION: Perioperative nefopam did not reduce acute morphine use, pain scores, hospital stay, or drug-related adverse events in spine surgery, though most studies used doses below the median effective dose, limiting conclusions on its efficacy and safety.
23 May 2026
Read appraisal →European radiology experimental
MRI radiomics-based approach to predict pituitary neuroendocrine tumor invasiveness
OBJECTIVES: To assess the diagnostic potential of magnetic resonance imaging (MRI) radiomics and machine learning models using T2-weighted and contrast-enhanced (CE)-T1-weighted images, individually and combined, to predict the invasiveness of pituitary neuroendocrine tumors (PitNETs). MATERIALS AND METHODS: Patients with macro-PitNETs were retrospectively enrolled from 2019 to 2022. Radiomic features were extracted from manually segmented lesions on preoperative T2-weighted and CE-T1-weighted images and, after a feature selection step, used to assess invasiveness, defined following Trouillas' classification. Five machine learning models (logistic regression, random forest, gradient boosting, AdaBoost, XGBoost) were trained using CE-T1-weighted, T2-weighted, and CE-T1-weighted plus T2-weighted features. Performance was evaluated on a test set using the area under the receiver operating characteristic curve (AUC). RESULTS: Two hundred patients were included in the study: 95 PitNETs were noninvasive (74 grade 1a; 21 grade 1b) and 105 invasive (70 grade 2a; 35 grade 2b). A total of 102 radiomic features were extracted per sequence. The best-performing model was the XGBoost, using five combined CE-T1-weighted and T2-weighted features, with an AUC of 0.85 (95% confidence interval: 0.75‒0.95). Lower AUC values were obtained for logistic regression using CE-T1-weighted images (0.80) and AdaBoost using T2-weighted images (0.78). CONCLUSION: The XGBoost model, incorporating tumor shape, texture, and first-order features extracted from both CE-T1-weighted and T2-weighted MRI, showed high performance in predicting PitNETs invasiveness. This radiomic model might help identify tumors with a higher risk of disease persistence, recurrence, or progression. RELEVANCE STATEMENT: The radiomic model based on contrast-enhanced T1-weighted and T2-weighted MRI demonstrated high discriminative ability in predicting invasiveness of pituitary neuroendocrine tumors and could aid in identifying tumors that may be at higher risk for recurrence or progression, ultimately improving patient outcomes through personalized treatment strategies. KEY POINTS: Pituitary neuroendocrine tumors (PitNETs) represent a significant challenge in clinical practice. Accurate preoperative prediction of PitNET invasiveness is crucial for surgery and prognosis. Contrast-enhanced T1-weighted and T2-weighted MRI-based radiomic model effectively predicts PitNET invasiveness. The developed radiomic model could help optimize individualized treatment decisions before surgery.
21 May 2026
Read appraisal →Neurosurgical review
Preoperative predictors of seizure outcomes after epilepsy surgery for mesial temporal sclerosis: A systematic review
Mesial temporal lobe epilepsy (MTLE) due to hippocampal sclerosis (HS) is a leading cause of drug-resistant epilepsy. Surgical resection, particularly anterior temporal lobectomy (ATL), achieves high rates of seizure freedom, but outcomes vary. Identifying reliable preoperative predictors may optimize patient selection and surgical success. To systematically evaluate preoperative clinical, neuroimaging, and neuropsychological factors associated with postoperative seizure outcomes in MTLE. A systematic review was conducted according to PRISMA 2020 guidelines. PubMed, Scopus, and Web of Science were searched for cohort studies (2010-2025) reporting predictors of seizure freedom after MTLE-HS surgery. Eligible studies assessed one or more preoperative factors (clinical, EEG, imaging, neuropsychological) in relation to postoperative outcomes. Data were extracted for qualitative synthesis, and methodological quality was assessed with the Newcastle-Ottawa Scale (NOS). From 615 records, 24 studies were included, encompassing patients treated with ATL, selective amygdalohippocampectomy (SAHE), or stereotactic laser ablation. Seizure freedom rates (Engel I/ILAE 1) ranged from 50% to 75%, with ATL achieving ~ 70% at 1-2 years. Multimodal concordance-MRI-visible HS, unilateral seizure onset on EEG, and concordant PET hypometabolism-was the strongest predictor of seizure freedom. Bilateral EEG/PET abnormalities consistently predicted poorer outcomes, whereas structural measures, such as hippocampal subfield volumes and HS subtypes, showed little prognostic value. Multimodal presurgical concordance is a robust predictor of favorable outcomes in MTLE-HS surgery, whereas bilateral or discordant findings indicate a higher risk of failure. Comprehensive presurgical evaluation remains essential to optimize surgical decision-making.
21 May 2026
Read appraisal →Neurosurgical review
Short-and long-term responsiveness of deep brain stimulation on motor and cognitive outcomes in GBA vs. Non-GBA parkinson's disease: a systematic review and meta-analysis of observational studies
Deep brain stimulation (DBS) is an established therapy for motor complications in Parkinson's disease (PD). Patients carrying glucocerebrosidase (GBA) mutations exhibit distinct disease trajectories, raising questions regarding potential differences in clinical outcomes following DBS compared with non-carriers. To evaluate short- and long-term motor, medication, and cognitive outcomes following DBS in patients with GBA-PD compared with non-GBA PD. We conducted a systematic review and meta-analysis of studies reporting clinical outcomes in PD patients with and without GBA mutations who underwent DBS and had a minimum follow-up of one year. Random-effects inverse variance models were applied, with subgroup analyses according to GBA status. DBS was associated with significant improvements in motor function in the off-medication state and sustained reductions in levodopa equivalent daily dose in both GBA carriers and non-carriers, with no significant between-group differences. Cognitive performance declined over long-term follow-up in both groups. At five years, greater cognitive decline, assessed using the Mattis Dementia Rating Scale, was observed among GBA-PD mutation carriers compared with non-carriers. Motor improvement and medication reduction following DBS were comparable between PD patients with and without GBA mutations. Over long-term follow-up, greater cognitive decline was observed among GBA-PD carriers.
21 May 2026
Read appraisal →PloS one
A novel hybrid framework integrating GA-driven 3D ResUNetGAN for MRI brain tumor segmentation
Accurate brain tumor segmentation by multi-modal MRI is crucial for diagnosis, treatment planning, and prognostic assessment. This work proposes a novel hybrid architecture within a GA optimized by 3D residual U-Net (ResUNet) with generative adversarial network (GAN) for the accurate segmentation of tumor subregions, namely the tumor core (TC), whole tumor (WT), and enhancing tumor (ET), using a dataset collected from BraTS2023 (437 training and 188 validation). By using GAs, we enable the computer to automatically find the best model structure and training settings, which helps keep the model simple enough to avoid overfitting while being powerful enough to generalise well to new data. The GAN part of our method trains the model to draw more realistic and consistent boundaries around tumor regions in MRI scans, thereby improving the overall quality of the segmentation. In our experiments, this GA-ResUNetGAN approach performed better than several leading methods, such as 3D UNet, DynUNet, UNETR, SwinUNETR, and the standard ResUNet, especially in accurately identifying TC, WT, and ET parts-achieving Dice scores of 0.94, 0.96, and 0.91 on the validation set. In addition, K-Fold cross-validation was performed to ensure consistent performance across different data splits. While the method involves more processing work than some baseline techniques, it provides improved segmentation quality and boundary delineation on the evaluated dataset. These results demonstrate the advantages of combining evolutionary optimization with adversarial deep learning for challenging medical imaging tasks.
19 May 2026
Read appraisal →Neurosurgical review
The impact of augmented reality on radiation exposure during spine surgery: a systematic review
BACKGROUND: Augmented reality (AR) has rapidly emerged as an important navigational technology in spine surgery, with growing interest in its potential to reduce dependence on fluoroscopy and mitigate radiation exposure for both patients and operating room staff. METHODS: This systematic review examined current evidence on radiation-related outcomes of AR-assisted spine procedures. A PRISMA-guided search of PubMed, Embase, and Scopus identified twelve eligible studies, including randomized trials, prospective and retrospective clinical cohorts, and cadaveric or synthetic-model investigations. RESULTS: Across the included studies, AR was consistently associated with reduced fluoroscopy use, with several studies demonstrating statistically significant reductions in exposure time compared with conventional fluoroscopy. Two clinical studies directly measured occupational radiation and reported substantially lower staff doses when AR-based navigation and optimized shielding strategies were employed. Patient radiation exposure was similarly decreased in most studies, particularly when AR was integrated with low-dose cone-beam CT protocols. Operative time findings were mixed, reflecting early learning curves and variability in AR systems, but accuracy remained high across platforms. CONCLUSION: Current evidence suggests that AR may reduce intraoperative radiation exposure without compromising workflow or surgical precision, available studies are limited by small sample sizes, heterogenous methodologies, and a paucity of direct staff-dosimetry data. Larger, high-quality multicenter studies are needed to clarify the magnitude of AR's radiation-sparing benefits and to define its role in modern spine surgery.
19 May 2026
Read appraisal →Pituitary
Pituitary adenoma and intracerebral aneurysms: case series, systematic review and meta-analysis
PURPOSE: Intracranial aneurysms (IAs) and Pituitary Adenoma (PA) coexistence has been reported for decades, yet available evidence remains fragmented. We performed a systematic review and meta-analysis following PRISMA 2020 guidelines to assess clinical features of patients with both conditions and quantify the prevalence of IAs in PA patients. METHODS: PubMed and Embase were searched up to December 15, 2025. Studies reporting coexistence of IAs and PAs were included. Individual patient-level data (Group 1) and aggregate prevalence data (Group 2) were analyzed separately. Risk of bias (RoB) was assessed using Joanna Briggs Institute tools. All analyses were performed using metaprop function from the meta package in R software. RESULTS: Seventy-one studies met inclusion criteria. Most studies have a low RoB. In Group 1 (74 patients), PAs were predominantly macroadenomas (91.9%), most frequently non-functioning (40.5%). IAs were mainly in the cavernous segment of the internal carotid artery (33%). IA diagnosis occurred significantly later than PA diagnosis (p < 0.01). In Group 2 (5264 patients), the pooled prevalence of IAs among PAs was 4% (95% CI 2-4%; I² = 92.1%, τ² = 1.1050, p < 0.0001). Sex-stratified prevalence was 8% (95% CI: 6%-9%) in females and 6% (95% CI: 4%-7%) in males. IAs sex-specific prevalence was significantly higher in both male and female PA patients as compared to the general population (p < 0.01). CONCLUSION: Patients with PAs show a higher IAs prevalence compared with the general population, likely reflecting combined hemodynamic, anatomical, and endocrine influences.
18 May 2026
Read appraisal →Computer methods and programs in biomedicine
Geometry-aware PointNet for rapid prediction of cerebral aneurysm hemodynamics
BACKGROUND AND OBJECTIVE: Cerebral aneurysms affect 2-5% of the global population and pose a significant health risk upon rupture. While computational fluid dynamics provides detailed hemodynamic information for risk assessment, its high computational demands limit routine clinical use. This study aims to develop a deep learning model to rapidly predict three-dimensional velocity fields and wall shear stress at peak systole using aneurysm geometry. METHODS: We synthesized a dataset of 984 idealized middle cerebral artery bifurcation aneurysms. For each case, computational fluid dynamics simulations were conducted with pulsatile boundary conditions to generate ground-truth data, and peak-systolic snapshots were extracted. We developed a single-input point-cloud network augmented with a distance-to-wall feature to predict both velocity fields and wall shear stress. Model performance was evaluated using mean absolute error (MAE), normalized MAE (NMAE), and relative L2 error (rL2). RESULTS: On the test set, the model achieved velocity-field accuracy of NMAE 4.05% and rL2 19.2% over the full geometry domain, and WSS accuracy of NMAE 2.59% and rL2 23.9%. The mean inference time was approximately 1.6 seconds for velocity and 0.3 seconds for wall shear stress per case. Out-of-distribution evaluation on non-idealized geometries showed substantial zero-shot degradation (NMAE 19.1%, rL2 62.4%), while leave-one-out fine-tuning improved performance (NMAE 10.8%, rL2 37.0%). CONCLUSIONS: The proposed geometry-aware point-cloud surrogate provides fast peak-systolic hemodynamic prediction on idealized aneurysm geometries. However, out-of-distribution evaluation indicates that broader patient-specific training, physiological boundary conditions, and reliability assessment are required before routine clinical application.
17 May 2026
Read appraisal →Spine
Identifying Predictors of Failed Back Surgery Syndrome Following Lumbar Spine Surgery: A Machine Learning Approach
STUDY DESIGN: Retrospective cohort study from a tertiary academic medical center. OBJECTIVE: To build a prognostic machine learning model to predict 1-year FBSS incidence after lumbar spine surgery. SUMMARY OF BACKGROUND DATA: A minority of patients who undergo degenerative lumbar spine surgery will have persistent postoperative pain, characterized as "Failed Back Surgery Syndrome" (FBSS). Adequate preoperative identification of patients at risk of having an undesirable outcome after surgery is an essential part of a spine surgeon's workflow. Although several studies have proposed mechanisms and risk factors for FBSS, no studies have developed a prognostic machine learning model to quantify and functionalize predictions. METHODS: A cohort of lumbar fusion and lumbar decompression surgeries was queried from a tertiary academic medical center from 2002 to 2022. Patient and operative characteristics were systematically extracted for each surgery. Several machine learning algorithms were used and optimized to predict FBSS occurrence within 1 year of surgery. SHAP feature importance values were computed for the top-performing model. RESULTS: A total of 10,128 unique lumbar decompression surgeries and 2890 unique lumbar fusion surgeries were included. The Random Forest model had the highest performance of tested models (AUROC of 0.715 for lumbar decompression, 0.701 for lumbar fusion). For lumbar decompression, the top three predictors of FBSS were absence of microdiscectomy, lack of preoperative immunosuppressant usage, and preoperative benzodiazepine usage. For lumbar fusion, prior FBSS diagnosis, lack of preoperative immunosuppressant usage, and operating room duration were the most important predictors. Other key variables spanned several domains, including preoperative medication usage, patient demographics, and operative indications and characteristics. CONCLUSION: This study demonstrates the successful creation of a prognostic machine learning model for prediction of FBSS within one year postoperatively. These models, after external validation, have the potential to be instrumental aspects of a spine surgeon's workflow. LEVEL OF EVIDENCE: Level III.
16 May 2026
Read appraisal →Journal of neurology, neurosurgery, and psychiatry
Comparison of neuropsychological side effects between contemporary radiofrequency ablative neurosurgery for psychiatric disorders and conventional neurosurgical procedures: systematic review and meta-analysis
BACKGROUND: Psychiatric disorders are increasingly contributing to global disability. Despite advances in conservative management, the prevalence of treatment-resistant cases remains high. Meanwhile, neurosurgery for psychiatric disorders (NPD) remains underused, largely due to strict regulations and historical concerns, particularly those related to neuropsychological side effects (NPSE). OBJECTIVE: To address this issue, we conducted a systematic review with meta-analysis to compare NPSE associated with radiofrequency ablative NPD to those observed in neuro-oncological, neurovascular and epilepsy surgeries. METHODS: PubMed, Embase and LILACS databases were searched in April 2024 for articles published in English/Spanish from 1990 to 2022, following Preferred Reporting Items for Systematic Reviews and Meta-analyses guidelines. RESULTS: A total of 48 articles with 2678 participants were included. The frequency of transient and permanent NPSE in the NPD group ranged from 0.94% to 11.50% and 0.94% to 2.03%, respectively, comparable to the other surgical groups (epilepsy: 0.31-11.70%; vascular: 0.52-22.90%; oncology: 0.94-17.60% for transient NPSE; epilepsy: 0.31-12%; vascular: 0.40-1.96% and oncology: 0.84-1.48% for permanent NPSE). Regarding permanent NPSE, arguably the most critical consideration, the NPD group showed better outcomes in memory, language and social cognition than the epilepsy group, but worse outcomes in executive and perceptual-motor functions. Compared with the vascular group, the NPD group had better executive function but worse complex attention. Finally, the NPD group had fewer permanent deficits than the oncology group in executive function, complex attention and perceptual-motor domains, although language performance was lower. CONCLUSIONS: Contemporary NPD apparently carries a similar risk of NPSE as other conventional neurosurgical procedures, challenging misconceptions and this unjustified barrier to its broader use.
16 May 2026
Read appraisal →Spine
Automated Classification of Cervical Spinal Stenosis Using Deep Learning on Computed Tomography Scans
STUDY DESIGN: Retrospective study. OBJECTIVE: To develop and validate a computed tomography-based deep learning (DL) model for diagnosing cervical spinal stenosis (CSS). BACKGROUND: Although magnetic resonance imaging (MRI) is widely used for diagnosing CSS, its inherent limitations, including prolonged scanning time, limited availability in resource-constrained settings, and contraindications for patients with metallic implants, make computed tomography (CT) a critical alternative in specific clinical scenarios. The development of CT-based DL models for CSS detection holds promise in transcending the diagnostic efficacy limitations of conventional CT imaging, thereby serving as an intelligent auxiliary tool to optimize health care resource allocation. MATERIALS AND METHODS: Paired CT/MRI images were collected. CT images were divided into training, validation, and test sets in an 8:1:1 ratio. The 2-stage model architecture employed: (1) A Faster R-CNN-based detection model for localization, annotation, and extraction of regions of interest (ROI), (2) Comparison of 16 Convolutional Neural Network (CNN) models for stenosis classification to select the best-performing model. The evaluation metrics included accuracy, F1-score, and Cohen κ coefficient, with comparisons made against diagnostic results from physicians with varying years of experience. RESULTS: In the multiclass classification task, 4 high-performing models (DL1-b0, DL2-121, DL3-101, and DL4-26d) achieved accuracies of 88.74%, 89.40%, 89.40%, and 88.08%, respectively. All models demonstrated >80% consistency with senior physicians and >70% consistency with junior physicians. In the binary classification task, the models achieved accuracies of 94.70%, 96.03%, 96.03%, and 94.70%, respectively. All 4 models demonstrated consistency rates slightly below 90% with junior physicians. However, when compared with senior physicians, 3 models (excluding DL4-26d) exhibited consistency rates exceeding 90%. CONCLUSIONS: The DL model developed in this study demonstrated high accuracy in CT image analysis of CSS, with a diagnostic performance comparable to that of senior physicians.
16 May 2026
Read appraisal →Journal of neurointerventional surgery
Long-term outcomes of the Woven EndoBridge device for intracranial aneurysms: systematic review and meta-analysis
BACKGROUND: The Woven EndoBridge (WEB) device is widely recognized as a safe and effective treatment for intracranial aneurysms (IAs). However, data on the long-term evolution of aneurysm occlusion remain limited. This meta-analysis evaluates the long-term (≥1 year) safety and efficacy outcomes of patients treated with the WEB device. METHODS: A comprehensive literature search was conducted in PubMed, Web of Science, and Scopus for studies published between January 1, 2011 and August 1, 2024 following PRISMA guidelines. Studies reporting outcome for IAs treated with the WEB device and a follow-up period of ≥1 year were included. Data were pooled using a random-effects model to account for variability across studies. RESULTS: A total of 25 studies including 1735 patients and 1768 aneurysms were analyzed (30.1% ruptured). The pooled adequate occlusion rates were 87.3% (95% CI 83.5% to 91.1%) at 1 year, 90.7% (95% CI 86.2% to 95.2%) at 1-2 years, 93.3% (95% CI 87.7% to 99.0%) at 3 years, and 88.4% (95% CI 80.5% to 96.4%) at 5 years. Adequate occlusion was achieved in 89.2% (95% CI 83.0% to 93.2%) of unruptured aneurysms and 85.9% (95% CI 80.2% to 90.1%) of ruptured aneurysms. The overall retreatment rate at the last long-term follow-up was 7.2% (95% CI 4.8% to 9.6%). No procedure- or device-related adverse events were reported beyond 1-year follow-up. Additionally, no cases of delayed rupture or aneurysm rebleeding were observed. CONCLUSION: This systematic review and meta-analysis confirms the high long-term efficacy and safety of the WEB device in treating both ruptured and unruptured aneurysms. The findings support the WEB device as a reliable and effective treatment option for IAs.
16 May 2026
Read appraisal →BMJ open
Prediction of Oswestry Disability Index and Numeric Rating Scale scores after lumbar spine surgery: machine learning model development and fairness assessment
BACKGROUND: One-third of patients operated for degenerative conditions in the lumbar spine do not report substantial improvement after 12 months. Most previous outcome prediction models are classifiers. This constrains nuances in prediction and use for decision support. OBJECTIVES: To develop and test models for the prediction of continuous outcome scores and retrieval of similar patients' outcomes, and to evaluate the models' fairness. SETTING: Norwegian public and private specialist healthcare. PARTICIPANTS AND DATA SOURCE: All cases recorded with an elective operation for lumbar disc herniation (LDH, n=18 377) or lumbar spinal stenosis (LSS, n=24 540) in the Norwegian Registry for Spine Surgery from 1 January 2007 to 23 May 2023. OUTCOME MEASURES: All outcomes were patient-reported 12 months after the operation. The primary outcome was the Oswestry disability index (ODI), modelled on a scale ranging from 0 to 100. Numeric Rating Scale scores (range 0-10) for back and leg pain were secondary outcomes. MODEL BUILDING AND PERFORMANCE: We selected 22 predictors recorded preoperatively by patients and clinicians based on Shapley Additive Explanations values. Data were split into 80%/20% training/test samples for LDH and LSS. Six machine learning methods for regression, that is, with a continuous outcome (extreme gradient boosting (XGBoost), Gaussian process regression, gradient boosting regression, artificial neural networks and linear regression), were trained for both conditions using fivefold cross-validation. We report the magnitude and distribution of errors as mean absolute error (MAE) with 95% CIs, and explanatory power as the coefficient of determination (R2). Fairness and calibration were assessed with violin and calibration plots of error. We developed a patient-similarity function that uses a K-nearest neighbour model to retrieve the individual outcomes of the 50 most similar patients and evaluated it by calculating L1 distances (Manhattan distances) across subgroups. RESULTS: XGBoost regression performed best for both conditions. The models showed good calibration and predicted ODI with MAE 11.32 (95% CI 11.00 to 11.63) and R2 0.27 (95% CI 0.24 to 0.29) for LDH and MAE 12.05 (95% CI 11.76 to 12.32) and R2 0.31 (95% CI 0.28 to 0.34) for LSS. The MAEs for back and leg pain were 2.09 (95% CI 2.04 to 2.15) and 1.95 (95% CI 1.90 to 2.00) for LDH and 2.33 (95% CI 2.28 to 2.38) and 2.13 (95% CI 2.08 to 2.16) for LSS. All models were fair with differences in error between subgroups for sex, age, education level and native language. In the patient-similarity function, distances at baseline were evenly distributed across subgroups. CONCLUSIONS: Our machine learning models predicted continuous outcomes with MAEs close to the SEs of measurements. The models were fair across sociodemographic subgroups. We succeeded in developing a patient-similarity function which supplements the predictions.
15 May 2026
Read appraisal →Fluids and barriers of the CNS
Cognitive assessment methods and outcomes following shunt surgery in idiopathic normal pressure hydrocephalus (iNPH): a systematic review and meta-analysis
INTRODUCTION: Core cognitive deficits in iNPH include slowed information processing, psychomotor slowing and executive dysfunction. However, cognitive outcomes following shunt surgery are not well understood. This review synthesised evidence on cognitive assessment methods and outcomes following shunt surgery in iNPH. METHODS: PubMed, Scopus, PsycINFO and Web of Science were searched for peer-reviewed studies including adults with iNPH who underwent shunt surgery and had within-subject cognitive evaluations pre- and post-operatively. Key data were extracted and study quality was assessed. Random-effects meta-analyses were performed on pooled baseline and post-shunt difference scores for frequently reported cognitive tests with comparable outcome data. RESULTS: Of 1,876 records, 195 met the inclusion criteria, comprising 11,445 patients. Cognitive evaluation methods ranged from subjective reports and NPH grading scales to brief screening tools and comprehensive test batteries. Over 193 distinct tests were reported and 54.4% of studies did not formally assess any core iNPH cognitive deficits. Post-shunt improvement rates, follow-up times and criteria for defining improvement varied widely. Eighty-five studies contributed data to meta-analyses of ten outcomes. Pooled estimates indicated post-shunt cognitive improvement, with Trail Making Test-A, Grooved Pegboard-Dominant and Trail Making Test-B showing changes exceeding thresholds for clinically significant improvement. CONCLUSIONS: Cognitive assessment in iNPH is highly heterogeneous and frequently omits core domains, limiting detection of treatment effects. When domain-relevant cognitive measures are used, shunt surgery is associated with statistically and clinically significant cognitive improvement. These findings highlight the need for standardised iNPH-appropriate cognitive evaluation tools with validated criteria for detecting clinically meaningful change and have direct implications for clinical assessment, interpretation of shunt response and the selection of cognitive endpoints in future interventional studies.
15 May 2026
Read appraisal →Neurosurgical review
Safety profile and surgical outcomes of the endoscopic transorbital approach as a skull base surgical corridor: a systematic review and meta-analysis
Endoscopic techniques have enabled minimally invasive approaches in neurosurgery, providing shorter recovery times and favorable outcomes. Among these, the endoscopic transorbital approach (ETOA) has emerged as a versatile surgical modality. Despite the growing body of evidence, complication rates associated with ETOA have not yet been systematically evaluated. We systematically searched PubMed, Embase, Scopus, and Web of Science up to March 2026. We included studies enrolling ≥ 5 patients who underwent ETOA as the sole surgical modality to treat both skull base and orbital lesions, providing data on early or long-term complications. A single-group meta-analysis was performed using a random-effects model with 95% confidence intervals. Heterogeneity was assessed with the I² statistic and further explored through Baujat plots and sensitivity analyses. A total of 11 observational studies, comprising 269 patients, were included. Overall, 21 different pathologies were reported. Meningioma represented the most frequent lesion (60.6% of cases), followed by schwannoma (12.0%), cavernous hemangioma (4.6%), and glioma (2.7%). Mean follow-up was 27.6 ± 15.1 months. CSF leak was observed in 1% (95% CI: 0.00 to 0.04, I² = 46.5%), and wound infection was observed in 3% (95% CI: 0.01 to 0.07, I²=0%). Ptosis occurred in 4% (95% CI: 0.00 to 0.14, I²=79.4%) and diplopia occurred in 6% (95% CI: 0.01 to 0.14, I²=68.9%). Medial gaze palsy occurred in 9% (95% CI: 0.04 to 0.18, I²=8.8%). Improvement in visual function was seen in 47% (95% CI: 0.22 to 0.73, I²=88.7%). Visual dysfunction occurred in 1% (95% CI: 0.00 to 0.04, I²=48.6%). Transient facial numbness occurred in 16% (95% CI: 0.09 to 0.25, I²=35.0%). Mortality was 0% (95% CI: 0.00 to 0.02, I²=28.7%). ETOA is a safe and promising technique for managing a wide range of skull base and orbital lesions. Future prospective and comparative studies are needed to refine indications and validate its long-term efficacy.
14 May 2026
Read appraisal →Experimental brain research
Subthalamic nucleus deep brain stimulation and associations with attention and processing speed in Parkinson's disease
Although subthalamic nucleus deep brain stimulation (STN DBS) is an effective treatment for the motor symptoms of Parkinson's disease (PD), its effects on cognitive functions are controversial. This cross-sectional study aimed to compare attention and processing speed in PD patients with STN-DBS and those receiving medical therapy, using a multimodal assessment combining P300 event-related potentials and neuropsychological tests. The study included 20 PD patients who underwent STN DBS and 17 PD patients who were followed with medical treatment. Demographic and clinical data for all patients were recorded. Cognitive functions were assessed using the P300 potential, the Stroop test (ST), and the Serial Digit Learning Test (SDLT). P300 potential latency and amplitude values, as well as neuropsychometric test results, were statistically compared between the two groups. P300 latency was shorter in the DBS-treated group than in the non-DBS group (p = 0.004). Performance times on Part III of the ST were shorter in the DBS-treated group (p = 0.03). In addition, a higher proportion of patients in the DBS-treated group performed normally on Part I of the ST compared to the non-DBS group (p = 0.03). There was no significant difference between the two groups in SDLT results. Shorter P300 latency and subtle differences in ST performance suggest a potential association between STN-DBS and the cognitive domains of attention and processing speed. Combining neuropsychological and electrophysiological assessments could provide a more comprehensive evaluation, and future large-scale, longitudinal studies are needed to clarify domain-specific cognitive effects.
14 May 2026
Read appraisal →Endocrine-related cancer
Systematic review of the molecular basis for cavernous sinus invasion in somatotropinomas
Somatotropinomas are a subtype of pituitary adenomas that have a particular predilection to invade the cavernous sinus. The objective of this systematic review was to examine the evidence regarding the molecular basis for cavernous sinus invasion in somatotropinomas. This review was conducted in accordance with the 2020 PRISMA guidelines on 13 April 2025. Inclusion criteria were reports of associations between somatotropinoma molecular changes and cavernous sinus invasion in adult patients. Title/abstract screening and full-text screening were performed, with studies assessed for risk of bias using the Newcastle-Ottawa scale. A total of 43 studies were identified, encompassing 1,824 patients (724 invasive tumours). Overall, 33 studies identified molecules that were upregulated in invasive tumours and 20 studies identified molecules that were downregulated. Few studies incorporated modern proteomic or transcriptomic techniques. Risk of bias was low with a mean Newcastle-Ottawa scale score of 7.0 (±0.6). Molecules associated with invasion were related to epithelial-mesenchymal transition (E-cadherin, ESRP1, fascin-1, and MMP-9), cellular proliferation (PTTG, AIP, TCERG1, EIF2β, E2F1, Notch 2, STAT3, ARRB1, TGFB1, SMAD3, SOX9, SGK1, MAGEA6 DLL3, EGFL7, and pEGFR), hormonal signalling (GNAS, DRD5, DRD1, sst5TMD4, SSTR2, and SSTR5), and tumour angiogenesis (VEGF and Drp1). These molecular variations present a possible explanation for the proclivity of somatotropinomas for the cavernous sinus. Identified molecules represent options for novel targeted therapies or biomarkers that could inform prognostication. Modern proteomic and transcriptomic techniques and larger somatotropinoma datasets are required to further elucidate the molecular pathways responsible for cavernous sinus invasion in somatotropinomas.
13 May 2026
Read appraisal →Neurosurgical review
Deep brain stimulation for freezing of gait in Parkinson's disease: An updated systematic review, meta-analysis, and a single-center clinical experience.
Freezing of gait is a disabling and treatment-resistant manifestation of Parkinson's disease (PD). The effectiveness of deep brain stimulation (DBS) for freezing of gait remains inconsistent across stimulation targets, frequencies, and medication states. We conducted a systematic review and meta-analysis following PRISMA guidelines to examine how DBS affects freezing of gait in patients with PD. We searched Medline, Scopus, Web of Science, and Cochrane up to September 28, 2025. For synthesis, we combined mean differences and 95% confidence intervals for the Freezing of Gait Questionnaire (FOG-Q) and the Unified Parkinson's Disease Rating Scale (UPDRS) part III across different medication and stimulation settings to calculate the final effect size. Thirty-one studies with 905 patients were included. Of these, 21 provided FOG-Q data, and all reported UPDRS-III results. DBS led to a modest decrease in FOG-Q scores (mean difference [MD] = - 2.99; 95% CI = - 5.69 to - 0.29). The biggest improvement in FOG was seen when stimulation was used while patients were off medication (Med-OFF/Stim-OFF vs. Med-OFF/Stim-ON: MD - 5.88; 95% CI - 9.28 to - 2.47). Stimulation during the medication-ON state had smaller effects (Med-ON/Stim-OFF vs. Med-ON/Stim-ON: MD - 2.65; 95% CI - 4.99 to - 0.32), and there was no significant benefit when comparing Med-ON/Stim-OFF to Med-OFF/Stim-ON (MD - 0.70; 95% CI - 3.88 to 2.48). UPDRS-III scores improved substantially in the medication-OFF state with stimulation (MD - 14.35; 95% CI - 17.39 to - 11.32). High-frequency stimulation targeting the subthalamic nucleus provided more consistent benefits, yet substantial variation persisted across studies. The results of our small cohort showed significant improvement in FOG-Q and UPDRS-III (P values = 0.034, 0.022, respectively). DBS improves freezing of gait primarily in the medication-OFF state, with greater effects observed using high-frequency stimulation and subthalamic nucleus targets. Significant heterogeneity and limited data for alternative targets warrant cautious interpretation and further controlled studies.
13 May 2026
Read appraisal →Neurosurgical review
Effectiveness and safety of proton therapy in intracranial meningioma treatment: a systematic review and meta-analysis
Meningiomas are the most common primary intracranial tumors, often treated surgically. However, complete resection is frequently limited by proximity to critical structures, necessitating adjuvant or definitive radiotherapy. Proton therapy offers dosimetric advantages over photon-based radiotherapy, particularly in sparing adjacent normal tissues. This study aims to systematically evaluate the effectiveness and safety of proton therapy for intracranial meningiomas across tumor grades and clinical scenarios. A systematic review and meta-analysis was conducted according to PRISMA 2020 guidelines using PubMed, EMBASE, Scopus, Web of Science, and Cochrane from inception to November 10, 2025. Studies were eligible if they reported clinical outcomes of proton therapy in ≥ 10 adult meningioma patients. Data extraction and risk-of-bias assessment were performed independently by two reviewers. Pooled complication rates and survival outcomes were calculated using random-effects models. Nineteen studies involving 1,431 patients were included. WHO Grade I tumors comprised 70.6% of cases; Grades II/III made up 25.2% and 4.2%, respectively. The most common proton dose regimens ranged from 13 to 70.2 Gy (RBE). The pooled complication rate was 16% (95% CI 5-27; p < 0.001; I² = 98.5%). Nine studies reported a statistically significant 5-year overall-survival proportion of 91% (95% CI 88-94; p < 0.001; I² = 49.3%). Radiologic local control averaged 71% (95% CI 50-86; I² = 88.2%). Proton therapy provides effective tumor control with acceptable toxicity, especially for low-grade or anatomically complex meningiomas. It is a valuable option for select patients, though further prospective studies are needed to optimize dosing and assess long-term outcomes.
13 May 2026
Read appraisal →Neurology
IV Fosphenytoin for Acute Trigeminal Neuralgia: A Multicenter, Randomized, Double-Blind, Placebo-Controlled Trial
BACKGROUND AND OBJECTIVES: Trigeminal neuralgia (TN) is a debilitating condition characterized by sudden, severe facial pain. IV medications for acute TN exacerbations have not been investigated in randomized controlled trials (RCTs). Oral medications are often insufficient for acute attacks, and surgery is not immediately available. We conducted an RCT to evaluate IV fosphenytoin therapy (IFT) as a rapid-acting rescue treatment for acute TN exacerbations. We hypothesized that, compared with placebo, IFT would reduce acute TN pain. METHODS: This multicenter, double-blind, placebo-controlled phase 3 trial was conducted at 6 institutions (April 2023-April 2024). Patients with classical or idiopathic TN who were experiencing TN exacerbation (numerical rating scale [NRS] score ≥5) were recruited from emergency and outpatient settings, and all study drugs were administered during hospital admission. Participants were randomized 1:1 to IFT (initial dose: 18 mg/kg, maintenance: 7.5 mg/kg for 4 days) or placebo. The primary end point was the change in NRS pain scores from baseline to 120 minutes after the initial dose. Secondary end points included attack frequency, the proportion achieving ≥50% NRS score improvement, and adverse events. Data were collected by blinded personnel and analyzed using repeated-measures mixed-effects models. RESULTS: Of 31 participants screened, 22 were randomized; 1 placebo-assigned participant did not meet the NRS ≥5 criterion and was excluded, leaving 21 for analysis (IFT: 11; placebo: 10). Participants had a mean age of 65.2 years (range 42-83; 8 men, 13 women). Compared with placebo, IFT significantly reduced pain (NRS change: -6.1 vs -2.4; between-group difference -3.8; 95% CI -6.4 to -1.1; p = 0.008), decreased attack frequency within 24 hours (2.5 ± 5.3 vs 16.1 ± 19.6, difference -13.6; 95% CI -26.4 to -0.7), and increased the proportion achieving ≥50% NRS improvement (90.9% vs 40.0%, difference 50.9%; 95% CI 5.6%-81.6%). Adverse events (somnolence, hypotension, and nausea) were mild and transient. DISCUSSION: IFT provided rapid and well-tolerated pain relief in acute TN exacerbations. Although findings are preliminary because of the small sample size, IFT may be a viable short-term treatment option, meriting further investigation. TRIAL REGISTRATION INFORMATION: Japan Registry of Clinical Trials, jRCT2011220043. Registered March 3, 2023. First enrollment April 25, 2023. jrct.mhlw.go.jp/en-latest-detail/jRCT2011220043. CLASSIFICATION OF EVIDENCE: This study provides Class I evidence that in patients with acute TN exacerbations, IV fosphenytoin is superior to placebo in reducing pain intensity at 120 minutes.
12 May 2026
Read appraisal →Journal of neuro-oncology
cGAS-STING agonists in preclinical glioblastoma animal models: a systematic review of tumor microenvironment modulation and survival outcomes
BACKGROUND/PURPOSE: Glioblastoma (GBM) is characterized by an immunosuppressive tumor microenvironment and poor responsiveness to immune checkpoint blockade, driving interest in cGAS-STING pathway activation to stimulate antitumor immunity. We performed a systematic review of preclinical in vivo studies evaluating STING agonists in glioblastoma, with emphasis on immune microenvironment effects and survival outcomes. METHODS: A systematic review of PubMed, Cochrane, and Embase was conducted through February 2025 following PRISMA guidelines. Studies were included if they evaluated STING agonists in live animal models of GBM and reported survival outcomes or tumor microenvironment changes. Two reviewers independently screened studies and extracted data. Risk of bias was assessed qualitatively based on study design and reporting characteristics. Given heterogeneity in models, treatments, and outcomes, results were synthesized descriptively. RESULTS: Fourteen studies met the inclusion criteria, spanning synthetic and natural cyclic dinucleotides and non-cyclic STING agonists. Across diverse delivery methods, including intracranial injection, hydrogels, and nanoparticle systems, STING agonists were associated with increased CD8 + T-cell and NK cell infiltration and repolarization of tumor-associated macrophages toward pro-inflammatory phenotypes. Several studies reported prolonged survival, including long-term tumor clearance in select models. Combination therapies with immune checkpoint inhibitors or radiotherapy showed synergistic effects in some studies. CONCLUSIONS: STING agonists can enhance anti-tumor immune responses and prolong survival in preclinical GBM models by promoting cytotoxic lymphocyte recruitment and remodeling the tumor-associated myeloid landscape. However, translation remains challenging due to limitations of current models, the limited clinical traction STING modulation has thus far achieved in other cancer types, incomplete understanding of cell-type-specific STING activation in the brain, and the possibility that sustained STING signaling may drive maladaptive inflammation rather than durable antitumor immunity.
12 May 2026
Read appraisal →Endocrine pathology
Lineage Classification of Pituitary Neuroendocrine Tumors From Whole-Slide Images Using Attention-Guided Graph Representation Learning
Pituitary neuroendocrine tumors (PitNETs) are common sellar neoplasms and represent a major component of routine pituitary pathology. In the 2022 World Health Organization (WHO) Classification, transcription factor-defined lineage assignment is central to diagnosis. However, lineage-related morphologic information on routine hematoxylin and eosin (H&E)-stained whole-slide images (WSIs) has not been systematically characterized. We developed an attention-guided graph neural network to predict PitNET lineage directly from H&E-stained WSIs and to identify regions prioritized for classification. Consecutive patients who underwent surgical resection for PitNETs at Beijing Tiantan Hospital between 2021 and 2025 were included. In the internal hold-out set, the five fold-specific models achieved a mean F1-score of 92.78% and a mean balanced accuracy of 94.84%. In a temporally independent validation cohort, the final model achieved an F1-score of 87.64% and a balanced accuracy of 89.48%. Performance varied across lineages and histomorphologic subtypes, and the most common error pattern was misassignment of PIT-1 and T-PIT tumors to SF-1. Attention maps predominantly highlighted tumor-rich regions. Quantitative cell-level morphometry supported lineage-associated patterns, including larger cell and nuclear sizes in PIT-1 tumors, more elongated nuclei in SF-1 tumors, and higher cellular density with reduced intercellular spacing in T-PIT tumors. In six cases with multiple synchronous PitNETs of distinct lineages, patch-level prediction maps corresponded closely to transcription factor immunohistochemistry. In a small exploratory subset with available DNA methylation data, methylation classifier results were concordant with model predictions in 11 of 15 cases and with routine histopathologic diagnoses in 8 of 15 cases. These findings indicate that routine H&E-stained WSIs contain learnable morphologic information related to PitNET lineage. Attention-guided spatial modeling provides an interpretable framework for characterizing lineage-associated patterns in PitNETs.
12 May 2026
Read appraisal →Biomedical physics & engineering express
Enhanced ResU-Net for brain tumor segmentation using EfficientNetB0, channel attention, and ASPP
Accurate and efficient segmentation of brain tumors is critical for diagnosis, treatment planning, and monitoring in clinical practice. In this study, we present an enhanced ResU-Net architecture for automatic brain tumor segmentation, integrating an EfficientNetB0 encoder, a channel attention mechanism, and an atrous spatial pyramid pooling (ASPP) module. The EfficientNetB0 encoder leverages pre-trained features to improve feature extraction efficiency, while the channel attention mechanism enhances the model's focus on tumor-relevant features. ASPP enables multi-scale contextual learning, which is crucial for handling tumors of varying sizes and shapes. The proposed model was evaluated on two benchmark datasets: The Cancer Genome Atlas Low Grade Glioma and brain tumor segmentation (BraTS-2020). Experimental results demonstrate that our method consistently outperforms the baseline ResU-Net and its EfficientNet variant, achieving dice similarity coefficient of 0.903 and 0.851, and HD95 scores of 9.43 and 3.54 for whole tumor and tumor core (TC) regions on the BraTS 2020 dataset, respectively. Compared to state-of-the-art methods, our approach shows competitive performance, particularly in whole tumor and TC segmentation. These results indicate that combining a powerful encoder with attention mechanisms and ASPP can significantly enhance BraTS performance. The proposed approach holds promise for further optimization and application in other medical image segmentation tasks.
11 May 2026
Read appraisal →AJNR. American journal of neuroradiology
Predicting Intracranial Aneurysm Rupture Risk and Intervention Outcomes Using Denoising-Enhanced CTA
BACKGROUND AND PURPOSE: Our aim was to develop a comprehensive multimodal framework for assessing the rupture risk of intracranial aneurysms and predicting intervention outcomes. In addition, it seeks to a novel denoising algorithm to enhance the quality of CTA images, thereby improving morphologic profiling. MATERIALS AND METHODS: This retrospective multicenter study included 352 patients with intracranial aneurysms who underwent CTA. A multimodal framework was developed, integrating 3 complementary feature sets: clinical variables, radiomic texture features, and deep learning-derived aneurysm morphologic data. A novel denoising algorithm was applied to improve image quality, thereby enhancing prediction performance. Model validation was performed through cross-validation, using multiple end points, including the Hunt-Hess, World Federation of Neurosurgical Societies (WFNS), and mRS grading systems. RESULTS: The multimodal framework demonstrated robust performance, achieving an area under the curve (AUC) of 0.896 [0.819-0.973] for aneurysm rupture prediction, outperforming conventional single-technique models (radiomics-based model: 0.752 [0.693-0.809]; deep learning-based model: 0.823 [0.789-0.827]). Incorporating the denoising technique further enhanced performance, with the AUC for rupture prediction increasing to 0.908 [0.836-0.981]. In clinical grading tasks, the model showed strong efficacy, achieving an AUC of 0.907 [0.845-0.968] for Hunt-Hess grading, 0.883 [0.662-0.988] for World Federation of Neurosurgical Societies grading, and 0.926 [0.879-0.973] for mRS. CONCLUSIONS: Our system demonstrates promising performance in predicting aneurysm rupture and clinical grading assessments, indicating its potential for comprehensive aneurysm evaluation. Moreover, the proposed denoising method effectively mitigates noise interference, enhances morphologic edge features, and improves the accuracy of existing models.
11 May 2026
Read appraisal →AJNR. American journal of neuroradiology
High-Resolution 2D versus 3D Lumbar Spine MRI Optimized with a Deep Learning Reconstruction Algorithm and Prototype Conformal Coil
BACKGROUND AND PURPOSE: Lumbar spine MRI is predominantly performed using 2D FSE sequences. 3D FSE sequences offer potential advantages over 2D, especially with recent advances in deep-learning reconstruction (DLR) and the use of conformal high-density coil arrays to improve the SNR. This study aimed to compare image quality and diagnostically relevant differences between 2D and 3D lumbar spine protocols, both using a prototype conformal coil and DLR. MATERIALS AND METHODS: Subjects with lumbar curvature referred for routine lumbar spine MRI were prospectively recruited (n=31). A prototype, conformal spine coil array with 70 total posterior receiver elements was used at 3T. DLR was applied to both the 2D- and 3D-protocols to improve sharpness and reduce noise. For 3D, a prototype DLR ("Sonic DL") technique was applied to provide higher acceleration factors. Three attending musculoskeletal radiologists assessed 2D and 3D T1-weighted (T1), T2-weighted (T2), and STIR sequences for image quality and diagnostic performance. The Gwet agreement coefficient (AC1, AC2) or intraclass correlation (ICC) was used to assess interrater agreement, while the Wilcoxon signed rank test or a sign test with Bonferroni correction assessed differences between 2D and 3D sequences. RESULTS: There was an overall 14% scan time reduction of 3D compared with 2D sequences, and a 38% time reduction for T2 sequences. All 3D sequences exhibited similar image quality to 2D. 3D T2 sequences had less CSF flow artifact than 2D T2 sequences. Interrater agreement was mostly comparable between all 2D and 3D assessments, including excellent agreement for the spinal canal area (ICC = 0.952 [95% CI: 0.907-0.976] for 2D, 0.941 [0.866-0.973] for 3D), good agreement for foraminal stenosis assessments on T2 sequences (AC2 = 0.713 to 0.795 for 2D, 0.706-0.832 for 3D), and good agreement for fracture detection on T1 sequences (AC1 = 0.869 for 2D, 0.815 for 3D). CONCLUSIONS: DLR-enabled 3D lumbar spine MRI offers comparable image quality to 2D with reduced overall scan time.
11 May 2026
Read appraisal →Biomedical physics & engineering express
Numerical investigation of neutron beam characteristics for the treatment of deep-seated brain tumour by boron neutron capture therapy
Objective.This study aims to investigate neutron beam characteristics for Boron Neutron Capture Therapy (BNCT) targeting brain tumours and to clarify the physical limitations of single-field irradiation for treatment of deep-seated tumours.Approach.Using Monte Carlo simulations with a voxelated Snyder head phantom, we systematically evaluated the impact of three key characteristics-neutron energy (mono-beam), beam radius, and current-to-flux ratio (J/Φ) -on dose distributions.Results.The analysis identified the 1-10 keV energy range as optimal for depth penetration. Increasing theJ/Φ was found to linearly enhance the tumour dose by improving beam directionality. However, a critical trade-off was observed with beam radius.Significance.These findings demonstrate the fundamental limits of single-field BNCT for deep-seated malignancies and highlight the necessity of multiple-irradiation strategies such as each beam should shape narrow, high-J/Φ epithermal beams. By establishing a database of each beam characteristics provides the essential physical foundation for designing future personalised and multi-beam treatment plans.
10 May 2026
Read appraisal →Biomedical physics & engineering express
Enhancing CNN regressors with contour encoding and self-supervision for improved 3D/2D x-ray to CT registration in spinal surgery navigation
With advances in deep learning, regression-based methods have shown promising results in 3D/2D medical image registration. However, strict intraoperative radiation dose constraints produce low-dose x-ray images with severe blur and reduced contrast, significantly degrading registration accuracy and limiting precise image-guided spinal interventions. We propose the Contour Encoding Regressor (CER), a novel end-to-end CNN framework that extracts highly discriminative features directly from binary contour masks of intraoperative x-rays without any restrictions on contour length, shape, or morphology. These contour features are efficiently encoded by a dedicated module and seamlessly fused into the regression pipeline to improve robustness against image degradation. To further enhance pose estimation, CER employs a dual-branch architecture that explicitly decouples rotational and translational parameters, thereby reducing mutual interference and improving overall accuracy. In addition, a self-supervised fine-tuning strategy with a tailored multi-component loss function is introduced to adapt the model to blurred low-dose conditions and minimize residual errors. On low-dose x-ray images, CER achieves a mean target registration error of 1.39 mm-a clinically acceptable threshold-while outperforming state-of-the-art methods in accuracy and enabling real-time performance (0.03-0.06 s per frame on clinically accessible GPUs). These improvements meet the stringent precision and speed requirements of intraoperative navigation, offering strong potential to enhance surgical safety and outcomes in minimally invasive spinal procedures.
10 May 2026
Read appraisal →Neurosurgical review
Deep brain stimulation for clozapine-resistant schizophrenia: a systematic review of target-specific outcomes and stereotactic technical considerations
Treatment-resistant schizophrenia (TRS) affects approximately 20-30% of patients, and a substantial proportion develop clozapine-resistant schizophrenia (CRS). Deep brain stimulation (DBS) has emerged as a potential neurosurgical intervention targeting dysfunctional cortico-striato-limbic circuitry. However, technical heterogeneity and limited clinical data constrain interpretation of outcomes. This systematic review was conducted in accordance with PRISMA guidelines and prospectively registered in PROSPERO (CRD420251080715). Seven electronic databases were searched from inception through January 31, 2025. Clinical studies investigating DBS in TRS or CRS were included. Methodological quality was assessed using Joanna Briggs Institute (JBI) tools. Data extraction emphasized stereotactic targeting methods, hardware configurations, stimulation parameters, and clinical outcomes. The total number of study is 6. We excluded paper by Manssuer 2023. The total study population comprises 21 patients. Seven studies involving 21 patients met inclusion criteria. Targets included the nucleus accumbens (NAcc; n = 11), substantia nigra (SNr; n = 1), habenula (HB; n = 2), subgenual cingulate (SCG; n = 4), subgenual anterior cingulate cortex (sgACC; n = 3). Reported PANSS total score changes ranged widely (11%-85.7%), reflecting substantial inter-individual variability and methodological limitations. Surgical complications occurred in 3 of 21 patients (14.2%), including infection and hemorrhage. All cases utilized open-loop stimulation and conventional cylindrical leads. Current evidence suggests a preliminary therapeutic signal for DBS in highly selected CRS patients, particularly with NAcc targeting. However, conclusions remain limited by small sample sizes, technical heterogeneity, and absence of controlled trials. Future investigations should prioritize standardized stereotactic reporting, volumetric lead reconstruction, and long-term safety assessment within specialized neurosurgical research settings. PROSPERO CRD420251080715.
10 May 2026
Read appraisal →Quality of life research : an international journal of quality of life aspects of treatment, care and rehabilitation
Quality of life after tranexamic acid in subarachnoid hemorrhage: post-hoc analysis of the ULTRA trial
PURPOSE: The ULTRA trial evaluated the impact of ultra-early and short-term tranexamic acid (TXA) treatment in patients with subarachnoid hemorrhage (SAH) and found no clinical benefit at six months. This post-hoc analysis examines whether TXA improves quality of life (QoL) at three and six months. METHODS: The ULTRA trial was a randomized, controlled, multicenter study conducted from July 2013 to July 2019. Patients received either TXA or standard care. This analysis included patients who completed at least one QoL questionnaire. The primary endpoint was QoL, assessed using the EQ-5D-3L questionnaire at three and six months. Linear mixed models adjusted for confounders were used to analyze the association between TXA and QoL. RESULTS: Of the 955 ULTRA patients, approximately 25% died, and 63% completed at least one QoL questionnaire. At three months, the TXA group had a mean EQ-5D index score of 0.75 versus 0.71 in the control group (p = 0.11) and a mean EQ-5D Visual Analogue Scale (VAS) score of 89 versus 86 (p = 0.10). At six months, the mean EQ-5D index score was 0.84 in the TXA group compared to 0.82 in the control group (p = 0.23), and the mean VAS was 92 in the TXA group compared to 89 in the control group (p = 0.13). CONCLUSION: Ultra-early and short-term TXA did not result in a significant improvement in QoL at three or six months in patients with SAH. Given the lack of benefit on both clinical outcome and QoL, routine use of TXA is not recommended. TRIAL REGISTRATION: Netherlands Trial Register: NTR3272. CLINICALTRIALS: gov: NCT02684812.
10 May 2026
Read appraisal →Neurosurgical review
Sequesterectomy versus standard micro‑/open discectomy for lumbar disc herniation: a systematic review and meta-analysis
Lumbar disk herniation is a common clinical entity affecting about 1% of the entire population every year. The purpose of the present work is to provide a systematic review and meta-analysis comparing the safety and efficiency of sequesterectomy and discectomy in the management of lumbar disk herniation. A systematic review and meta-analysis using the random effects method was performed. This search was applied through the 6th of March 2025 to PubMed, Scopus, Cochrane Central Register of Controlled Trials and the Directory of Open Access Journals. The data collected included patient demographics, spinal level at which the operation occurred, duration of operation and hospital stay, outcome, recurrence rate as well as potential immediate and delayed complications. A total of 18 original studies with a cumulative number of 4394 patients were identified. No statistically significant difference was found in the re-herniation and complication rate between the two groups (OR: 1.058, 95% CI: 0.726-1.541, p=.769 and OR: 1.399, 95% CI: 0.964-2.032, p=.077 respectively). The same applied for mean hospital stay (standard difference in means: 0.206, SE = 0.167, p= .219). In contrast, mean operating time was found to be significantly shorter in the sequesterectomy group than in the discectomy group (mean 58.086 min versus 72.885 min respectively). As or the patient reported outcomes, VAS score for back pain two years after the operation was the only index that was significantly higher in patients with discectomy (standard difference in means: 0.348, SE = 0.172, p= .04). Based on the available data, the two approaches do not differ in terms of risk of reherniation, reoperation rate and postoperative complications. Nevertheless, patients that have undergone sequesterectomy could potentially benefit from a more significant reduction in back pain in the long run.
10 May 2026
Read appraisal →Epilepsy research
Independent evaluation of deep learning models for detecting focal cortical dysplasia
The purpose of this study is to perform an independent assessment of three state-of-the-art tools for the detection of focal cortical dysplasia (FCD) from Magnetic Resonance images (MRI). These tools include DeepFCD, the Multi-center Epilepsy Lesion Detection (MELD) Classifier, and MELDGraph. T1-weighted and fluid-attenuated inversion recovery MRIs from 101 epilepsy patients with FCD and 101 epilepsy patients without FCD were retrospectively included. Classifiers were evaluated at patient-level by their ability to correctly identify the presence of any FCD lesions, and at lesion-level by their capacity to identify lesions within regions delineated by neuroradiologists in MRI reports. A calibrated threshold for DeepFCD prediction probabilities was empirically determined to improve classifier specificity. Classifier test-retest consistency was measured using the Dice coefficient on repeated MRI scans of 21 individuals. At patient-level, MELDClassifier achieved 52% accuracy (sensitivity=91%, specificity=14%), MELDGraph reached 61% accuracy (sensitivity=76%, specificity=47%) and DeepFCD performed with 56% accuracy (sensitivity=62%, specificity=50%) at an empirically determined threshold of 0.90. At lesion-level, MELDClassifier performed with a sensitivity of 70% and a positive predictive value (PPV) of 13%. MELDGraph reached 53% sensitivity and PPV of 36%, whereas the DeepFCD performed with 30% sensitivity and PPV of 19%. Test-retest reliability was low, with an average [min, max] Dice coefficient of 0.28 [0.0, 1.0] for MELDClassifier, 0.38 [0.0, 1.0] for MELDGraph, and 0.35 [0.05, 0.54] for DeepFCD. This study highlights the current limitations of using deep learning models in FCD diagnosis and emphasizes the need to enhance the tools' accuracy, reliability, and interpretability to improve clinical utility.
9 May 2026
Read appraisal →Neural networks : the official journal of the International Neural Network Society
MGML: A plug-and-play meta-guided multi-modal learning framework for incomplete multimodal brain tumor segmentation
Leveraging multimodal information from Magnetic Resonance Imaging (MRI) plays a vital role in lesion segmentation, especially for brain tumors. However, in clinical practice, multimodal MRI data are often incomplete, making it challenging to fully utilize the available information. Therefore, maximizing the utilization of this incomplete multimodal information presents a crucial research challenge. We present a novel meta-guided multi-modal learning (MGML) framework that comprises two components: meta-parameterized adaptive modality fusion and consistency regularization module. The meta-parameterized adaptive modality fusion (Meta-AMF) enables the model to effectively integrate information from multiple modalities under varying input conditions. By generating adaptive soft-label supervision signals based on the available modalities, Meta-AMF explicitly promotes more coherent multimodal fusion. In addition, the consistency regularization module enhances segmentation performance and implicitly reinforces the robustness and generalization of the overall framework. Notably, our approach does not alter the original model architecture and can be conveniently integrated into the training pipeline for end-to-end model optimization. We conducted extensive experiments on the public BraTS2020 and BraTS2023 datasets. Compared to multiple state-of-the-art methods from previous years, our method achieved superior performance. On BraTS2020, for the average Dice scores across fifteen missing modality combinations, building upon the baseline, our method obtained scores of 87.55, 79.36, and 62.67 for the whole tumor (WT), the tumor core (TC), and the enhancing tumor (ET), respectively. We have made our source code publicly available at https://github.com/worldlikerr/MGML.
9 May 2026
Read appraisal →Magnetic resonance in medicine
Dynamic-Guided Diffusion Probability Model for Cranial Nerves Segmentation
PURPOSE: Segmentation of cranial nerves (CNs) bundles using magnetic resonance imaging (MRI) provides a valuable quantitative approach for analyzing the morphology and orientation of individual CNs. Currently, the CN regions can be segmented directly using deep learning-based methods. However, existing methods overlook the unique characteristics of CNs, particularly their environmental features and representation in multimodal images that may lead to suboptimal segmentation outcomes. METHODS: We proposed a dynamic-guided diffusion probability model for CNs segmentation, which enhances segmentation performance by integrating the intrinsic characteristics of CNs. A dynamic-guided mechanism approach called the SE-A-NL module was proposed. The module is capable of addressing both the varying characterization abilities of multimodal images and the long-range connections of CNs within images. RESULTS: Quantitative and qualitative experiments demonstrate that the proposed method surpasses current state-of-the-art approaches, delivering accurate and effective segmentation of five pairs of cranial nerves. Notably, the method outperforms existing techniques in 16 out of the 20 evaluated metrics. CONCLUSION: The overall network model effectively integrates multimodal information and anatomical priors by combining multi-channel attention and non-local attention mechanisms, thereby improving CNs segmentation performance. Thorough comparative and ablation studies highlight the superior performance of the proposed method.
5 May 2026
Read appraisal →European radiology
A deep learning model to reduce agent dose for contrast-enhanced MRI of the cerebellopontine angle cistern
OBJECTIVES: To evaluate a deep learning (DL) model for reducing the agent dose of contrast-enhanced T1-weighted MRI (T1ce) of the cerebellopontine angle (CPA) cistern. MATERIALS AND METHODS: In this multicenter retrospective study, T1 and T1ce of vestibular schwannoma (VS) patients were used to simulate low-dose T1ce with varying reductions of contrast agent dose. DL models were trained to restore standard-dose T1ce from the low-dose simulation. The image quality and segmentation performance of the DL-restored T1ce were evaluated. A head and neck radiologist was asked to rate DL-restored images in multiple aspects, including image quality and diagnostic characterization. RESULTS: 203 MRI studies from 72 VS patients (mean age, 58.51 ± 14.73, 39 men) were evaluated. As the input dose increased, the structural similarity index measure of the restored T1ce increased from 0.639 ± 0.113 to 0.993 ± 0.009, and the peak signal-to-noise ratio increased from 21.6 ± 3.73 dB to 41.4 ± 4.84 dB. At a 10% input dose, using DL-restored T1ce for segmentation improved the Dice from 0.673 to 0.734, the 95% Hausdorff distance from 2.38 mm to 2.07 mm, and the average surface distance from 1.00 mm to 0.59 mm. Both DL-restored T1ce from 10% and 30% input doses showed excellent image quality (3, interquartile range (IQR) [Q3-Q1] = 3-3 and 3, IQR [Q3-Q1] = 4-3), with the latter being considered more informative (4, IQR [Q3-Q1] = 4-3). CONCLUSION: The DL model improved the image quality of low-dose MRI of the CPA cistern, which makes lesion detection and diagnostic characterization possible with 10-30% of the standard dose. KEY POINTS: Question Deep learning models that aid in the reduction of contrast agent dose are not extensively evaluated for MRI of the cerebellopontine angle cistern. Findings Deep learning models restored the low-dose MRI of the cerebellopontine angle cistern, yielding images sufficient for vestibular schwannoma diagnosis and management. Clinical relevance Deep learning models make it possible to reduce the use of gadolinium-based contrast agents for contrast-enhanced MRI of the cerebellopontine angle cistern.
4 May 2026
Read appraisal →European radiology
Predicting molecular types of adult-type diffuse gliomas based on MRI reports with large language models
OBJECTIVES: To evaluate the performance of large language models (LLMs) in predicting molecular types of adult-type diffuse gliomas according to the 2021 WHO classification using MRI radiology reports. MATERIALS AND METHODS: This retrospective study included 2169 patients diagnosed with adult-type diffuse gliomas (294 oligodendrogliomas, 295 IDH-mutant astrocytomas, and 1580 IDH-wildtype glioblastomas) between July 2005 and March 2024 from four hospitals in Asia and Europe. Seven proprietary and open-source LLMs were assessed: GPT-4o-mini, GPT-4.1-mini, Llama 3.1 8B, Llama 3.1 70B, Qwen2.5 7B, Deepseek-r1 8B, and Mistal 7B. The performance of LLMs in classifying molecular types was compared based on the provision of relevant knowledge of glioma imaging findings (knowledge-based vs. naïve prompt). The impact of radiologists' subspecialization in neuro-oncology, report quality, and reporting language on LLMs' performance was also evaluated. RESULTS: LLMs achieved significantly higher (naïve vs. knowledge-based; GPT-4o-mini, 77.0% vs. 79.1%, p < 0.001; Qwen2.5 7B, 75.9% vs. 79.5%, p < 0.001; Deepseek-r1 8B, 66.0% vs. 73.2%, p < 0.001) or comparable accuracy (GPT-4.1-mini, 78.7% vs. 78.6%; Llama 3.1 70B, 78.0% vs. 78.1%; Mistral 7B, 58.4% vs. 57.4%) using knowledge-based prompt compared to naïve prompt, except for Llama 3.1 8B (65.4% vs. 44.6%, p < 0.001). Differences in accuracy were more pronounced in smaller-sized LLMs. Additionally, the accuracy was significantly higher with reports by neuro-oncology specialists and high-quality reports in all LLMs (p < 0.001). CONCLUSIONS: LLMs may provide preoperative information on the tumor types of adult-type diffuse gliomas from MRI reports by providing relevant knowledge in the prompt. Informative and descriptive reports could further enhance LLMs' performance. KEY POINTS: Question Our study aimed to evaluate large language models' (LLMs) ability to efficiently predict molecular types of adult-type diffuse gliomas according to the 2021 WHO classification. Findings Larger models generally showed better accuracy and were less sensitive to domain-specific knowledge. Their performance improved when using high-quality, longer reports or reports by neuro-oncology specialists. Clinical relevance These findings highlight the potential role of LLMs in predicting glioma molecular types, underscoring the importance of informative and descriptive reports in enhancing their performance.
4 May 2026
Read appraisal →Magnetic resonance in medical sciences : MRMS : an official journal of Japan Society of Magnetic Resonance in Medicine
Visualization of the Trochlear Nerve Using Deep Learning-enhanced 3D T2-weighted MR Imaging at 3T
PURPOSE: Cranial nerve imaging with 3T MRI commonly uses 3D fast imaging employing steady-state acquisition (3D-FIESTA); however, this sequence has limitations in achieving higher spatial resolution and provides poor tissue contrast between cranial nerves and adjacent vascular structures. We evaluated 3D T2-weighted imaging (T2-CUBE) with deep learning-based reconstruction (DLR) for cranial nerve visualization, focusing on the trochlear nerve, the smallest cranial nerve with the longest intracranial course, and compared it with T2-CUBE without DLR and 3D-FIESTA. METHODS: Ten healthy male volunteers (age, 23-40 years; mean age, 32 years) underwent T2-CUBE with and without DLR, and 3D-FIESTA at 3T. Two neuroradiologists independently evaluated trochlear nerve visualization in 4 anatomical segments (origin from the midbrain, cisternal, tentorial, and anterior portion of its cavernous segments) using a 3-point scale, and SNR of the pons (SNRPONS) and cerebrospinal fluid (SNRCSF) were calculated. RESULTS: T2-CUBE with DLR achieved a 100% visualization across all trochlear nerve segments and demonstrated significantly better visualization than both T2-CUBE without DLR and 3D-FIESTA (P < 0.025). T2-CUBE without DLR showed 67.5%-100% visualization across the 4 segments. 3D-FIESTA showed 32.5%-80% visualization of the origin from the midbrain, cisternal, and tentorial segments, with no visualization of the cavernous segments. DLR increased SNRPONS and SNRCSF by factors of 1.8-2.5 (SNRPONS: 14.1 vs 5.7; SNRCSF: 31.8 vs 17.5, respectively; P < 0.001). T2-CUBE with DLR demonstrated significantly higher SNRPONS than 3D-FIESTA (14.1 vs 6.4, P < 0.001), while SNRCSF was comparable (31.8 vs 36.3, P = 0.20). CONCLUSION: T2-CUBE with DLR at 3T provided a significantly better trochlear nerve visualization than T2-CUBE without DLR and 3D-FIESTA. This technique may extend beyond the trochlear nerve to other cranial nerves and to the evaluation of neurovascular compression in the cistern, with the potential to become the new standard for cisternal imaging.
3 May 2026
Read appraisal →Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer
Conducting a randomized controlled clinical trial on palliative care in patients with glioblastoma - what are the challenges?
PURPOSE: Patients with glioblastoma represent a highly vulnerable cohort as they often experience rapid health deterioration with severe symptom burden including neurological, (neuro)psychological, and psychiatric symptoms. The aim of this sub-analysis of the "Early Palliative Care for Patients with Glioblastoma" (EPCOG) trial was to investigate the specific challenges of conducting a multicenter, randomized, controlled, clinical trial in glioblastoma patients testing a specialized palliative care (PC) intervention. METHODS: We analyzed screening protocols and protocol deviations with respect to number and reasons for non-participation, skipped/delayed visits and attrition using descriptive statistics and content analysis of free-text comments. RESULTS: In total, 41.5% of 556 screened patients were enrolled. Main reasons for non-participation were lack of interest (25.7%) and low functional status (11.5%). Attrition due to death (57.6%) was higher than due to illness (5.2%) or other reasons (21.2%). Main reasons for visit deviations were structural issues (in > 50% of neurosurgical visits), health status, and patient request. Protocol deviations showed that specialized PC intervention visits were least frequently skipped (4.5%) compared to study-specific outcome assessment (10.1%) and neurosurgical (43.3%) visits. Further, only 11.0% of the specialized PC intervention visits were delayed compared to 22.3% of the outcome assessment and 56.4% of the neurosurgical visits. CONCLUSION: In this clinical trial involving glioblastoma patients, a high level of motivation among the study participants could be reached, as reflected by low protocol deviations during the specialized PC intervention and study-specific outcome assessment visits. Reasons for this might be a close guidance as well as a patient and caregiver-oriented communication, e.g., by a personal contact of the PC team in the intervention group, personal outcome assessment visits at patients' whereabouts, or the inclusion of a study nurse at each site. Considering the high vulnerability of glioblastoma patients is crucial when designing and conducting clinical trials.
2 May 2026
Read appraisal →Child's nervous system : ChNS : official journal of the International Society for Pediatric Neurosurgery
Structural equation modeling of findings in pediatric tele-neuroradiology: a 2-year nationwide study of turnaround time predictors and clinical decision support
BACKGROUND: Pediatric neuroradiology faces significant workforce shortages, with teleradiology emerging as a vital solution. However, studies investigating findings and their operational impact from teleradiology centers remain limited. OBJECTIVES: To develop and validate structural equation models for identifying predictors of turnaround time and formulate recommendations for workflow optimization in pediatric tele-neuroradiology services. DESIGN: A retrospective cohort study following STROBE guidelines. SETTINGS: 107 hospitals across 17 states in the United States (US) via a teleradiology platform providing interpretation services through US board-certified radiologists. PATIENTS AND METHODS: We analyzed 9985 pediatric neuroradiology scans from 7958 patients (January 2023-December 2024). We utilized confirmatory factor analysis to validate findings structures, followed by structural equation modeling to predict turnaround times. Binary logistic regression models were developed with area-under-the-curve (AUC) estimation for performance assessment. Bootstrap validation with 5000 samples ensured model stability. MAIN OUTCOME MEASURES: Primary outcome was turnaround time. Secondary outcomes included requirements for multiple imaging studies, follow-up recommendations, and consultations. SAMPLE SIZE: A total of 9985 studies providing over 99% statistical power for detecting significant relationships. RESULTS: Factor analysis demonstrated a two-factor structure (trauma: α = 0.742, structural: α = 0.685). The structural model explained 7.8% of turnaround time variance, with computed tomography (CT) modality (β = -0.164), trauma score (β = 0.125), and structural score (β = 0.142) as significant predictors. Among immediate neurosurgical emergencies (n = 180, 1.8%), 89.4% achieved turnaround time within the 60-min benchmark for time-sensitive consultations. Prediction models demonstrated excellent discrimination: traumatic findings (AUC = 0.91), structural findings (AUC = 0.92), critical findings (AUC = 0.95), and a dedicated neurosurgical emergency model (AUC = 0.94, NPV = 0.996). A severity classification system showed strong validation against imaging needs (AUC = 0.76) and consultations (AUC = 0.89). CONCLUSIONS: Our study establishes a validated SEM framework for pediatric tele-neuroradiology with excellent predictive performance (AUC = 0.91-0.95). Among immediate neurosurgical emergencies (n = 180, 1.8%), 89.4% met the 60-min benchmark, and a dedicated emergency prediction model achieved AUC = 0.94. However, translation to improved neurosurgical care delivery and patient outcomes remains unvalidated, representing the next investigational priorities. LIMITATIONS: Retrospective design limits causal inference; a single platform may limit generalizability; the CT majority (96.8%) limits magnetic resonance imaging conclusions. Critically, post-diagnostic clinical outcomes, including neurosurgical consultations, interventions performed, and patient outcomes, were not tracked, precluding conclusions about whether documented operational efficiency translated to improved neurosurgical care delivery.
2 May 2026
Read appraisal →Cell reports. Medicine
Bed nucleus of the stria terminalis-nucleus accumbens stimulation for depression: A randomized, double-blind, crossover trial
Although deep brain stimulation (DBS) shows potential in treatment-resistant depression (TRD), the efficacy remains controversial. To assess the efficacy of DBS of the bed nucleus of the stria terminalis (BNST) and nucleus accumbens (NAc) for TRD, we conduct a randomized, double-blind, crossover trial after an open-label optimization stage. Stimulation leads to a mean decrease in the Hamilton Depression Scale-17 (HAMD) scores of 10.1 points (p < 0.001) with a 50% response rate at the end of the open-label stage. Anxiety, quality of life, and disability are also improved. The HAMD scores are significantly lower in patients during active DBS than during sham DBS (p < 0.001). Serious adverse events include suicide (1 patient) and seizure (1 patients). With individual stimulation analysis, we identify optimal stimulation sites, fiber tracts, and functional networks (false discovery rate [FDR] p < 0.05). This study demonstrates the efficacy and safety of BNST-NAc DBS for TRD and reveals optimal brain targets for stimulation. This study was registered at ClinicalTrials.gov (NCT04530942).
25 Apr 2026
Read appraisal →PloS one
LHW-Net: An ensemble-based machine learning framework for brain tumor classification
The classification of brain tumors is an unsolved problem associated with heterogeneity of tumors and fluctuations in imaging conditions. In this work, the investigation introduces a powerful novel framework, named LHW-Net that combines handcrafted features called local binary patterns (LBP), histogram of oriented gradients (HOG), and wavelet transform (WT). Within the LHW-Net framework, the extracted features are utilized in different machine learning classifiers, such as K-Nearest Neighbors (KNN), Random Forest (RF) and Support Vector Classifier (SVC). The results of the individual classifiers are further combined using probabilistic score fusion approach to improve classification performance. The effectiveness and robustness of the proposed work are validated by the achieved experimental results on commonly accepted benchmark datasets.
24 Apr 2026
Read appraisal →PloS one
Controlled comparative study of YOLOv8-Pose, YOLOv11-Pose, and Detectron2 for vertebrae detection and keypoint estimation
Accurate vertebrae detection with precise keypoint localization is essential for medical image analysis and clinical applications, such as spinal alignment assessment. This study presents a controlled, task-driven comparison of four pose-based deep learning models for vertebrae detection and keypoint estimation: YOLOv8n-Pose, YOLOv11n-Pose, and Detectron2 (Keypoint R-CNN) with ResNet-50 and ResNet-101 backbones. A single-class vertebrae dataset with bounding box annotations and four anatomically meaningful keypoints per vertebra was evaluated under consistent training settings. Performance was assessed in terms of keypoint localization accuracy, detection precision, inference speed, and vertebrae-specific prediction behavior, including detection completeness and duplicate detections, which are critical for clinical usability. Results show that YOLOv11n-Pose provides the best balance between keypoint accuracy and inference efficiency, while YOLOv8n-Pose achieves the fastest inference with competitive performance. Detectron2-based models exhibit lower keypoint accuracy, slower inference, and frequent duplicate predictions that obscure correct anatomical landmarks. Additional experiments indicate that larger YOLO variants (particularly YOLOv8l-Pose) improve accuracy, albeit at increased computational cost. Overall, the results demonstrate that model capacity or architectural recency alone does not guarantee superior performance in vertebrae keypoint detection, highlighting the importance of anatomy-aware model selection for spine imaging applications.
23 Apr 2026
Read appraisal →Journal of Korean medical science
Comparison of Clinical and Radiological Outcomes Between Suction Aspiration and Combination Methods of Mechanical Thrombectomy in Patients With Acute Cerebral Infarction: The COMPETE Trial
BACKGROUND: Recent advances in suction catheter technology suggest that suction aspiration may prevent thrombus fragmentation during mechanical thrombectomy. We therefore hypothesize that the radiological outcomes of suction aspiration as a first-line treatment would not be inferior to those of the combination technique. This study aims to evaluate the radiological and clinical outcomes of first-line suction aspiration compared with those of the first-line combination technique for large artery occlusion amenable to both modalities. METHODS: The COMPETE trial is a prospective, randomized, multicenter, noninferiority, open-label trial. A total of 1,136 patients will be randomized at a 1:1 ratio to either the suction aspiration or combination technique groups. RESULTS: The primary endpoints are successful recanalization (modified Thrombolysis in Cerebral Infarction scale score ≥ 2b) and a good clinical outcome (modified Rankin Scale score of 0-2) at 90 days after thrombectomy. The technical outcome is the switching rate from the combination technique to suction aspiration and from suction aspiration to the combination technique. The safety outcomes include procedural morbidity, nonprocedural morbidity, procedural mortality, and nonprocedural mortality. CONCLUSION: The COMPETE trial is expected to determine whether the use of suction aspiration as a first-line approach in patients with acute ischemic stroke is noninferior to the combination technique in achieving successful radiological and good clinical outcomes. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT06254755; CRIS (KCT0007726).
23 Apr 2026
Read appraisal →Journal of medical Internet research
The Real-Time Support Role of Augmented Reality Technology in Shared Decision-Making in Neurosurgery Under the SEGUE Framework: Randomized Controlled Trial
BACKGROUND: Preoperative risk communication is essential for shared decision-making (SDM) in neurosurgery; however, conveying complex neuroanatomy and surgical risks using traditional verbal explanations can limit understanding and contribute to dissatisfaction and medicolegal disputes. Augmented reality (AR) may provide patient-specific, interactive 3D visualization to support these conversations. OBJECTIVE: This study evaluates whether AR-assisted preoperative risk communication improves objective understanding and other SDM-related outcomes, compared with communication supported by a conventional physical anatomical model within a standardized SEGUE-informed protocol. METHODS: A prospective, single-center, randomized controlled trial was conducted with 62 neurosurgery communication recipients (patients when capable; otherwise, a legally authorized representative [LAR]). Patients were stratified by planned surgical approach (frontal, parietal, and occipital) and, within each stratum, were randomized into an experimental AR group and a control physical-model group. The primary outcome was postsession objective understanding, assessed by a multiple-choice knowledge questionnaire. Secondary outcomes were subjective understanding, communication satisfaction, pre-to-post anxiety changes, communication duration, and neurosurgeons' communication skills from video recordings. RESULTS: Of the 67 individuals screened, 62 communication recipients were enrolled and completed all assessments (patients, n=30; LARs, n=32; AR, n=32; and control, n=30). Objective understanding was higher with AR than with the physical model in the prespecified pooled comparison (P=.01). Communication satisfaction was also higher with AR (P<.001). There were no clear between-group differences in subjective understanding (P=.41), anxiety changes (ΔState-Trait Anxiety Inventory [ΔSTAI] Y-1, P=.37; ΔSTAI Y-2, P=.84), in-session face-to-face communication duration (excluding any presession AR technical preparation time; P=.73), or SEGUE scores (P=.60). Exploratory stratified analyses suggested larger comprehension gains with AR in the parietal and occipital approach strata. CONCLUSIONS: In a standardized preoperative SDM conversation, an integrated visualization-support package combining AR, patient-specific modeling, and interactivity improved neurosurgical decision makers' objective understanding and satisfaction without prolonging in-session, face-to-face communication duration. Larger multicenter trials with longer-term outcomes are warranted to confirm effectiveness and to evaluate implementation and cost considerations. TRIAL REGISTRATION: ISRCTN Registry ISRCTN11483487; http://www.isrctn.com/ISRCTN11483487.
20 Apr 2026
Read appraisal →PLoS computational biology
'Backpropagation and the brain' realized in cortical error neuron microcircuits
Neural responses to mismatches between expected and actual stimuli have been widely reported across different species. How does the brain use such error signals for learning? While global error signals can be useful, their ability to learn complex computation at the scale observed in the brain is lacking. In comparison, more local, neuron-specific error signals enable superior performance, but their computation and propagation remain unclear. Motivated by the breakthrough of deep learning, this has inspired the 'backpropagation and the brain' hypothesis, i.e., that the brain implements a form of the error backpropagation algorithm. In this work, we introduce a biologically motivated, multi-area cortical microcircuit model, implementing error backpropagation under consideration of recent physiological evidence. We model populations of cortical pyramidal cells acting as representation and error neurons, with bio-plausible local and inter-area connectivity, guided by experimental observations of connectivity of the primate visual cortex. In our model, all information transfer is biologically motivated, inference and learning occur without phases, and network dynamics demonstrably approximate those of error backpropagation. We show the capabilities of our model on a wide range of benchmarks, and compare to other models, such as dendritic hierarchical predictive coding. In particular, our model addresses shortcomings of other theories in terms of scalability to many cortical areas. Finally, we make concrete predictions, which differentiate it from other theories, and which can be tested experimentally.
19 Apr 2026
Read appraisal →Journal of global health
Associations between haemoglobin-to-red cell distribution width ratio and mortality in intracerebral haemorrhage: a population-based analysis of the MIMIC-IV database
BACKGROUND: Intracerebral haemorrhage (ICH) is a leading cause of mortality and morbidity worldwide. Identifying early prognostic biomarkers is crucial to optimise clinical management of critically ill patients with ICH. The haemoglobin-to-red cell distribution width ratio (HRR) has recently emerged as a potential predictor in various critical illnesses, but its role in ICH remains unclear. This study aimed to evaluate associations between HRR and mortality in patients with ICH. METHODS: This retrospective cohort study included the data of adults (≥18 years) extracted from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database (version 1). HRR was calculated from the first available haemoglobin and RDW measurements within one day of each other. Patients were categorised into HRR quartiles. The primary outcomes were 28-day and 1-year all-cause mortality. Associations were assessed using Cox proportional hazards models. RESULTS: The data of 1915 patients (mean age 67.5 years) were analysed retrospectively. After adjusting for possible confounders, compared with the lowest HRR quartile (Q1), patients in Q3 and Q4 had significantly lower 28-day mortality (Q3: adjusted hazard ratio (aHR) = 0.72; 95% CI = 0.54, 0.97; Q4: aHR = 0.67; 95% CI = 0.49, 0.90). Similarly, higher HRR quartiles were associated with reduced 1-year mortality risk (Q3: aHR = 0.64; 95% CI = 0.49, 0.84; Q4: aHR = 0.56; 95% CI = 0.42, 0.75). CONCLUSIONS: Lower HRR at admission is independently associated with higher short-term and long-term mortality in ICU patients with ICH. HRR may serve as a candidate prognostic biomarker for early risk stratification in this high-risk population. Further prospective studies are warranted to confirm these findings.
18 Apr 2026
Read appraisal →Journal of neurointerventional surgery
Safety and efficacy of selective and superselective intra-arterial cerebral infusion with blood-brain barrier disruption for glioma: a systematic review and meta-analysis
BACKGROUND: Selective and superselective intra-arterial cerebral infusion (SIACI/SSIACI) delivers chemotherapy directly to tumor-supplying arteries, achieving high local drug levels with reduced systemic toxicity. Often combined with blood-brain barrier disruption (BBBd) to enhance penetration, these methods have been widely studied, yet a comprehensive evidence synthesis is lacking. This study systematically assesses the safety and efficacy of intra-arterial chemotherapy with BBBd for glioma treatment. METHODS: We searched PubMed, Embase, and Web of Science for studies on SIACI with BBBd in glioma patients. Safety outcomes included rates of cases with complications, procedure-related complications (major/minor), stroke, intracranial and intratumoral hemorrhage, and mortality. Efficacy was based on tumor response (complete, partial, stable disease, progression). A subanalysis of SSIACI-only cases was also conducted. RESULTS: Nine studies with 230 glioma patients were included. The pooled rate of cases with complications was 27.1% (95% CI 19.8% to 35.7%), with procedure-related complications occurring in 15.4% (95% CI 6.1% to 24.6%). Major and minor complication rates were 4.3% (95% CI 0.9% to 7.7%) and 9.7% (95% CI 1.0% to 18.7%), respectively. Stroke, intracranial hemorrhage, and intratumoral hemorrhage occurred in 3.1% (95% CI 0% to 6.1%), 0.5% (95% CI 0% to 3.2%), and 0.04% (95% CI 0% to 3%), respectively, with no procedure-related deaths reported. Pooled response rates were 10.4% complete (95% CI 0% to 21.5%), 24.2% partial (95% CI 14.3% to 34.1%), 38.2% stable disease (95% CI 21.5% to 54.9%), and 39.3% progression (95% CI 14.8% to 63.8%). Subanalysis of superselective infusions yielded comparable outcomes to the overall cohort. CONCLUSION: The findings indicate that SIACI/SSIACI chemotherapy following BBBd is a feasible and safe approach for glioma treatment, demonstrating a favorable procedural risk profile and preliminary signs of efficacy. Further studies are warranted to validate these results and refine procedural protocols.
18 Apr 2026
Read appraisal →Journal of neurointerventional surgery
Feasibility and non-inferiority of mobile telementoring for digital subtraction angiography: a single-center observational study
BACKGROUND: Telementoring is an emerging approach in surgical education that offers remote supervision and guidance through digital platforms. This study aimed to evaluate the feasibility and non-inferiority of a mobile-based telementoring system for digital subtraction angiography (DSA) and compare it with traditional face-to-face mentoring. METHODS: This prospective, single-center observational study included 71 patients who underwent DSA between April 2021 and May 2024. Patients were categorized into control (n=48, face-to-face mentoring) and telementoring (n=23) groups. A mobile telementoring system (JOIN, Allm Inc., Tokyo, Japan), which enabled real-time image sharing and voice communication between the examiner and the remote supervisor, was employed. The primary endpoints were contrast volume, procedural time, and radiation dose, with a non-inferiority margin of 20% applied. RESULTS: No significant differences were observed between the two groups in contrast volume (88.3±39.6 mL vs 97.1±36.4 mL, p=0.499), procedural time (44.1±17.7 min vs 50.7±19.0 min, p=0.308), or radiation dose (427.9±262.2 mGy vs 506.6±307.1 mGy, p=0.346). Non-inferiority was confirmed across all primary endpoints. No procedural complications occurred. Qualitative feedback indicated high user satisfaction, with the system facilitating effective remote supervision and decision-making. CONCLUSIONS: This study demonstrates the feasibility and non-inferiority of a mobile telementoring system for DSA, effectively supporting real-time remote guidance and reducing the need for on-site supervision. Its implementation may enhance access to expert mentoring, particularly in regions with limited specialist availability, contributing to equitable and efficient cerebrovascular care.
18 Apr 2026
Read appraisal →Journal of neurointerventional surgery
Stroke thrombectomy with a novel reperfusion system including a 0.088'' aspiration catheter: the Imperative Trial
BACKGROUND: Mechanical thrombectomy is the standard of care for large vessel occlusion (LVO) stroke, yet most device trials focus on individual technologies rather than complete systems. OBJECTIVE: To evaluate the safety and efficacy of the Zoom Reperfusion System compared with performance goals derived from a meta-analysis of trials using established thrombectomy technologies. METHODS: Prospective, multicenter, non-randomized, investigational device exemption trial conducted across 26 United States centers from October 2021 to March 2024. Adults with anterior circulation LVO stroke within 8 hours of onset were treated using the Zoom System, which includes aspiration catheters ranging from 0.035″ to 0.071″, and a novel 0.088″ intracranial guide/aspiration catheter. The primary efficacy endpoint was successful reperfusion (modified Thrombolysis in Cerebral Infarction (mTICI) 2b-3) within three passes using Zoom-only components, adjudicated by an independent core laboratory. The primary safety endpoint was symptomatic intracranial hemorrhage (sICH). Secondary outcomes included final reperfusion, first-pass success, time to reperfusion, 90-day modified Rankin Scale (mRS), and mortality. RESULTS: Among 260 patients (median age 68 years; median National Institutes of Health Stroke Scale (NIHSS) 15), successful reperfusion within three passes was achieved in 83% (216/259; 95% CI: 78% to 89%), exceeding the performance goal (p<0.001). Final reperfusion was 92%, with 5.5% requiring rescue devices. First-pass mTICI 2b-3 success was 57%. Median puncture-to-reperfusion time was 19 min. At 90 days, 55% achieved mRS 0-2. The sICH rate was 1.9%, and 90-day mortality was 12.7%. CONCLUSIONS: The Zoom Reperfusion System demonstrated a safety and efficacy profile exceeding prespecified contemporary performance metrics with potential to significantly shorten reperfusion times and reduce the need for rescue therapy. TRIAL REGISTRATION NUMBER: ClinicalTrials.gov--Identifier:NCT04129125.
17 Apr 2026
Read appraisal →Journal of neurointerventional surgery
Transverse venous sinus stenting versus cerebrospinal fluid shunting in idiopathic intracranial hypertension: a multi-institutional and multinational database study
BACKGROUND: Cerebrospinal fluid (CSF) shunting and transverse venous sinus (TVS) stenting are promising treatment choices for idiopathic intracranial hypertension (IIH), addressing different aspects of IIH pathophysiology. However, large-scale comparative data remain limited. METHODS: We performed a multinational, multi-institutional, retrospective propensity score-matched analysis using the TriNetX platform. Adult patients diagnosed with IIH who underwent either TVS stenting or CSF shunting were included. The primary outcome was treatment failure, defined as the need for subsequent procedures (repeat TVS stenting, CSF shunt, or optic nerve fenestration). Secondary outcomes included residual symptoms (headache, visual disturbances, dizziness, and pulsatile tinnitus), ongoing use of IIH-related medications (furosemide, acetazolamide, and topiramate), and healthcare utilization, assessed through unplanned hospital readmissions and emergency department (ED) visits at 1 year follow-up. RESULTS: Of 134 530 IIH patients identified, 1362 underwent TVS stenting and 5278 underwent CSF shunting. After propensity score matching, patients who received TVS stenting had significantly lower odds of repeat interventions (9.6% vs 38.6%; OR 0.169, 95% CI 0.136 to 0.212, P<0.001). They also had significantly lower odds of residual headache, visual disturbances, and papilledema. However, stenting was associated with higher odds of persistent pulsatile tinnitus (6.7% vs 2.2%; OR 3.183, P<0.001). TVS stenting was associated with lower odds of unplanned inpatient readmissions (24.1% vs 40.5%; OR 0.466, P<0.001) and ED visits (22.0% vs 34.0%; OR 0.548, P<0.001). CONCLUSION: Both TVS stenting and CSF shunting resulted in symptomatic improvement and reduced medication use in patients with IIH. However, stenting was associated with significantly lower treatment failure rates, fewer residual papilledema, headaches and visual symptoms, and reduced healthcare utilization. Persistent pulsatile tinnitus was more common following stenting.
17 Apr 2026
Read appraisal →Child's nervous system : ChNS : official journal of the International Society for Pediatric Neurosurgery
Surgical management of anterior sacral meningoceles: a case series and systematic review
PURPOSE: Anterior sacral meningoceles (ASMs) are rare forms of spinal dysraphism caused by anterior herniation of meninges through a sacral defect. Surgical management is the treatment of choice, yet the optimal approach remains debated. This study compares outcomes of three main surgical approaches-anterior transabdominal, posterior transsacral, posterior sagittal (PSARP-type)-focusing on the efficacy and safety of the PSARP-type. METHODS: A retrospective single-center analysis was conducted on eight patients treated for ASM between 2008 and 2025. Demographic, clinical, radiological, functional data were reviewed. Outcomes included recurrence, reoperation, sac size reduction, bladder function; complications were categorized as early or late. A systematic literature review was performed according to PRISMA guidelines. RESULTS: Eight patients (6 females, 2 males; mean age 19.4 years) underwent surgery (five anterior Pfannenstiel incision, two posterior sagittal, one posterior transsacral). All were symptomatic, 87.5% had associated malformations. Sac reduction was achieved in 87.5% of cases, with no new neurological deficits. Complications were mild and self-limiting, including transient urinary retention and cerebrospinal fluid fistula managed with lumboperitoneal shunt. The literature review (49 studies, 68 patients) confirmed female predominance (81%), association with Marfan and Currarino syndromes (35%), preference for posterior approaches (70%), which showed lower morbidity and recurrence rates. One postoperative death (1.4%) was reported. CONCLUSIONS: Posterior approaches-particularly the PSARP-type-provide safe, effective, and functionally favorable alternatives to anterior surgery for ASM, offering optimal exposure, precise dural closure, superior cosmetic outcomes with minimal morbidity. The anterior route should be reserved for large or high-lying lesions. Further multicenter studies with longer follow-up are warranted.
17 Apr 2026
Read appraisal →European journal of trauma and emergency surgery : official publication of the European Trauma Society
Comparison of CATCH, PECARN and CHALICE rules in children with minor head trauma
PURPOSE: The aim of this study is to prospectively compare the diagnostic performance of the PECARN, CATCH, and CHALICE clinical decision rules in pediatric patients presenting with minor head trauma, within a rural secondary-level emergency department characterized by limited resources, high patient volume, and restricted access to specialist physicians. METHODS: The study was designed as a prospective observational study. The PECARN, CATCH, and CHALICE clinical decision rules were applied to the patients included in the study, and the data were recorded. The data included in the study were statistically analyzed using the SPSS (Statistical Package for Social Sciences; SPSS Inc., Chicago, IL) 27 program. A value of p < 0.05 was considered statistically significant. RESULTS: A total of 1,032 patients were included in the study. The PECARN did not miss any of the 15 patients with pathological brain CT and had 100% sensitivity and 52.1% specificity. CATCH failed to detect pathological brain CT in 1 patient and had 93.3% sensitivity and 53.3% specificity. CHALICE failed to detect pathological brain CT in 2 patients, with 86.7% sensitivity and 87.8% specificity. Overall, PECARN was more successful in detecting pathological brain CT, but it also had a high false-positive brain CT rate. CONCLUSION: PECARN criteria are more sensitive than other criteria in predicting brain CT pathology, but they lead to a large number of brain CT scans. While the CHALICE criteria are beneficial in reducing unnecessary brain CT scans, they may miss positive cases.
16 Apr 2026
Read appraisal →Neurosurgery
Congress of Neurological Surgeons Systematic Review and Evidence-Based Guidelines for the Treatment of Adults With WHO Grade II Diffuse Glioma: Update
BACKGROUND: The management of World Health Organization (WHO) grade II diffuse glioma is an important facet of all physicians involved in neuro-oncology. OBJECTIVE: This is an update of the evidence-based guidelines for management of WHO grade II diffuse gliomas published by the Congress of Neurological Surgeons and American Association of Neurological Surgeons in 2015. METHODS: The medical literature from January 1, 2013, through January 31, 2020, was searched to determine if information was available to update, modify, or create new recommendations related to imaging, surgical approaches, neuropathology and molecular markers, radiotherapy, chemotherapy, and management of tumor recurrence. RESULTS: The writing group used the information from the updated literature search to formulate recommendations based on this evidence and not simply built on biased consensus or expert opinion. CONCLUSION: This series of guideline documents provides an update of the information and recommendations provided in the 2015 version. It sets a benchmark as to the published information we have to support the management of this difficult disease. It also provides clues to key investigations that are necessary to move us toward effective control of WHO grade II diffuse gliomas.
16 Apr 2026
Read appraisal →Spine
Predictors for Unsuccessful Outcome of Lumbar Spinal Stenosis Surgery: A Secondary Analysis of the 2 Randomized NORDSTEN Trials
STUDY DESIGN: Observational cohort study. OBJECTIVE: To evaluate potential predictors of unsuccessful outcomes after surgery in patients with lumbar spinal stenosis (LSS). SUMMARY OF BACKGROUND DATA: LSS is a common cause of disability in adults and the leading indication for spine surgery in Norway. Despite advances in surgical techniques, nearly one-third of patients report either minor or no improvement or worsening of symptoms after surgery. Identifying predictors of unsuccessful outcomes is essential for improving patient selection and shared decision-making. MATERIALS AND METHODS: This secondary analysis used data from the 2 NORwegian Degenerative spondylolisthesis and spinal STENosis (NORDSTEN) randomized trials, which included 704 surgically treated patients with LSS, with (n=267) or without (n=437) degenerative spondylolisthesis. The Oswestry Disability Index (ODI) was the primary outcome measure. A reduction in ODI score of <30% from baseline to 2 years postoperatively was defined as an unsuccessful outcome. Multivariable logistic regression analysis was used to evaluate whether carefully selected baseline variables were associated with an unsuccessful outcome at 2-year follow-up. RESULTS: Longer duration of radiating pain (>12 mo; OR: 2.58, 95% CI: 1.54-4.29), psychological distress (HSCL-25 ≥1.75; OR: 1.60, 95% CI: 1.01-2.53), and advanced disc degeneration (Pfirrmann grades 4-5; OR: 1.98, 95% CI: 1.26-3.12) were independently associated with an unsuccessful outcome. Commonly discussed factors such as age, BMI, smoking, ASA grade, and predominant back pain did not reach statistical significance for association with the outcome. CONCLUSION: Among patients undergoing surgery for LSS, longer symptom duration, psychological distress, and advanced disc degeneration were associated with a higher risk of unsuccessful postoperative outcomes.
16 Apr 2026
Read appraisal →Child's nervous system : ChNS : official journal of the International Society for Pediatric Neurosurgery
The role of age and Galassi type in management and surgical outcomes of pediatric middle fossa arachnoid cysts: a systematic review and meta-analysis
PURPOSE: Arachnoid cysts are found in approximately 2.6% of the pediatric population, mostly asymptomatic, incidental findings. However, those with mass effect symptoms from cyst growth may require surgery. Because of the variability in progression, we investigated the interaction of patient age with middle fossa arachnoid cyst (MFAC) clinical outcomes. METHODS: A systematic review using PubMed, Google Scholar, and Web of Science electronic databases was completed according to the PRISMA guidelines to identify articles detailing pediatric MFACs. RESULTS: Sixty articles meeting the inclusion criteria, totaling 1024 patients, were included. Signs of elevated ICP (194/873, prevalence: 22.2%, 95% CI: 19.5-25.0%) and primary headaches (263/873, prevalence: 30.1%, 95% CI: 27.1-33.2%) were the most common presenting symptoms. In the evaluation of the hemispheric location of MFACs, younger ages at presentation were more likely to present with bilateral MFACs (OR: 0.71, 95% CI: 0.52-0.98, p = 0.034). Most MFACs in the retrospective studies had left laterality (421/677, prevalence: 62.2%, 95% CI: 58.6-65.1%) and were singular (791/817, prevalence:96.8%, 95% CI: 95.6-98.2%). A higher proportion of younger patients required a second operation (OR: 0.82, 95% CI: 0.72-0.93, p = 0.002) and cerebrospinal fluid shunting (OR: 0.88, 95% CI: 0.79-0.97, p = 0.011) across the case reports. There was no significant difference in complications when comparing older children (5-18 years) to young children (≤ 4 years) (p = 0.737) or Galassi type (p = 0.736), but Galassi type 1 was associated with management through observation (p = 0.019). CONCLUSION: Younger patients presented with a higher rate of bilateral MFACs and required more invasive treatment methods and repeat operations more frequently, suggesting that infants and young children with MFACs may require greater surveillance during and after management to minimize complications.
14 Apr 2026
Read appraisal →Medicine
Glioma biomarker analysis and drug targeting prediction based on ferroptosis-related genes
Glioma represents a significant challenge in neuro-oncology due to its highly invasive nature and poor prognosis. Recent studies indicate that ferroptosis, a form of regulated cell death, plays a crucial role in the pathogenesis of glioma. Modulating ferroptosis may offer a novel therapeutic approach for glioma treatment. This study aims to identify ferroptosis-related biomarkers and patterns of immune infiltration in glioma using bioinformatics techniques, and to predict potential therapeutic drugs targeting these biomarkers. Gene expression profiles (GSE16011, GSE50161) were retrieved from the GEO database, while ferroptosis-related genes were sourced from the FerrDb database. Intersection genes were identified using the CytoHubba algorithm and a consensus clustering method. Immune infiltration was assessed using the CIBERSORT algorithm. Functional enrichment analysis and gene set enrichment analysis were conducted with Gene Ontology and Kyoto Encyclopedia of Genes and Genomes databases. Drug targeting predictions were made based on identified hub genes. We identified 10 hub genes: TP53, RRM2, EZH2, CDKN1A, MYCN, KIF20A, BLM, GLS2, HMOX1, and GOT1. Gene Ontology and Kyoto Encyclopedia of Genes and Genomes analyses revealed that ferroptosis is primarily associated with apoptosis, reactive oxygen metabolism, the p53 signaling pathway, and immune regulation. Immune infiltration analysis showed significant differences in the expression of plasma cells, CD8 T cells, follicular helper T cells, activated NK cells, and macrophages between groups. qRT-PCR validation in glioma cell lines confirmed the differential expression of key ferroptosis-related genes, supporting the robustness of our bioinformatic findings. Furthermore, molecular docking demonstrates excellent binding properties between the drug components and key targets, and these key targets were further validated by PCR analysis in vitro. In summary, this study highlights the potential of ferroptosis-related biomarkers in glioma and suggests novel drug targets, providing a foundation for future therapeutic strategies.
12 Apr 2026
Read appraisal →European journal of trauma and emergency surgery : official publication of the European Trauma Society
A machine-learning-based tool for stroke risk prediction in blunt cerebrovascular injury: development and preliminary evaluation
PURPOSE: Stroke risk correlates with the Biffl grading system in blunt cerebrovascular injury (BCVI). Although anti-thrombotic therapy is the mainstay of stroke prevention, no point-of-care clinical decision-support tool exists to guide timing for therapy. We sought to develop an interactive online calculator that incorporates patient-specific demographic and injury characteristics to estimate stroke risk and risk reduction with anti-thrombotic (AT) administration. METHODS: Data from BCVI patients (n = 1,197) at a Level I Trauma Center were retrospectively collected. Six machine learning methods were employed to predict stroke risk with and without AT therapy. Class imbalance was addressed using downsampling and/or class weighting. Model performance was assessed using 10-fold cross-validation. The model was implemented as an R-based Shiny online application. RESULTS: Stroke rate among the population was 4%, and the strongest predictors for stroke were the greatest Biffl grade of carotid (aOR [95%CI] = 2.02 [1.62-2.53]) and vertebral injuries (1.44 [1.18-1.77]). The least absolute shrinkage and selection operator (LASSO) model outperformed all others, achieving 66% [33%-100%] sensitivity and 74% [62%-82%] specificity for stroke prediction, with an area under the receiver operating characteristic curve of 0.79 [0.57-0.95]. This model was integrated into an interactive online tool ( https://grady-bcvi-calc.shinyapps.io/calculator/ ), where patient demographic and injury characteristics can be used to compute baseline stroke risk and estimate stroke risk with AT. CONCLUSION: We developed and evaluated a preliminary predictive model for personalized stroke risk assessment in patients with BCVI using key risk factors. The integration of patient-specific risk-benefit assessments into clinical decision-making could optimize and reduce variability in AT therapy. External validation is warranted to prepare this tool for broad clinical applicability.
11 Apr 2026
Read appraisal →Biochemical and biophysical research communications
Interpretable prognostic modeling of glioblastoma using cross-cohort transcriptome integration and machine learning approaches
Glioblastoma (GBM) is an aggressive brain tumor with highly variable patient outcomes due to pronounced molecular heterogeneity. Prognosis remains dismal (median survival ∼15 months) and current prognostic models often function as "black boxes," lacking interpretability and limiting clinical utility. There is an urgent need for interpretable prognostic tools to better stratify GBM patients. This study performed cross-cohort, cross-platform transcriptome data integration (TCGA RNA-seq and GEO microarrays) and incorporated inferred immunogenomic features to capture GBM's complexity. An automated machine learning (AutoML) pipeline tested over 100 algorithmic combinations to build an optimal survival prediction model. The final model is a 22-gene signature, and SHAP (SHapley Additive exPlanations) analysis was applied to explain each gene's contribution to risk. Key genes identified by the model (e.g. UBE2W, EID1, HS2ST1) were validated by qRT-PCR and Western blot, confirming their dysregulated expression in GBM cell lines. The 22-gene model achieved a concordance index of ∼0.72 and was validated on independent cohorts (TCGA training and GEO validation), demonstrating robust performance. It effectively stratified patients into high- and low-risk groups with significant survival differences. High-risk tumors were associated with an immune-cell-enriched yet immune-evasive microenvironment, showing greater infiltration of immunosuppressive cells and higher TIDE scores (indicating immune escape). In contrast, low-risk patients had a more favorable immune profile, and their tumors were predicted to be more sensitive to multiple chemotherapeutic agents. This interpretable transcriptome-based integrative prognostic model can serve as a valuable tool for GBM risk stratification and may guide therapeutic decision-making by highlighting potential targets. Not only does it improve outcome prediction, but it also identifies novel prognostic biomarkers, holding promise for personalized treatment and clinical translation in glioblastoma.
10 Apr 2026
Read appraisal →Scientific reports
Association between estimated plasma volume status and all-cause mortality in critically ill patients with non-traumatic subarachnoid hemorrhage: analysis of the MIMIC-IV database
BACKGROUND: The estimated plasma volume status (ePVS) is an independent risk factor for poor prognosis in certain cardiovascular disease populations. However, the relationship between ePVS and prognosis in critically ill patients with non-traumatic subarachnoid hemorrhage (NSAH) remains unclear. This study aims to explore the association between ePVS and all-cause mortality (ACM) in NSAH patients. METHODS: A total of 750 NSAH patients were included in this retrospective study. The primary outcome was 1-month ACM. A Cox proportional hazards model was constructed to examine the relationship between ePVS and ACM in critically ill NSAH patients. A restricted cubic spline model was used to assess the relationship between ePVS and the outcome. RESULTS: In this patient cohort, 1-month, 3-month, and 1-year ACM rates were 21%, 25%, and 29%, respectively. After adjusting for potential confounders, we found a U-shaped relationship between ePVS and 1-month ACM, with an inflection point at 3.94. Specifically, when ePVS is below the inflection point, each unit increase in ePVS reduces the mortality risk by 56% [HR, 0.44 (95% CI 0.25, 0.76)]. However, once the inflection point is surpassed, each unit increase in ePVS increases the mortality risk by 1.8 times [HR, 2.80 (95% CI 1.58, 4.97)]. CONCLUSION: We identified a U-shaped relationship between ePVS and ACM in critically ill patients with NSAH, suggesting both low and high ePVS levels may portend adverse outcomes. Prospective multicenter studies are warranted to validate these findings and elucidate underlying mechanisms.
10 Apr 2026
Read appraisal →JAMA
Treatment for Brain Metastases With Stereotactic Radiation vs Hippocampal-Avoidance Whole Brain Radiation: A Randomized Clinical Trial
IMPORTANCE: Brain metastases are common in patients with cancer, and radiation is often used for management. Among patients with more than 4 brain metastases, the effects of stereotactic radiation targeting only individual tumors, compared with whole brain radiation with hippocampal avoidance, which radiates both tumors and normal brain, remain unknown. OBJECTIVE: To determine whether stereotactic radiation improves symptom severity and interference with daily functioning, compared with whole brain radiation with hippocampal avoidance. DESIGN, SETTING, AND PARTICIPANTS: Phase 3, open-label, randomized clinical trial conducted at 4 United States-based centers. Eligible patients had 5 to 20 brain metastases and no prior brain-directed radiation. Enrollment occurred between April 11, 2017, and May 17, 2024 (final follow-up, March 18, 2025). INTERVENTION: Stereotactic radiation, compared with whole brain radiation with hippocampal avoidance. MAIN OUTCOMES AND MEASURES: Mean weighted patient-reported symptom severity and interference score change over 6 months postbaseline relative to baseline using the MD Anderson Symptom Inventory-Brain Tumor instrument (scale, 0-10; score change range, -10 to 10; -10 = best). A clinically meaningful Δ was defined as 0.98. RESULTS: Of 196 randomized patients (mean age, 61 years; 129 [66%] female; 176 [90%] White; median number of brain metastases, 14 [IQR, 11-18]; 49 [25%] with prior neurosurgical resection), 83 (42%) completed the 6-month assessment. For the primary outcome, between baseline and postbaseline assessments through the 6-month follow-up, stereotactic radiation changed the weighted composite MD Anderson Symptom Inventory-Brain Tumor score from 2.69 to 2.37 (mean change, -0.32) and hippocampal-avoidance whole brain radiation changed the score from 2.29 to 3.03 (mean change, 0.74) (mean difference, -1.06 [95% CI, -1.54 to -0.58]; P < .001). Related grade 3-5 adverse events occurred in 12 patients (12%) in the stereotactic radiation group and 13 patients (13%) in the hippocampal-avoidance whole brain radiation group; grade 1-3 fatigue was most frequent (27 [28%] vs 43 [44%], respectively). CONCLUSIONS AND RELEVANCE: In patients with 5 to 20 brain metastases, these findings support stereotactic radiation over hippocampal-avoidance whole brain radiation to improve symptoms and interference with daily functioning, key components of quality of life. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT03075072.
8 Apr 2026
Read appraisal →Translational vision science & technology
Diagnosis of High Intracranial Pressure by Non-Optic Nerve Retinal Image Features
PURPOSE: To assess the performance of an artificial intelligence deep learning (DL) model compared with neuro-ophthalmologists for the classification of subjects with elevated intracranial pressure (ICP) and papilledema versus control subjects, based on retinal images with and without masking the optic nerve heads (ONHs). METHODS: Widefield retinal images were obtained in 32 subjects (70 images) with elevated ICP and papilledema and 31 control subjects (62 images). ONH-unmasked images were generated by cropping the image to a 30° circular region. ONH-masked images were generated by masking the ONH and peripapillary region. Classification was performed using a convolutional neural network model and by two neuro-ophthalmologists (graders). RESULTS: For the ONH-unmasked images, the classification accuracies of the model, grader 1, and grader 2 were 83% (area under the receiver operating characteristic curve [AUC] = 0.94), 93%, and 86%, respectively. For the ONH-masked images, the classification accuracies of the model, grader 1, and grader 2 were 79% (AUC = 0.90), 66%, and 76%, respectively. The classification performance of the DL model and graders did not significantly differ for both datasets (P ≥ 0.38). There was no significant effect of ONH masking on the performance of the DL model (P = 1.0) and grader 2 (P = 0.38), whereas the performance of grader 1 was significantly reduced (P = 0.02). CONCLUSIONS: Both expert graders and the DL models demonstrated excellent performance for classifying retinal images of subjects with elevated and normal ICP using images with or without masking the ONH. TRANSLATIONAL RELEVANCE: Methods for assessment of non-optic nerve retinal image features have the potential to improve diagnosis and monitoring the progression and response to treatment of elevated ICP.
7 Apr 2026
Read appraisal →AJNR. American journal of neuroradiology
Delphi Consensus on Early Neurologic Improvement after Mechanical Thrombectomy
BACKGROUND AND PURPOSE: Early neurologic improvement (ENI) following mechanical thrombectomy (MT) has been a topic of substantial interest. The literature has more than 40 ENI definitions, yet no consensus has been reached. In this Delphi study, we sought to investigate experts' perspectives on the available ENI definitions and determine whether a consensus can be achieved. MATERIALS AND METHODS: The Delphi approach assessed experts' perspectives on available ENI definitions. Following a systematic literature review, the first survey round was prepared and sent to 20 experts using a Web-based anonymous survey platform (qualtrics.com). The first round of questions was publicly shared on the letsgetproof.com platform to gather perspectives of neurointerventionalists worldwide on ENI definitions. Expert and volunteer answers formed the basis of subsequent rounds, in which closed-ended questions were sent only to experts. Consensus was defined as an agreement of ≥70% for binary closed-ended questions and ≥50% for closed-ended questions with >2 response options. RESULTS: Experts completed 3 survey rounds. They recognized that the heterogeneity in ENI definitions is the most critical factor limiting the use of ENI in clinical practice and stroke research. All experts acknowledged that stroke physicians need a standardized universal ENI definition. Consensus was reached on the notion that a unified ENI definition should focus on predicting functional independence at 3 months. They agreed that NIHSS improvement of ≥8 points at 24 hours could serve as the unified ENI definition. They acknowledged that incorporating prestroke comorbidities, occlusion location, baseline NIHSS scores, and procedure-related parameters would complicate the ideal ENI definition and limit its use in clinical settings. The experts could not reach a consensus on the potential utility of ENI as a primary end point in MT trials. CONCLUSIONS: In our Delphi analysis, experts agreed on an ENI definition. They did not endorse using different ENI criteria for patients with comorbidities, posterior circulation occlusions, or high baseline NIHSS scores. Further prospective studies are needed to validate or refine ENI definitions and to address the paucity of data on the prognostic utility of ENI in specific clinical scenarios.
5 Apr 2026
Read appraisal →AJNR. American journal of neuroradiology
Flow Diversion versus Coiling with or without Stenting for Unruptured Wide-Neck Intracranial Aneurysms: A Randomized Comparison
BACKGROUND AND PURPOSE: There are few randomized trials comparing coiling (with or without stent placement) and flow diversion (FD) for the treatment of wide-neck unruptured intracranial aneurysms. MATERIALS AND METHODS: EVIDENCE was an investigator-led randomized (1:1) trial conducted in 7 French university hospitals. Patients with 7 to 20-mm intradural unruptured intracranial aneurysms with a 4- to 10-mm neck and a "dome/neck" ratio of ≥1 were randomly allocated to coiling with or without adjunctive stent placement or FD alone. The composite primary efficacy outcome was "treatment failure," defined as initial failure to treat the aneurysm; aneurysm rupture or retreatment during follow-up; death or dependency (mRS> 2); or an angiographic residual aneurysm adjudicated by an independent core laboratory at 12 months. The primary hypothesis (revised for slow accrual) was that FD would decrease treatment failures from 35% to 10%, requiring 90 patients. Primary analyses were intent to treat. RESULTS: Among the 91 enrolled patients, four (two in each group) withdrew consent; 87 patients were included in the analysis: 43 in the FD group and 44 in the control group. Most patients had <10 mm (57/87; 65.5%) asymptomatic ophthalmic aneurysms (75/87, 86.2%). A poor primary outcome, ascertainable in 86 patients, was reached in 8/43 patients with FD (18.6%; 95% CI, 9.7%-32.6%) compared with 10/43 coiling patients (23.3%; 95 CI, 13.1%-37.7%) (RR = 0.80; 95% CI, 0.35-1.83; P = .60). Serious adverse events were similar. CONCLUSIONS: For patients with mostly unruptured, wide-neck ophthalmic aneurysms of <10 mm, FD was not superior to coiling with or without stent placement.
5 Apr 2026
Read appraisal →BMJ open
Development and acceptability of a patient decision aid for people with degenerative cervical myelopathy: an international mixed-methods study
OBJECTIVES: To develop and user-test a patient decision aid for people diagnosed with degenerative cervical myelopathy and who are considering surgery. DESIGN: Mixed-methods study describing the development of a patient decision aid. SETTING: A draft decision aid was developed by a multidisciplinary steering group (including study authors with degenerative cervical myelopathy, health professionals and researchers) informed by the best available evidence, authorship consensus and existing patient decision aids. PARTICIPANTS: Patient-participants and health professional-participants who manage people with degenerative cervical myelopathy were recruited through social media and the steering group's research and practice network. Quantitative questionnaires were used to gather baseline data, descriptive feedback, refine the decision aid and assess its acceptability. Qualitative semi-structured interviews were conducted online to gather feedback on the decision aid and were analysed using reflexive thematic analysis. RESULTS: We conducted 32 interviews: 19 patient-participants and 13 health professional-participants who manage people with degenerative cervical myelopathy (neurosurgeons, neurologists, physiotherapists, orthopaedic surgeons, general practitioners, rehabilitation and pain specialists and consultant occupational physicians and chiropractors). Participants were from 10 countries (Australia, Canada, Cyprus, Germany, Ireland, New Zealand, Sweden, Switzerland, United Kingdom and USA). Most participants rated the decision aid's acceptability as good-to-excellent and agreed with most aspects of the decision aid (eg, defining degenerative cervical myelopathy, management recommendations, potential benefits and harms, questions to consider asking a health professional). CONCLUSION: Our patient decision aid was rated as an acceptable tool by both health professional-participants who treat degenerative cervical myelopathy and patient-participants with lived experience of degenerative cervical myelopathy. This decision aid can be used by clinicians and people with degenerative cervical myelopathy to help with shared decision making following a diagnosis of degenerative cervical myelopathy. A study testing the potential benefits of this decision aid in a clinical setting is recommended.
5 Apr 2026
Read appraisal →AJNR. American journal of neuroradiology
Temporomandibular Joint Lesions with Intracranial Extension: Illustrative Cases from a Systematic Review of the Literature and Our Institution
BACKGROUND: Intracranially extending temporomandibular joint (TMJ) lesions may be radiologically misinterpreted as primary intracranial or skull base pathologies, leading to diagnostic delays or inappropriate management. PURPOSE: This systematic review aimed to characterize the clinical and imaging features of such TMJ lesions and evaluate the impact of radiologic misclassification. We also aimed to develop a diagnostic framework for when to consider an intracranially extending TMJ lesion, based on clinical and radiologic features. DATA SOURCES: A comprehensive search of MEDLINE, Scopus, and EMBASE, conducted in accordance with PRISMA guidelines, yielded 2255 records. STUDY SELECTION: After screening with predetermined inclusion and exclusion criteria, 128 studies involving 152 patients were included in the final analysis. DATA ANALYSIS: Statistical analyses were performed using STATA software. We also identified 3 patient cases through our institutional neuroradiology practice who were clinically and radiologically assessed for intracranially extending TMJ lesions. DATA SYNTHESIS: Patients had symptoms for an average of 34 months before diagnosis (47% women, mean age 50 years). The most common pathologies were pigmented villonodular synovitis/tenosynovial giant-cell tumor (43%) and synovial chondromatosis (24%). Neurologic symptoms were reported in 48% of cases, most frequently hearing loss (70%). Nearly one-third (33%) of cases with an imaging differential did not list a TMJ pathology (18/55). In cases with accurate imaging diagnosis, 90% had both CT and MRI performed. Most lesions were nonenhancing (CT 83%, MRI 75%) and demonstrated no adjacent brain edema (96%). In 2 cases, a TMJ ganglion cyst and pseudogout were misdiagnosed as intracranial tumors, resulting in unnecessary intervention, including repeat craniotomy and radiotherapy. LIMITATIONS: There were inherent biases of case report literature, including variability in the reporting of the imaging and clinical features, management, and follow-up. CONCLUSIONS: TMJ lesions with intracranial extension often present with nonspecific symptoms and can mimic extra-axial tumors, leading to misdiagnosis on imaging. Recognition of hallmark imaging features, including lack of parenchymal invasion and distinct imaging patterns, may help improve radiologic accuracy and prevent overtreatment. We propose a diagnostic framework outlining when to suspect intracranially extending TMJ lesions based on clinical and imaging features, and how to avoid common diagnostic pitfalls.
4 Apr 2026
Read appraisal →Journal of neurology
Sonographic optic nerve sheath diameter measurement for detecting intracranial hypertension in a suspected population: a systematic review and meta-analysis of diagnostic thresholds and influencing factors
OBJECTIVES: In this study, we aimed to assess the clinical efficacy of sonographic optic nerve sheath diameter (ONSD) measurements for detecting intracranial hypertension (ICH). Our objectives included evaluating its diagnostic precision compared with invasive intracranial pressure (ICP) monitoring; exploring potential sources of heterogeneity, such as measurement technique (multi vs. single-planar), population demographics (Asian vs. non-Asian), and major etiologies; and determining validated thresholds for prompt bedside ICP assessment in acute neurological crises. DATA SOURCES: We comprehensively searched eight databases, including four in English (PubMed, Web of Science, MEDLINE®, and Embase) and four in Chinese (China National Knowledge Infrastructure [CNKI], Wanfang, VIP, and SinoMed). The search covered literature published from the inception of the databases up to May 31, 2025. STUDY SELECTION: This review includes prospective, retrospective, and case-control studies that assess the efficacy of sonographic ONSD measurement for detecting ICH, defined as an ICP exceeding 20 mm Hg, 20 cmH2O, 25 cmH2O with invasive ICP measurement as the gold standard. DATA EXTRACTION: X.T. and Q.T. independently screened the studies and assessed the risk of bias using the QUADAS-2 tool. STATISTICAL ANALYSIS: Diagnostic accuracy was pooled using a bivariate random-effects model to generate summary receiver operating characteristic (SROC) curves. Subgroup analyses of the measurement technique, study population, and etiology were conducted. Publication bias was assessed using Deeks' test. DATA SYNTHESIS: The decision tree analysis revealed that an ONSD ≥ 5.1 mm is the critical diagnostic threshold for detecting intracranial hypertension. The regression tree model indicated a range of CDEI values from 0.64 to 0.95, with a root node value of 0.82 (95% CI: 0.79-0.85). The incorporation of a multiplanar assessment significantly enhanced the prediction of favorable outcomes (CDEI > 0.85; p < 0.001). Moreover, compared with a 20 mmHg threshold, a 25 cmH₂O threshold resulted in greater specificity (88.4% vs. 82.9%) and a higher positive likelihood ratio (LR+ 6.5 vs. 5.0). The utilization of multiplane techniques and experienced operators notably improved diagnostic accuracy, leading to a 50% reduction in missed diagnoses (LR- 0.1). Nontraumatic brain injury cases exhibited superior sensitivity (91.9% vs. 85.2%) and a 107% higher diagnostic odds ratio (63.3 vs. 30.5) than traumatic brain injury cases did. CONCLUSIONS: Findings from this study suggest that an ONSD threshold ≥ 5.1 mm is a promising diagnostic marker for elevated ICP (> 20 cmH₂O/mmHg or acute etiology), although external validation is needed. A multiplane evaluation improves its predictive accuracy for favorable outcomes. The developed decision model supports the use of sonographic ONSD measurement as a supplementary screening tool in emergency and critical care, particularly when invasive monitoring is unavailable. Additionally, an ONSD of approximately 6.0 mm is a potential prognostic indicator for unfavorable outcomes, highlighting a key area for future research. These findings can only be applied after their validation through multicenter studies and the establishment of standardized measurement protocols.
4 Apr 2026
Read appraisal →European radiology
Attention-based deep learning network for predicting World Health Organization meningioma grade and Ki-67 expression based on magnetic resonance imaging
OBJECTIVES: Preoperative assessment of World Health Organization (WHO) meningioma grading and Ki-67 expression is crucial for treatment strategies. We aimed to develop a fully automated attention-based deep learning network to predict WHO meningioma grading and Ki-67 expression. MATERIALS AND METHODS: This retrospective study included 952 meningioma patients, divided into training (n = 542), internal validation (n = 96), and external test sets (n = 314). For each task, clinical, radiomics, and deep learning models were compared. We used no-new-Unet (nn-Unet) models to construct the segmentation network, followed by four classification models using ResNet50 or Swin Transformer architectures with 2D or 2.5D input strategies. All deep learning models incorporated attention mechanisms. RESULTS: Both the segmentation and 2.5D classification models demonstrated robust performance on the external test set. The segmentation network achieved Dice coefficients of 0.98 (0.97-0.99) and 0.87 (0.83-0.91) for brain parenchyma and tumour segmentation. For predicting meningioma grade, the 2.5D ResNet50 achieved the highest area under the curve (AUC) of 0.90 (0.85-0.93), significantly outperforming the clinical (AUC = 0.77 [0.70-0.83], p < 0.001) and radiomics models (AUC = 0.80 [0.75-0.85], p < 0.001). For Ki-67 expression prediction, the 2.5D Swin Transformer achieved the highest AUC of 0.89 (0.85-0.93), outperforming both the clinical (AUC = 0.76 [0.71-0.81], p < 0.001) and radiomics models (AUC = 0.82 [0.77-0.86], p = 0.002). CONCLUSION: Our automated deep learning network demonstrated superior performance. This novel network could support more precise treatment planning for meningioma patients. KEY POINTS: Question Can artificial intelligence accurately assess meningioma WHO grade and Ki-67 expression from preoperative MRI to guide personalised treatment and follow-up strategies? Findings The attention-enhanced nn-Unet segmentation achieved high accuracy, while 2.5D deep learning models with attention mechanisms achieved accurate prediction of grades and Ki-67. Clinical relevance Our fully automated 2.5D deep learning model, enhanced with attention mechanisms, accurately predicts WHO grades and Ki-67 expression levels in meningiomas, offering a robust, objective, and non-invasive solution to support clinical diagnosis and optimise treatment planning.
4 Apr 2026
Read appraisal →Current opinion in neurology
AI in epilepsy neuroimaging
PURPOSE OF REVIEW: Recent advances in the capabilities and usability of artificial intelligence (AI) architectures coupled with increased availability of neuroimaging datasets has fuelled a rapid expansion in AI applications to epilepsy neuroimaging. This review summarizes the main applications of AI in epilepsy neuroimaging and suggests future directions for the field. RECENT FINDINGS: A range of different machine learning approaches, from multi-layer perceptrons to volumetric and graph-based convolutional neural networks, have been utilized for prediction of whether people will have epilepsy, detection of structural epilepsy lesions, localization of seizure onset zones, segmentation of resection cavities after epilepsy surgery as well as for image enhancement. SUMMARY: AI in epilepsy neuroimaging research has primarily focussed on lesion detection and localization, with a number of open and validated tools now available for evaluation across diverse settings. Additional applications of AI in epilepsy neuroimaging are either at earlier stages of development or emerging as new challenges. As these tools and their supporting evidence mature, further work addressing the hurdles of clinical integration is required.
4 Apr 2026
Read appraisal →Neurological research
Machine learning-based preoperative prediction of IDH mutation status in adult gliomas using clinical features
BACKGROUND: As isocitrate dehydrogenase (IDH) mutation status represents a critical prognostic factor in adult gliomas, there is a demand for a straightforward but effective predictive model to facilitate rapid preoperative diagnosis. METHODS: A cohort of 418 adult glioma patients from our institution were retrospectively enrolled and randomly partitioned into training (70%) and internal validation (30%) sets. Among 9 machine learning algorithms evaluated, AdaBoost demonstrated superior predictive performance based on receiver operating characteristic (ROC) analysis and was subsequently selected as the optimal model. Through feature importance ranking derived from the model, the top 8 most contributory features were identified and incorporated into the final streamlined prediction model. The model's generalizability was further assessed using an independent external validation cohort comprising 206 adult glioma cases. RESULTS: The AdaBoost model demonstrated robust discriminative performance, achieving an area under the receiver operating characteristic curve (AUC-ROC) of 0.901 in the internal validation cohort and 0.849 in the independent external validation cohort. SHAP (SHapley Additive exPlanations) interpretation revealed age as the most influential predictive feature, contributing significantly to the model's decision-making process. CONCLUSIONS: This validated AdaBoost model offers a practical and interpretable solution for preoperative IDH status assessment, demonstrating both diagnostic reliability and biological plausibility through its feature importance profile.
4 Apr 2026
Read appraisal →Japanese journal of radiology
Super-resolution deep learning reconstruction improves brain MRI quality and detection of metastases.
PURPOSE: Accurate identification of brain metastases is critical for determining prognosis and guiding treatment. Deep learning reconstruction (DLR) enhances MRI quality by reducing noise, while super-resolution DLR (SR-DLR) may further improve spatial resolution and lesion detectability. To evaluate SR-DLR versus conventional DLR in detecting and visualizing brain metastases on postcontrast T1-weighted brain MRI. MATERIALS AND METHODS: This retrospective study included 47 consecutive patients who underwent postcontrast 3D whole-brain T1-weighted MRI between July and December 2024. Images were reconstructed using both SR-DLR and DLR. Three independent readers evaluated metastatic lesion detection and rated image quality. Subjective assessments included lesion visibility, visibility of normal structures, sharpness, noise, and overall image quality. Objective metrics-full width at half maximum (FWHM), edge rise distance (ERD), edge rise slope (ERS), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR)-were also measured. Statistical tests included jackknife alternative free-response receiver operating characteristic (JAFROC) analysis, Wilcoxon signed-rank test, McNemar's test, and paired t-tests, with significance threshold of p < 0.050. RESULTS: A total of 117 brain metastases were detected in 47 patients (mean age, 59 years ± 18; 27 men). SR-DLR demonstrated significantly better lesion detection performance than DLR (mean figure of merit = 0.842 vs. 0.797; p = 0.042). Subjective image quality ratings favored SR-DLR for lesion and structure visibility, sharpness, noise, and overall quality in most cases. Objectively, SR-DLR yielded lower FWHM (1.2 mm vs. 1.9 mm; p < 0.001), higher ERS (791.3 mm- 1 vs. 645.3 mm- 1; p = 0.013) indicating enhanced sharpness as well as improved CNR (27.5 vs. 24.9; p < 0.001) compared to DLR. CONCLUSION: Compared to DLR, SR-DLR significantly enhances brain MRI quality and improves detection of metastatic lesions.
4 Apr 2026
Read appraisal →Neuro Oncol
EANS-EANO guidelines on the extent of resection in gliomas
Intense efforts are employed to optimize neurosurgical resection of gliomas in different clinical scenarios. However, the level of evidence employed toward personalized treatment decisions is still moderate. Therefore, a joint task force was created by the European Association for Neurosurgical Societies (EANS) and the European Association of Neuro-Oncology (EANO) in order to provide interdisciplinary guidance on the extent of resection (EOR) in glioma surgery. This task force assessed the data on the EOR in gliomas, evaluated the level of evidence, and composed recommendations. The EOR is determined routinely by postoperative magnetic resonance imaging. Since EOR may be associated with survival and may have an impact on epilepsy, neurocognition, quality of life, neurological status, and also on planning of radiation and pharmacotherapy (evidence classes I-IV), recommendations of different levels can be made for the resection of newly diagnosed glioblastomas (level A), recurrent glioblastomas (level C), newly diagnosed (level B) and recurrent (good practice point) IDH mutant gliomas, ependymomas in children (level B) and adults (good practice point) as well as World Health Organization CNS grade 1 tumors (good practice point). We hereby report the outcome of this collaborative effort by the joint task force between EANS and EANO.
1 Jan 2026
Read appraisal →J Surg Educ
Effect of Artificial Intelligence-Augmented Human Instruction on Feedback Frequency and Surgical Performance During Simulation Training
OBJECTIVE: To determine whether personalized feedback from a human instructor receiving artificial intelligence (AI) error data will result in reduced feedback frequency and improvement of surgical skill compared to AI instruction. As feedback was only provided following AI error detection, a reduced feedback frequency is associated with fewer errors in performance. We hypothesized that AI-augmented personalized instruction would result in reduced feedback frequency and improvement in technical skill. DESIGN: This cross-sectional cohort study was a follow-up of a randomized controlled trial, which utilized the NeuroVR, an immersive virtual reality neurosurgical simulator. Participants were stratified by year in medical school and block randomized to receive one of 3 educational interventions as they performed simulated procedures on the NeuroVR: AI tutor instruction, scripted human instruction, and AI-augmented personalized instruction. Performance was assessed by the feedback frequency and technical skill performance metrics. CLINICALTRIALS: gov ID: NCT06273579. SETTING: Neurosurgical Simulation and Artificial Intelligence Learning Centre, McGill University, Montreal, Canada. PARTICIPANTS: Volunteer sample of medical students from 4 Quebec universities in preparatory, first, or second year without prior use of the NeuroVR. Eighty-eight students participated in the study with 87 included in the final analysis; 1 was excluded due to technical issues. RESULTS: By the third repetition, the AI-augmented personalized instruction group received significantly fewer total instructions (incidence rate ratio [IRR], 1.50 [95% CI, 1.16-1.94] instructions; p < 0.001), and high aspirator force instructions (IRR, 1.71 [95% CI, 1.15-2.55] instructions; p = 0.002), compared to the second repetition. Compared to AI tutor instruction, AI-augmented personalized instruction resulted in a significantly lower rate of healthy tissue removal (p = 0.01), instrument tip separation distance (mean ratio, 1.25 [95% CI, 1.05-1.50] mm; p = 0.008), and aspirator force (mean ratio, 1.68 [95% CI, 1.23-2.31] N; p < 0.001). AI-augmented personalized instruction showed a significant improvement from baseline in all subsequent repetitions for all performance metrics. CONCLUSIONS: This cohort study demonstrated that AI-augmented personalized instruction resulted in less frequent feedback, indicating fewer errors in trainee performance, and an improvement in simulated surgical skills.
1 Nov 2025
Read appraisal →