Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 36 appraisals
European radiology
Deep learning improves image quality in motion-robust and sedation-free pediatric brain MRI
OBJECTIVES: Motion and limited compliance compromise diagnostic MR image quality, particularly in pediatric patients who frequently require sedation. Single-shot sequences offer a time-efficient alternative but suffer from reduced image quality. This study aimed to evaluate the diagnostic performance of a deep learning (DL) framework combining compressed sensing (CS) and convolutional neural networks (CNNs) to enhance T2-weighted single-shot MRI (T2-SSHDL) compared with conventional CS-based reconstruction (T2-SSHconv) and routinely acquired high-resolution T2-weighted sequences. MATERIALS AND METHODS: This prospective single-center study included 62 pediatric patients (mean age, 7.4 ± 4.9 years; 36 males, 26 females), who underwent T2-weighted single-shot brain MRI (29 sedated, 33 awake). Raw data were reconstructed using a DL-based pipeline and compared with conventional CS-based reconstructions. Quantitative metrics included apparent contrast-to-noise ratio (aCNR), apparent signal-to-noise ratio (aSNR), and edge rise distance (ERD). Two radiologists rated images for artifacts, sharpness, lesion conspicuity, and overall quality on a 5-point Likert scale. RESULTS: T2-SSHDL-sequences showed significantly higher aCNR (29.9 ± 22.6 vs. 26.7 ± 16.5; p < 0.001), aSNR (41.6 ± 27.9 vs. 38.2 ± 20.8; p = 0.003), and improved sharpness (ERD 0.90 ± 0.35 mm vs. 1.35 ± 0.42 mm; p < 0.001). Qualitative assessments confirmed superior image quality, lesion conspicuity, and sharpness (p < 0.001). Compared with high-resolution T2-weighted sequences, T2-SSHDL-sequences showed fewer motion artifacts and comparable lesion conspicuity in non-sedated patients. CONCLUSION: DL-based reconstruction significantly enhances the diagnostic quality of T2-weighted single-shot brain MRI in pediatric patients, enabling clinically usable, ultrafast, motion-robust imaging with potential to reduce the need for sedation. KEY POINTS: Question Can deep learning-based reconstruction elevate motion-robust single-shot T2-weighted pediatric brain MRI to diagnostic image quality levels, enabling reliable imaging without sedation? Findings Both quantitative and qualitative evaluations confirmed significantly improved image quality of deep learning-enhanced single-shot T2-weighted brain MRI compared with conventional reconstruction. Clinical relevance Deep learning-enhanced reconstruction improves image quality in ultrafast, motion-robust single-shot pediatric brain MRI, potentially reducing the need for sedation while preserving diagnostic accuracy. This approach may enhance patient safety and shorten examination time in routine neuroimaging.
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 →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 →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 →Neuroinformatics
NeuroFusion: A Unified Framework for Generalized Visual Stimulus Decoding from fMRI Across Datasets and Subjects
Recent advancements in neural decoding have shown promising results in reconstructing visual experiences from brain activity. However, existing approaches focus primarily on decoding within a single dataset or subject, which limits generalization across various sources of neuroimaging. In this work, we propose a novel framework for the decoding of visual stimuli between subjects and between data sets, integrating neural recordings from multiple publicly available fMRI datasets. To address inherent intersubject and interdataset variability, we introduce a contrastive learning-based alignment strategy using image embeddings from a pre-trained IP-Adapter model. Our approach learns a shared latent space by aligning subject-specific neural representations with image features, enabling generalized decoding across both subjects and datasets. In addition, we propose a simple yet effective data augmentation method using ridge regression. This method synthesizes realistic fMRI-like signals from novel images by predicting voxel activity and injecting learned noise distributions, thus enhancing training diversity and model robustness. To the best of our knowledge, while several recent studies have explored cross-subject decoding, we extend recent cross-subject decoding efforts by training a single unified framework jointly across multiple public fMRI datasets and subjects, enabling cross-dataset transfer in addition to cross-subject generalization. We distinguish this multi-dataset unified training setting, where each dataset contributes training data, from a stricter leave-one-dataset-out transfer setting in which the target dataset is excluded from source pretraining and used only for lightweight alignment-layer adaptation. Empirically, our unified model achieves strong semantic reconstruction across datasets (e.g., up to 94.8% CLIP similarity on NSD (AUG) and 0.403 SSIM on BOLD5000 after lightweight finetuning), demonstrating robust cross-subject and cross-dataset transfer.
20 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 →Brain imaging and behavior
Associations between olfactory dysfunction and structural MRI findings in Parkinson's disease: a systematic review
Olfactory dysfunction is a common and early non-motor symptom of Parkinson's disease (PD). Structural Magnetic Resonance Imaging (MRI) studies have reported changes in olfactory-related brain regions, but findings remain inconsistent. This review synthesizes MRI evidence to clarify neuroanatomical correlates of olfactory dysfunction in PD. We performed a systematic review to find the associations between olfactory dysfunction and structural MRI findings in people with PD. A systematic search in PubMed, Scopus, and Web of Science yielded 20 eligible studies. The eligible studies involved 1,092 patients with PD. Although there were inconsistent regions of interest and types of analysis, we identified structural changes in the olfactory sulcus and bulb, cortical gray matter, hippocampus, parahippocampus, and basal ganglia that are associated with olfactory dysfunction. Olfactory dysfunction in PD is linked to structural changes in primary olfactory, limbic, and cortical regions. These MRI findings may serve as early biomarkers, but standardized, longitudinal studies are needed to confirm their diagnostic or prognostic value.
10 July 2026
Read appraisal →Translational stroke research
Quantitative Cerebrovascular Analysis for Improved Prediction of Post-Stroke Complications
Endovascular thrombectomy (EVT) has transformed the treatment of acute ischemic stroke (AIS). However, a substantial proportion of AIS patients experience poor outcomes despite successful recanalization, often due to severe neurological deterioration or life-threatening complications. Early identification of these high-risk patients remains a major unmet need. In this study, we developed and validated machine-learning (ML) models that integrate automated quantitative brain arterial morphology and collateral grading with demographic, clinical, laboratory, and imaging variables to predict major post-EVT complications and early neurological outcomes. Using a prospectively collected database of 727 AIS patients that underwent EVT, we developed ML models to incorporate patient-specific vascular morphometry with conventional clinical, laboratory, and imaging data to predict emergence of early neurological deterioration (END), symptomatic intracranial hemorrhage (sICH), malignant brain edema (MBE) requiring surgical decompression, and neurogenic respiratory failure and dysphagia requiring tracheostomy/gastrostomy (TC/PEG). Our analysis of morphological features, including increased tortuosity and reduced vessel diameter, showed strong associations with complications. Morphology-informed (MI) models consistently outperformed baseline-clinical (BC) models for patients with END (AUROC 0.81 for MI model vs. 0.73 for BC), sICH (AUROC 0.68 MI vs. 0.56 BC model), MBE (AUROC 0.67 MI model vs. 0.56 BC), or patients who underwent TC/PEG (AUROC 0.66MI vs. 0.58 BC model). Statistical testing confirmed significant AUROC improvements for END, sICH and mRS (p < 0.05), Finally, patient-specific calibrated probability profiles enabled individualized, multidimensional risk stratification, revealing distinct complication-specific risk patterns across patients. These findings demonstrate that cerebrovascular structure-an often overlooked yet physiologically fundamental determinant of ischemic injury and reperfusion dynamics-provides significant predictive information that is not captured by standard clinical or visual imaging assessments. Automated vascular segmentation and collateral grading techniques enable rapid and objective integration of cerebrovascular metrics into prognostic models, offering a scalable tool for precision risk stratification, supporting earlier intervention, targeted monitoring, and improved post-EVT management.
9 July 2026
Read appraisal →Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology
Topography and functional connectivity analysis of heart surgery-associated brain lesions: a literature review
BACKGROUND: Cardiac surgery is a major therapeutic advancement but remains associated with neurological complications, including ischemic stroke and postoperative cognitive decline. Compared with stroke of other etiologies, ischemic brain injury following cardiac surgery may involve distinct vascular territories and functional networks, potentially influencing its characteristic cognitive profile. METHODS: We performed a systematic review of case reports describing ischemic brain lesions occurring after cardiac surgery in adults with available neuroimaging data. Lesions were manually traced onto a standard brain atlas and compared with ischemic stroke lesions from the ATLAS database, matched for hemispheric involvement. Lesion topography was analyzed at the arterial territory and voxel levels. Lesion network mapping was conducted using normative resting-state functional connectivity data to identify patterns of functional disconnection. Permutation-based statistical analyses were applied, with correction for multiple comparisons and lesion volume included as a covariate. RESULTS: Nineteen articles met the inclusion criteria, yielding 20 cases of post-cardiac surgery ischemic lesions. Compared with stroke controls, these lesions more frequently involved posterior arterial territories, particularly the occipital branches of the posterior cerebral arteries and posterior thalamic regions. Lesion network mapping revealed a distinct pattern of functional disconnection in the occipital lobes, posterior thalamus (including the pulvinar), and medial frontal cortex. CONCLUSIONS: Our results suggest that ischemia associated with cardiac surgery may preferentially involve posterior arterial territories and be associated with distinct patterns of functional disconnection involving the occipital lobe, the pulvinar, and the medial frontal cortex.
6 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 →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 →Physics in medicine and biology
Hybrid learning: a combination of self-supervised and supervised learning for joint MRI reconstruction and denoising in low-field MRI
Objective.Deep learning has demonstrated strong potential for magnetic resonance imaging (MRI) reconstruction. However, conventional supervised learning requires high-quality, high-signal-to-noise-ratio (SNR) reference data for network training, which are often difficult or impossible to obtain, particularly in low-field MRI. Self-supervised learning (SSL) eliminates the need for reference training data but may suffer from degraded performance under low-SNR conditions. To address these limitations, we propose hybrid learning, a new training framework that integrates self-supervised and supervised learning for joint MRI reconstruction and denoising when only low-SNR training data are available.Approach.Hybrid learning is implemented in two sequential stages. In the first stage, SSL is applied to fully sampled low-SNR data to generate higher-quality pseudo-references. In the second stage, these pseudo-references are then used as targets for supervised learning to reconstruct and denoise undersampled, noisy data. The proposed method was evaluated in four experiments using simulated and real noisy MRI data of the breast, lung, and brain across different field strengths (0.3 T to 3 T), sampling trajectories (Cartesian, spiral, and radial), noise levels, and undersampling ratios.Main Results.Hybrid learning consistently improved reconstruction quality relative to both supervised and self-supervised baselines under different acceleration rates, noise levels, and sampling patterns in all experiments. Compared with standard supervised learning using noisy references, it achieved up to 167.70% higher structural similarity index measure (SSIM), 95.41% lower normalized mean squared error (NMSE), and 90.70% lower high-frequency error norm (HFEN). Compared with standard SSL, it achieved up to 23.88% higher SSIM, 60.85% lower NMSE, and 49.13% lower HFEN.Significance.Hybrid learning enables improved MRI reconstruction under low-SNR imaging conditions by jointly addressing noise and undersampling. It provides a practical solution for robust deep learning-based reconstruction and is particularly well suited for applications such as low-field MRI, where image quality is limited by reduced SNR.
26 June 2026
Read appraisal →The journal of headache and pain
The emerging role of the meningeal lymphatic and glymphatic systems in migraine pathophysiology: a systematic review
BACKGROUND/OBJECTIVE: Migraine is a common, debilitating neurological disorder of unclear pathophysiology. Recent evidence has implicated impaired meningeal lymphatic function and its interaction with the glymphatic system in the development of neuroinflammation and pain sensitization. This systematic review aimed to summarize existing evidence on the role of the meningeal lymphatic and glymphatic systems in migraine pathophysiology. METHODS: Following the PRISMA 2020 recommendations, we searched PubMed, Web of Science, and Scopus from inception to December 15, 2025. Inclusion criteria comprised human or animal studies examining meningeal lymphatic or glymphatic function in migraine or validated migraine animal models. SYRCLE's risk of bias tool for animal studies and the Joanna Briggs Institute (JBI) critical appraisal tools were used for quality assessment. RESULTS: The search yielded a total number of 457 records, out of which 10 articles fulfilled the eligibility criteria. These comprised six imaging studies conducted on human populations and four preclinical studies performed on animal models. Studies using dynamic contrast-enhanced (DCE)-MRI have shown changes in lymphatic enhancement characteristics in both episodic and chronic migraines. Diffusion tensor imaging along perivascular spaces (DTI-ALPS) yielded heterogeneous findings, with abnormalities more consistently observed in chronic and high-frequency migraine. Preclinical models demonstrated that cortical spreading depression, nitroglycerin exposure, and familial hemiplegic migraine mutations impaired glymphatic influx and reduced cerebrospinal fluid efflux through meningeal lymphatic vessels. DISCUSSION: Initial research has shown that altered lymphatic and glymphatic systems may be related to migraine. Nonetheless, there is no existing literature on whether these conditions can be considered causative agents for migraines. There is a need for longitudinal imaging studies in a larger population. REGISTRATION: PROSPERO ID: CRD420251266296.
20 June 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 →Cerebellum (London, England)
Novel Imaging Phenotype in Spinal Cerebellar Ataxia Type 8: Symmetrical White Matter Changes without Cerebellar Atrophy
Spinal Cerebellar Ataxia Type 8 (SCA8) is a rare autosomal dominant neurodegenerative disorder characterized by progressive cerebellar dysfunction. It is caused by pathogenic expansions of a CTG/CAG trinucleotide repeat sequence within the ATXN8OS/ATXN8 gene locus on chromosome 13q21. Although cerebellar atrophy is widely recognized as a cardinal neuroimaging feature of SCA8, the phenotypic spectrum remains incompletely characterized. This study identified two cases of SCA8 through genetic analysis. Pedigree information was gathered and analyzed for all available family members. A systematic literature review was conducted to identify all published SCA8 cases with available neuroimaging data. The distinctive clinical and radiological features of SCA8 were analyzed through detailed case characterization integrated with a comprehensive review of existing literature. We report two genetically confirmed SCA8 cases exhibiting a previously undescribed neuroimaging phenotype. Case 1: A 36-year-old woman presented with a one-year history of progressive gait ataxia. Brain MRI revealed confluent, symmetric white matter signal abnormalities without cerebellar atrophy. Repeat expansion analysis detected a pathogenic CTG/CAG expansion of 9/77 in the ATXN8 gene. Case 2: A 64-year-old man (father of case 1) exhibited significant gait abnormalities, cognitive impairment and dysarthria. Brain MRI showed symmetric white matter lesions similar to case 1, with a CTG/CAG repeat length of 17/73. Notably, our systematic review revealed no prior reports of SCA8 presenting with isolated, symmetric white matter abnormalities in the absence of cerebellar atrophy. These findings delineate a novel neuroimaging phenotype of SCA8, characterized by symmetric white matter alterations without cerebellar volume loss. This atypical presentation expands the radiological spectrum of SCA8 and underscores the importance of considering repeat expansion disorders in the differential diagnosis of leukoencephalopathies, even in the absence of classic neurodegenerative imaging signatures.
13 May 2026
Read appraisal →AJNR. American journal of neuroradiology
Hippocampal Subfield Susceptibility Alterations in Mild Cognitive Impairment Revealed by 7T MRI
BACKGROUND AND PURPOSE: Hippocampal magnetic susceptibility alterations may serve as early neurodegenerative biomarkers of Alzheimer disease (AD), but subfield-level evidence in mild cognitive impairment (MCI) remains limited. This study uses submillimeter high-resolution quantitative susceptibility mapping (QSM) to investigate hippocampal subfield susceptibility changes in MCI. MATERIALS AND METHODS: Thirteen individuals with MCI and 13 cognitively normal controls (NC) underwent 7T MRI scans including MP2RAGE and multiecho gradient echo imaging (for QSM). The visibility of hippocampal strata radiatum, lacunosum, and moleculare (SRLM) was assessed using a visual rating scale. Hippocampal subfields (Cornu Ammonis 1 [CA1], CA2, CA3, dentate gyrus [DG], and subiculums) were segmented, and magnetic susceptibility values (χ) were extracted for each subfield. The susceptibility difference between the DG and other subfields was also calculated. Associations between subfield susceptibility measures and cognitive performance were then assessed. RESULTS: Qualitative analysis revealed a distinct hyperintense curved pattern in the hippocampus on the 7T QSM image, corresponding to the SRLM. In NC, this pattern was clearly visible exhibiting consistently delineated boundaries, while it appeared blurred or absent in most subjects with MCI. The visual rating results showed that NC had significantly higher scores than subjects with MCI (Hedgesg = 1.43, 95% confidence interval) [95% CI, 0.60-2.35; P = .003], with most NC rating 3-4 and most subjects with MCI rating 1-2. Quantitative analysis of hippocampal subfield susceptibility revealed significantly elevated susceptibility [χ] in the left DG in those with MCI compared with NC (Hedgeg = 0.88, 95% CI, 0.10-1.72; P = .03), leading to reduced susceptibility contrast between the SRLM and adjacent CA1-CA3 or DG. Furthermore, regional differences of susceptibility between key subfields (left CA1 versus DG and subiculum versus DG) were significantly reduced in MCI, reflecting a loss of subfield contrast. These quantitative changes were significantly associated with lower cognitive performance, even when controlling for age. CONCLUSIONS: 7T QSM reveals susceptibility changes in hippocampal substructures in individuals with MCI, providing a potential early biomarker for AD.
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
Comparative Analysis of Artificial Intelligence-Based Quantification versus Visual Rating of Enlarged Perivascular Spaces in the Multi-Ethnic Study of Atherosclerosis Cohort
BACKGROUND AND PURPOSE: Enlarged perivascular spaces (PVS) are fluid-filled spaces surrounding small cerebral vessels. Current PVS research has been limited by the absence of efficient and scalable quantification tools. We compared visual ratings versus artificial intelligence (AI)-based quantification in identifying associations of PVS with vascular risk factors and cognitive performance. MATERIALS AND METHODS: This cross-sectional study included 235 participants from the Multi-Ethnic Study of Atherosclerosis who had undergone brain MRI and had available both visual ratings and AI-derived PVS quantification. Visual ratings were performed by an expert neuroradiologist (K.D.H.) using a semiquantitative scale. AI-derived counts were based on a fully automated deep learning algorithm. Visual and AI-derived counts were grouped into 4 a priori-defined anatomic locations: basal ganglia, frontoparietal cerebrum, midbrain, and cerebellum. The relationships of PVS counts with demographic characteristics, vascular risk factors, and global and domain-specific cognitive scores were examined using ordinal logistic regression (for ordinal categoric outcomes) and linear regression (for continuous outcomes) models. RESULTS: Mean age (SD) was 72.1 (6.8) years; 95 (40%) participants were men; and 126 (54%) self-reported as black. Means (SD) of AI-derived regional PVS counts were 63.7 (24.6) for basal ganglia, 414.9 (167.5) for frontoparietal cerebrum, and 9.8 (4.4) for midbrain. On visual ratings, the most prevalent count category for each region was 11-20 for basal ganglia (40%), 21-40 (31%) for frontoparietal cerebrum, and 1-5 (83%) for midbrain. For basal ganglia PVS, while both methods were associated with older age and white race/ethnicity, AI-derived counts exhibited additional associations with higher systolic blood pressure (β, 0.20; 95% CI, 0.05-0.36) and diabetes (unstandardized β coefficient [β], 11.51; 95% CI, 3.48-19.55), as well as poorer global cognition (β, -0.012; 95% CI, -0.023 to -0.0004), delayed memory (β, -0.005; 95% CI, -0.010 to -0.0005), and attention/processing speed (β, -0.005; 95% CI, -0.009 to -0.001) cognitive performance. CONCLUSIONS: In this cross-sectional study, AI-derived PVS quantification was more sensitive in detecting associations with vascular risk factors and cognitive outcomes than traditional visual ratings. AI-based quantification may aid in the analysis of large-scale epidemiologic data, advancing PVS research.
11 May 2026
Read appraisal →AJNR. American journal of neuroradiology
Neuroimaging Predictors of Futile Recanalization in Anterior Circulation Stroke: A Systematic Review and Meta-Analysis
BACKGROUND: Mechanical thrombectomy (MT) has transformed the management of large vessel occlusion stroke; however, a considerable proportion of patients fail to achieve functional recovery despite successful recanalization. This futile recanalization underscores the need to better understand imaging biomarkers that may predict poor outcomes after endovascular therapy. PURPOSE: To systematically review and synthesize evidence on neuroimaging biomarkers associated with futile recanalization after MT in acute ischemic stroke. DATA SOURCES: PubMed, Scopus, Web of Science, and EMBASE databases were searched up to March 2025, supplemented by manual reference screening. STUDY SELECTION: Eligible studies enrolled adult patients with anterior-circulation stroke who underwent thrombectomy, reported pretreatment neuroimaging findings, and evaluated functional outcomes despite successful reperfusion. Case reports, reviews, abstracts, and nonhuman studies were excluded. DATA ANALYSIS: Two reviewers independently screened, extracted data, and assessed study quality using the Prediction Model Risk of Bias Assessment Tool. Random-effects meta-analysis was performed where appropriate. Heterogeneity, publication bias, and sensitivity analyses were undertaken. DATA SYNTHESIS: Fifty-one studies were included. Lower ASPECTS scores were strongly associated with futile recanalization (OR = 0.81). Core infarct volume showed inconsistent associations, whereas perfusion and collateral markers, including elevated hypoperfusion intensity ratio, delayed venous outflow, and poor collateral scores, demonstrated strong predictive value. Chronic white-matter injury, leukoaraiosis, and cerebral atrophy were also consistently associated with worse outcomes. LIMITATIONS: Limitations included heterogeneity in imaging protocols and thresholds; predominance of retrospective single-center cohorts; limited direct comparison across imaging modalities; and variable adjustment for confounders. CONCLUSIONS: Neuroimaging biomarkers, particularly ASPECTS, perfusion-derived metrics, collateral status, and markers of chronic small vessel disease, provide important prognostic information for identifying patients at risk of futile recanalization despite successful thrombectomy.
11 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 →Journal of neuroradiology = Journal de neuroradiologie
Automated estimation of perivascular space and brain morphometry from deep learning-reconstructed three-dimensional T1-weighted MRI: comparison with the conventional technique
PURPOSE: To evaluate the utility of deep learning-based reconstruction (DLR) three-dimensional T1-weighted imaging (T1-WI) in improving fine structural delineation through the automated estimation of brain morphometry and perivascular space (PVS). MATERIALS AND METHODS: In this retrospective cohort study, participants who underwent T1-WI between August 2021 and June 2022 were included. Participants were categorized into normal and disease groups based on the presence of visible cerebral lesions. Cortical thicknesses and cerebral volumes from DLR T1-WI were estimated using FreeSurfer and compared to those derived from conventional T1-WI. Additionally, participants were grouped by MRI-visible PVS severity according to the number of enlarged PVS in centrum semiovale and basal ganglia. PVS volumes from DLR and conventional T1-WI were compared across these groups. Statistical comparisons were performed using a paired independent t-test with Benjamin-Hochberg adjustment. RESULTS: 240 participants (mean age: 40.8 ± 17 years) were included. In the normal group (n = 144), cortical thicknesses and volumes were significantly greater in DLR T1-WI compared to conventional T1-WI (P < 0.001). This trend was also observed in the disease group (n = 96) and in external datasets (n = 63). Across all three PVS severity groups (mild, n = 111; moderate, n = 71; severe, n = 58), DLR T1-WI significantly reduced PVS volumes and variability compared to conventional T1-WI. DLR T1-WI demonstrated PVS volumes (mild: 738.4 mm³ vs. 1408.1 mm³; moderate: 919.0 mm³ vs. 1895.8 mm³; severe: 1328.5 mm³ vs. 2711.7 mm³; all P < 0.001) and variability (mild: 224.4 mm3 vs. 420.9 mm³; moderate: 229.7 mm3 vs. 462.9 mm³; severe: 382.4 mm3 vs. 653.6 mm³) that were consistently smaller. CONCLUSION: DLR T1-WI yielded cerebral cortical thickness and volume measurements that were more consistent with expected anatomical values than those from conventional T1-WI.PVS volumes measured from DLR T1-WI exhibited less variability and better concordance with radiologists' visual assessments.
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 →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 →Reviews in the neurosciences
Microstructural alterations of the amygdala in neurodegenerative and neuroinflammatory disorders: insights from diffusion tensor imaging
Diffusion tensor imaging (DTI) is a valuable method for evaluating microstructural changes in the amygdala associated with neurodegenerative and neuroinflammatory disorders. This systematic review examines amygdala microstructural alterations in Alzheimer's disease (AD), Parkinson's disease (PD), amyotrophic lateral sclerosis (ALS), dementia with Lewy bodies (DLB), and multiple sclerosis (MS) using DTI metrics. Following PRISMA 2020 guidelines, we searched PubMed, Scopus, and Web of Science databases through August 2025, identifying 4,442 records. After screening and eligibility assessment, 13 studies were included, comprising 1,412 patients and 1,146 healthy controls. Due to sample heterogeneity and lack of standardized effect size measures, meta-analysis was not performed. Across disorders, elevated mean diffusivity (MD) emerged as the most consistent finding, present in 100 % of AD patients and observed in all examined conditions. Reduced fractional anisotropy (FA) was the second most frequent alteration, with 36.6 % of AD patients showing decreased FA. In MS, increased radial diffusivity (RD) was prominent, while longitudinal DLB studies revealed progressive free water (FW) increases. These DTI-based microstructural changes often preceded volumetric atrophy and correlated with clinical severity. Our findings demonstrate that DTI metrics, particularly MD and FA, serve as sensitive markers of amygdala pathology across neurodegenerative diseases and may facilitate early diagnosis, disease monitoring, and differential diagnosis of these conditions.
26 Apr 2026
Read appraisal →Journal of neurology
Iron accumulation in multiple sclerosis and implications for cognitive and clinical progression: a systematic review of advanced neuroimaging studies
BACKGROUND AND AIMS: Iron-related alterations are frequently implicated in multiple sclerosis (MS) neurodegeneration, but its relationship with clinical symptoms and cognitive impairment remains unclear. We systematically reviewed evidence linking iron-sensitive susceptibility-based magnetic resonance imaging (MRI) metrics to cognitive outcomes, in order to evaluate their potential role as diagnostic and prognostic biomarkers of cognitive decline in MS. MATERIALS AND METHODS: A systematic review was conducted using the PRISMA guidelines. 600 studies were identified by searching PubMed, Scopus, Web of Science, and Embase in October 2025. After screening, 12 studies fulfilled the eligibility criteria and were included. RESULTS: Two main patterns emerged: (i) higher basal ganglia susceptibility/iron-related metrics are consistently linked to worse cognitive performance, particularly information processing speed and executive control; and (ii) thalamic findings are more variable in direction and clinical meaning, with susceptibility often capturing a mixed signal that overlaps with thalamic atrophy. CONCLUSIONS: Iron-sensitive quantitative MRI captures clinically relevant deep gray matter (DGM) pathology associated with cognitive impairment in MS, with basal ganglia measures showing the strongest linkage with cognitive and clinical outcomes. Future studies should include harmonized methodology and a longitudinal component.
19 Apr 2026
Read appraisal →Journal of neurointerventional surgery
Intravascular lithotripsy in calcified carotid stenosis: technical and clinical outcomes
INTRODUCTION: Carotid artery stenosis (CAS) is a major cause of stroke, disability, and mortality worldwide. While medical therapy and revascularization remain the cornerstones of management, both surgical and endovascular approaches can be limited by complex anatomy and heavily calcified plaques, which increase procedural risk. Intravascular lithotripsy (IVL), originally developed for coronary and peripheral interventions, has recently emerged as a potential strategy for plaque modification in CAS. By delivering localized shockwave pulses, IVL fractures vascular calcium, facilitating safer angioplasty and stent deployment. However, its use in CAS remains off-label and poorly described. METHODS: A systematic search of PubMed, Google Scholar, and Embase was conducted in September 2025 in accordance with Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines. Eligible studies included patients with CAS undergoing IVL with reported procedural success and/or clinical outcomes. Risk of bias was assessed using the Joanna Briggs Institute (JBI) appraisal tools. RESULTS: Fifteen studies comprising 120 patients were included. The mean age ranged from 50 to 82 years, and the degree of stenosis from 70%-95%. Technical success was reported in 100% of cases. Across the pooled cohort, 101 of 120 patients (84.2%) achieved residual stenosis ≤30%. Seven patients (5.8%) experienced ipsilateral stroke or transient ischemic attack within 30 days. CONCLUSION: IVL for CAS is an emerging therapy demonstrating consistent technical feasibility and favorable short-term safety across published studies. These findings suggest that IVL may benefit patients with complex calcified plaques at high risk for standard revascularization; however, randomized controlled trials are needed to confirm its role in clinical practice.
17 Apr 2026
Read appraisal →Journal of neurology, neurosurgery, and psychiatry
Breaking the PROMISE: poor association between brain volume loss and clinical disability worsening over 2 years of follow-up in primary progressive multiple sclerosis.
BACKGROUND: Phase 2 clinical trials in primary progressive multiple sclerosis (PPMS) often use MRI brain volume measures as their primary endpoint. Here, we investigate the longitudinal association between change in MRI outcomes and change in disability over 2 years of follow-up in a large and well-characterised PPMS trial dataset. METHODS: Using the dataset from PROMISE (n=943, mean age of 58.0 years, mean Expanded Disability Status Scale (EDSS) 5.0, and mean disease duration of 10.5 years at baseline), a phase 3 trial of glatiramer acetate in PPMS, we described the change in MRI and disability measures during follow-up and used multivariable logistic regression models to investigate whether change in four MRI outcomes (grey matter volume, white matter volume, brain fraction and total burden of disease) was associated with seven measures of clinical disability worsening (including the EDSS, Timed 25 Foot Walk, Nine-Hole Peg Test and Paced Auditory Serial Addition Test). RESULTS: We found only weak and inconsistent associations between change in MRI and physical and cognitive outcome measures over 2 years of follow-up. Change in MRI measures in year 1 of the trial did not predict change in physical nor cognitive disability in year 2. DISCUSSION: The association of the investigated volumetric MRI measures and clinical disability outcomes was noticeably weak and inconsistent. Our findings question the suitability of brain volume loss and lesion burden accumulation as functionally relevant trial endpoints in PPMS and inform the design and interpretation of clinical trials in PPMS.
17 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 →Journal of the American Heart Association
A Position Statement on Endovascular Models and Effectiveness Metrics for Mechanical Thrombectomy Navigation, on Behalf of the Stakeholder Taskforce for Artificial Intelligence-Assisted Robotic Thrombectomy (START)
Although we are making progress in overcoming infectious diseases and cancer, one of the major medical challenges of the mid-21st century will be the increasing prevalence of stroke. Occlusions in large vessels are especially debilitating, yet effective treatment-needed within hours to achieve best outcomes-remains limited because of geographic accessibility. One solution for improving timely access to mechanical thrombectomy in geographically diverse populations is the widespread deployment of robotic surgical systems. Artificial intelligence assistance may enable the safe and effective upskilling of operators in this emerging therapeutic delivery approach. Our aim was to establish consensus frameworks for developing and validating artificial intelligence-assisted robots for thrombectomy. Objectives included standardizing effectiveness metrics and defining reference testbeds across in silico, in vitro, ex vivo, and in vivo environments. To achieve this, we convened experts in neurointervention, robotics, data science, health economics, policy, statistics, and patient advocacy. Consensus was built through an incubator day, a Delphi process, and a final position statement. We identified that the 4 essential testbed environments each had distinct validation roles. Realism requirements vary: simpler testbeds should include realistic vessel anatomy compatible with guidewire and catheter use, whereas standard testbeds should incorporate deformable vessels. More advanced testbeds should include blood flow, pulsatility, and disease features, such as atheromatous plaques. There are 2 macroclasses of effectiveness metrics: one for in silico, in vitro, and ex vivo stages focusing on technical navigation (eg, path-following error), and another for in vivo stages, focused on clinical outcomes (eg, modified treatment in cerebral infarction scores). Patient safety is central, and not a barrier, to this technology's development. One requisite patient safety task needed now is to correlate in vitro measurements to in vivo complications.
8 Apr 2026
Read appraisal →JMIR medical informatics
Deep Learning for Content-Based Medical Image Retrieval in Picture Archiving and Communication Systems for Brain Tumor Detection: Algorithm Development and Validation
BACKGROUND: Advances in medical imaging have led to massive archives, yet navigating these datasets remains challenging due to the limitations of traditional text-based search engines. While content-based medical image retrieval (CBMIR) offers a visual feature-based solution to enhance clinical workflows and research, its operational integration into picture archiving and communication systems (PACS) remains a significant bottleneck. Despite the progress in deep learning for feature extraction, CBMIR tools are rarely integrated and effectively implemented within existing radiology information systems due to complex protocol barriers. OBJECTIVE: To address these challenges, this study develops a CBMIR system meticulously designed to cater to 7 distinct types of brain tumors as seen in brain magnetic resonance images. Our system is tailored to assist radiologists and health care professionals in efficiently retrieving pertinent historical medical images, thereby providing quantitative decision support for radiologists and facilitating evidence-based case comparison, with the potential to improve retrieval efficiency and clinical workflow, rather than directly enhancing diagnostic accuracy. METHODS: The dataset used in this study was collected from a single medical center and is not publicly available. The core innovation is a state-of-the-art deep learning-based feature extraction algorithm specifically engineered for the CBMIR system. We use GoogLeNet as the primary architecture, incorporating generalized mean pooling to capture nuanced local features and an embedding layer for dimension reduction. Crucially, we address the integration gap by harmonizing 2 open-source projects to successfully embed the CBMIR system into a functional PACS environment via standard protocols. RESULTS: The image dataset contains 658 participants with 15,873 images collected from 2000 to 2017. The empirical findings of our research demonstrate the performance and robustness of the proposed CBMIR system. Our system achieves a remarkable mean average precision score of 89.16% and an equally impressive Precision@10 score of 94.08%. These metrics affirm the system's efficacy in retrieving relevant medical images. Furthermore, we successfully integrate the CBMIR system into a PACS by successfully harmonizing 2 open-source projects. CONCLUSIONS: This study presents the design and implementation of a PACS-integrated CBMIR system for brain magnetic resonance imaging, and the experimental results demonstrate that the system can achieve efficient and accurate image retrieval within a clinical workflow.
7 Apr 2026
Read appraisal →AJNR. American journal of neuroradiology
Reliability of Pseudocontinuous Arterial Spin-Labeling in Ischemic Stroke and Comparison with Other Perfusion Techniques: Systematic Review and Meta-Analysis
BACKGROUND: Pseudocontinuous arterial spin-labeling (pCASL) is a noninvasive, gadolinium-free MRI technique for assessing brain perfusion. PURPOSE: The test-retest reliability of pCASL-derived CBF measurements in ischemic stroke (IS) were evaluated and pCASL metrics were compared with those from DSC, CTP, and PET. DATA SOURCES: Systematic searches were conducted in MEDLINE, EMBASE, and LILACS. Risk of bias and methodologic quality were evaluated using QUADAS-2 and Quality Appraisal for Reliability Studies tools. STUDY SELECTION: Eleven studies, encompassing 383 participants with IS were included. DATA ANALYSIS: Random-effects meta-analysis with inverse variance method and heterogeneity assessed using I 2 statistics were used. DATA SYNTHESIS: No PET studies were identified. Only 1 low-quality, high-risk-of-bias study assessed test-retest reliability, finding no significant differences in repeated absolute CBF measurements over time and excellent reliability across regions. Most studies comparing pCASL with DSC, and all comparing pCASL with CTP, had a low risk of bias. In the hyperacute phase of IS, pCASL and DSC showed no significant differences in infarct core relative CBF (95% CI, -0.11 to 0.13; I 2 = 0%) or hypoperfusion volumes (95% CI, -0.28 to 0.68; I 2 = 69%). Evidence on the comparability of pCASL with other DSC or CTP metrics was limited. LIMITATIONS: The small number of included studies prevented a meta-analysis for the primary outcome and limited conclusions for secondary outcomes. CONCLUSIONS: Robust conclusions about the test-retest reliability of pCASL or the comparability of metrics obtained with this technique and DSC, CTP, or PET in different phases after IS could not be drawn.
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 →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 →Diagnostic and interventional imaging
Deep learning-based image reconstruction significantly improves image quality of MRI examinations of the orbit at 3 Tesla.
PURPOSE: The purpose of this study was to assess the benefit of a deep learning-based image reconstruction (DLBIR) for improving image quality in orbital magnetic resonance imaging (MRI) at 3 Tesla (T). MATERIALS AND METHODS: Seventy-one patients (48 women and 23 men) with a mean age of 52 ± 19.5 (standard deviation [SD]) years (age range: 7-90 years) who underwent MRI examination of the orbit at 3 T between January and June of 2024, were included in the study. Coronal T2-weighted MR images obtained in 70 patients and post-contrast fat-saturated (FS) coronal T1-weighted MR images obtained in 25 patients, were reconstructed with and without DLBIR, resulting in four imaging sets. Two radiologists independently and blindly measured the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of the optic nerves on the four imaging sets. Image quality and orbital abnormalities were assessed using a standardized 5-point Likert scale. Comparisons between MR images obtained with and without DLBIR were performed using Wilcoxon test for ordinal and quantitative variables and McNemar test for paired binary data. RESULTS: SNR and CNR of coronal T2-weighted MR images were significantly greater using DLBIR (26.67 ± 9.03 [SD], and 14.87 ± 10.31 [SD], respectively) than without DLBIR (18.91 ± 7.28 [SD], and 9.78 ± 8.47 [SD], respectively) (P < 0.001). There were no differences in SNR and CNR between post-contrast FS T1-weighted images obtained with DLBIR (85.56 ± 63.13 [SD], and 64 ± 41.38 [SD], respectively) and those obtained without DLBIR (91.36 ± 48.49 [SD], and 43.25 ± 20.4 [SD], respectively) (P = 0.35, and P = 0.14, respectively). Qualitatively, good-to-excellent image quality was obtained more frequently with DLBIR than without DLBIR for T2-weighted and post-contrast FS T1-weighted images with respect to optic nerve sharpness (67 % vs. 16 %, and 8 % vs. 0 %, respectively), brain sharpness (90 % vs. 6 %, and 68 % vs. 4 %, respectively), and overall image quality (73 % vs. 1 % and 36 % vs. 0 %, respectively) (all P ≤ 0.001). No significant differences in the detection rates of orbital abnormalities were found between MR images obtained with and without DLBIR, including optic nerve hyperintensity (34 % vs. 31 %, respectively; P = 0.16) and optic nerve atrophy (33 % for both) on T2-weighted images, and optic nerve enhancement on post-contrast FS T1-weighted images (16 % for both). CONCLUSION: DLBIR significantly improves image quality of MRI examinations of the orbit at 3 T, without losing clinically relevant information.
4 Apr 2026
Read appraisal →AJNR. American journal of neuroradiology
Multimodal CT Perfusion-Based Deep Learning for Predicting Stroke Lesion Outcomes in Complete and No Recanalization Scenarios
BACKGROUND AND PURPOSE: Predicting the final location and volume of lesions in acute ischemic stroke is crucial for clinical management. While CTP is routinely used for estimating lesion outcomes, conventional threshold-based methods have limitations. We developed specialized outcome-prediction deep learning models that predict infarct core in successful reperfusion cases and the combined core-penumbra region in unsuccessful reperfusion cases. MATERIALS AND METHODS: We developed single-modal and multimodal deep learning models using CTP parameter maps to predict the final infarct lesion on follow-up DWI. Using a multicenter data set from multiple sites, we developed deep learning models and evaluated them separately for patients with complete recanalization (successful reperfusion [CR], n = 350) and no recanalization (unsuccessful reperfusion [NR], n = 138) after treatment. The CR model was designed to predict the infarct core region, while the NR model predicted the expanded, hypoperfused tissue encompassing both the core and penumbra regions. Five-fold cross-validation was performed for robust evaluation. RESULTS: The multimodal 3D nnU-Net model demonstrated superior performance, achieving mean Dice scores of 35.36% in patients with CR and 50.22% in those with NR. This model substantially outperformed the current clinically used method, providing more accurate outcome estimates than the conventional single-technique threshold-based measures, which yielded Dice scores of 15.73% and 39.71% for CR and NR groups, respectively. CONCLUSIONS: Our approach offered both successful reperfusion and unsuccessful reperfusion estimations for potential treatment outcomes, enabling clinicians to better evaluate treatment eligibility for reperfusion therapies and assess potential treatment benefits. This advancement facilitates more personalized treatment recommendations and has the potential to substantially enhance clinical decision-making in acute ischemic stroke management by providing more accurate tissue outcome predictions than conventional single-technique threshold-based approaches.
4 Apr 2026
Read appraisal →