Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 64 appraisals
Medical physics
Reference-Free large language model agents for physician-guided radiotherapy treatment planning
BACKGROUND: Large language models (LLMs) have recently demonstrated exceptional capabilities, offering the potential to streamline workflows and enhance efficiency across diverse tasks. However, their application in domain-specific areas, such as radiotherapy treatment planning, remains challenging due to the lack of publicly available, specialized knowledge required for these tasks. PURPOSE: To investigate the critical architectural and functional components necessary to adapt an off-the-shelf large language model into a clinically viable planning agent for inverse treatment planning in intensity-modulated radiation therapy (IMRT). MATERIALS/METHODS: Twenty head-and-neck (HN) cancer patients who received IMRT at our institution were retrospectively collected under IRB approval. The LLM agent was implemented to directly interact with the clinical treatment planning system (TPS) to iteratively extract intermediate plan states and propose new constraint values to guide inverse optimization. Its decision-making was informed by real-time plan evaluations and prior optimization outcomes, enabling adaptive refinement of planning strategies across iterations. The agent was equipped with three core capabilities: comprehension of clinical planning objectives, contextual understanding of the optimization environment, and arithmetic proficiency for quantitative reasoning. Treatment planning was conducted in a reference-free inference setting, wherein the LLM operated without prior exposure to manually generated treatment plans and without any fine-tuning or task-specific training. LLM-generated treatment plans were compared with clinically approved plans created by certified dosimetrists. Key dosimetric endpoints were evaluated and statistically analyzed. Paired comparisons between LLM-generated and clinical plans were performed using the Wilcoxon signed-rank test. RESULTS: LLM-generated plans achieved comparable organ-at-risk (OAR) sparing relative to clinical plans, while demonstrating improved hot spot control (Dmax: 106.5% vs. 108.8%, p < 0.05) and superior conformity (conformity index: 1.18 vs. 1.39, p < 0.05 for boost PTV; 1.82 vs. 1.88, p = 0.47 for primary PTV). CONCLUSIONS: This study demonstrates the feasibility of a reference-free, LLM-driven workflow for automated IMRT treatment planning in a commercial TPS. The proposed approach provides a generalizable solution that could reduce planning variability and support broader adoption of AI-based planning strategies.
2 Aug 2026
Read appraisal →Physics in medicine and biology
Anatomically adaptive feature-wise linear modulation for deep learning-based low-dose CT denoising
Objective.Low-dose computed tomography (LDCT) reduces radiation dose but, introduces heterogeneous noise due to different photon attenuation based on anatomical tissue. Most deep learning techniques assume uniform noise in LDCT and perform equal noise removal across different regions, leading to sub-optimal performance across different tissues. This work aims to design a physics-based framework that explicitly models region-dependent noise characteristics to improve LDCT noise removal.Approach.We propose an anatomically adaptive noise reduction framework. The proposed anatomically adaptive feature-wise linear modulation (FiLM) model consists of a U-Net architecture that integrates two complementary units: the global FiLM unit in the encoder, which modifies features globally based on global image statistics to remove overall noise, and the local FiLM unit in the decoder, which modifies features locally based on the type of anatomical tissue. This dual design enables the modeling of overall image noise characteristics in addition to the removal of local noise associated with each anatomical tissue.Main results.The model performance was evaluated using AAPM-Mayo Clinic LDCT dataset, and the trained model tested on the TCIA dataset. The proposed model outperformed all competing methods. Local noise analysis showed that noise removal was consistent across different anatomical regions, achieving 37.14% in the lung, 48.75% in soft tissue, and 35.18% in bone. Visual results also confirmed significant improvements in noise removal, preservation of structural details, and reduction of non-residual distortions. Furthermore, the model demonstrated its ability to generalize under domain shift.Significance.This work presents a framework for anatomically adapted noise removal by linking feature modification with the physical properties of noise in LDCT through a dual-modulation process for both general and tissue-related noise. The model achieves a balance between noise removal and preservation of anatomical detail, making it a robust approach to LDCT noise removal.
28 July 2026
Read appraisal →Journal of radiation research
A model-based selection of oral cancer patient for passive scattering proton beam therapy
BACKGROUND AND PURPOSE: To identify patients with oral cancer (OC) who benefit from proton therapy versus photon therapy using a model-based approach (MBA) to reduce late adverse events. MATERIAL/METHODS: Passive scattering proton beam therapy (PSPT) and volumetric modulated arc therapy (VMAT) plans were established for 40 patients with OC, consisting of a dose of 70 Gy (relative biological effectiveness) in 35 fractions. At least 95% of the planning target volume received 95% of the prescribed dose, and the dose to the organs at risk was restricted to be as low as possible. Normal tissue complication probability (NTCP) was used to estimate the risk of late adverse events, including dysgeusia, xerostomia and osteoradionecrosis of the mandible. Patients who were considered as candidates for PSPT were selected if the NTCP difference between both plans (ΔNTCP) exceeded the threshold defined in the Dutch national indication protocol. RESULTS: PSPT reduced the doses to the spinal cord, pharynx, oral cavity and contralateral salivary glands compared with VMAT. PSPT was also superior for the risk evaluation of each late adverse event calculated by incorporating dose metrics and patient baseline risk factors. For the MBA using ΔNTCP and the thresholds, PSPT was indicated in 24 of the 40 cases, and the remaining 16 cases were considered to be equivalent to VMAT. CONCLUSION: MBA was used to select OC cases that were candidates for PSPT. Compared with VMAT, the risk of expected late adverse events was significantly reduced with PSPT, and 60% of patients were considered eligible for PSPT.
26 July 2026
Read appraisal →Physics in medicine and biology
Four-dimensional on-beam computed tomography reconstruction using projection-difference images
Purpose.Accurate verification of delivered dose requires anatomical information during the treatment beam delivery. However, conventional cone-beam computed tomography (CBCT) is typically acquired prior to beam delivery and fails to account for intrafractional tumor shift/drift. This study aims to develop a 4D on-beam computed tomography (4D OBCT) framework to capture anatomical states during irradiation.Materials and methods.A thoracic phantom with rigid tumor motion was used to develop a conformal arc treatment plan. During delivery, the target was displaced by 1 cm superior to its planned position to simulate a baseline shift, and megavoltage transmission data were acquired using an electronic portal imaging device. Transmission data corresponding to the planned tumor position were obtained from the planning CT (pCT) via Monte Carlo simulation. Volumetric difference images were reconstructed from the differences between the measured and simulated transmission data for each phase. Subsequently, the images were superimposed onto the corresponding phases of the 4D pCT to obtain 4D OBCT. For evaluation, we compared 4D OBCT with 4D pCT (ground-truth) and 4D CBCT which were acquired after the target displacement. A dosimetric performance was evaluated by recalculating 4D dose distributions on the three images and comparing in dose-volume histograms and gamma indices.Results.4D OBCT achieved lower root mean square error than 4D CBCT in both the lung (58.46 HU vs 74.37 HU) and chest wall regions (23.78 HU vs 66.84 HU). This quantitative accuracy was also reflected in the dosimetric comparison. Under 2%/2 mm and 1%/1 mm criteria, 4D OBCT achieved gamma pass rates of 99.76% and 99.08%, respectively, whereas 4D CBCT yielded 72.50% and 57.77%, respectively.Conclusions.The proposed 4D OBCT framework successfully reconstructed accurate phase-resolved images of the target during irradiation. By providing high-resolution volumetric images that reflect intrafractional motion, 4D OBCT could provide a robust solution for precise post-delivery dosimetric verification and adaptation.
12 July 2026
Read appraisal →Radiation protection dosimetry
Impact of neutron sieve therapy for deep site in boron neutron capture therapy using Monte Carlo calculation
Recent Boron neutron capture therapy (BNCT) has shifted to accelerator-based systems. One of them is a compact neutron generator developed using silicon carbide (SiC) semiconductors by Fukushima SiC Applied Technology Co. However, neutron penetration remains a critical challenge for treating deep-seated tumors. This study investigated the potential of neutron sieve therapy, originally developed to enhance the depth dose distribution in X-ray therapy, to improve BNCT dose distribution via Monte Carlo simulations based on the Fukushima SiC BNCT system. Dose distribution changes were investigated using polyethylene and 6LiF-plastic in block and sieve shapes. The results show that the maximum thermal neutron fluence depth was shallower (deeper) with polyethylene (6LiF-plastic) filters. The sieve filter moderately altered the dose distribution compared to the block filter due to density differences. The maximum dose point shifted 8 mm deeper using a sieve filter composed of 6LiF-plastic and polyethylene, with a 5.5% increase at 20 mm depth in neutron fluence at the same skin dose.
8 July 2026
Read appraisal →Biomedical physics & engineering express
A verification-oriented review of reaction-enhanced radiotherapy: linking nuclear data, transport modeling, and measurable observables
Reaction-enhanced radiotherapy (RER) aims to improve the therapeutic ratio of particle therapy by exploiting isotope-specific nuclear reactions that generate localized high-linear energy transfer secondary radiation. Absorbed dose remains the central metric for radiotherapy planning and evaluation; however, RER introduces additional verification requirements related to nuclear-reaction data, mixed-field transport, isotope delivery, and measurable secondary-field observables. This review frames RER as a verification-oriented physics problem built on three interdependent pillars: covariance-aware nuclear data, high-fidelity Monte Carlo transport, and reaction-specific secondary-field monitoring. Boron neutron capture therapy (BNCT) is treated as the clinically mature benchmark for RER, whereas PBCT and the emerging15N(p,α)12C-based proton-carbon-alpha therapy (Proton-CAT) are discussed as early-stage comparative cases. BNCT has the strongest clinical evidence base, while PBCT remains constrained by narrow resonances, low reaction yield, and limited observability. Proton-CAT provides a candidate 4.439 MeV prompt-γobservable whose verification value still requires detector-level validation and delivery/selectivity assessment. Overall, clinically credible RER requires coordinated progress in uncertainty-aware nuclear data, detector-integrated transport modeling, isotope delivery and tumor-to-normal biodistribution assessment, and high-sensitivity radiation monitoring for therapy verification.
7 July 2026
Read appraisal →Journal of medical systems
Security Analysis of a Federated Learning Framework for Medical Image-to-Image Translation
Federated Learning (FL) emerged as a privacy-preserving paradigm for collaborative training of deep learning models across institutions without sharing patient data. This approach has been applied to complex tasks such as medical image-to-image (I2I) translation, including MRI-to-synthetic CT (sCT) generation. However, existing federated I2I frameworks often assume privacy preservation as an inherent property of FL rather than a requirement to be explicitly validated, leaving their robustness to representative adversarial threat scenarios largely unexplored. In this study, we evaluated the vulnerability of a federated MRI-to-sCT translation framework (FedSynthCT-Brain) to three representative attack classes: Deep Leakage from Gradients (DLG), Federated Membership Inference Attack (FedMIA), and data poisoning. The efficacy of corresponding defense mechanisms, such as Secure Aggregation (SecAgg) and Byzantine-robust median aggregation (FedMedian), were assessed. DLG enabled only the recovery of coarse anatomical structures, with no clinically identifiable details (SSIM ≤ 0.16, PSNR ≤ 11 dB) across clients, suggesting limited vulnerability under the evaluated DLG setting. In contrast, FedMIA achieved high membership discrimination, with AUC scores between 0.92 and 0.99, revealing a critical privacy vulnerability. The introduction of SecAgg reduced AUC values to near-random levels (0.23-0.56) across all centers without impacting synthesis quality. Under high-noise poisoning, the standard federated averaging (FedAvg) aggregation rendered the federation inoperative, while FedMedian restored performance close to the no-poisoning baseline in most scenarios, with significant residual degradation in specific center configurations. At low noise levels, the advantage of FedMedian was less consistent, as low-level noise injection may be indistinguishable from natural heterogeneity across centers, potentially enabling stealthy degradation. These findings demonstrate that federated I2I translation frameworks are not inherently secure and require explicit, multi-layered evaluation. As FL is increasingly adopted in clinical workflows, our results underscore the necessity of integrating cryptographic, algorithmic, and infrastructural safeguards for secure deployment.
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 →Physics in medicine and biology
Deep learning-based dose prediction to enhance planning efficiency in cervical brachytherapy with hybrid applicators
Objective.This study aimed to develop a dose prediction model for hybrid applicators in cervical cancer brachytherapy.Approach.A total of 216 previous treatment plans were collected and divided into three datasets: training (161 plans), testing (40 plans), and clinical evaluation (15 plans). The treatment plans included three hybrid applicator types: tandem and ovoids combined with interstitial needles, tandem and ring combined with interstitial needles, and tandem and cylinder combined with interstitial needles. The model was validated on the testing dataset using mean absolute error (MAE) for voxel-wise dose evaluation and on the clinical evaluation dataset using dice similarity coefficient (DSC) and dose statistic differences.Main results.The model achieved a voxel-wise MAE of 0.45 ± 0.27 Gy and showed no statistically significant differences (p> 0.05) in all key dose-volume histogram parameters when compared to clinical plans. The DSC values ranged from 0.74 to 0.77. Small dosimetric differences between the optimized and manually generated plans were observed for the high-risk clinical target volume (HR-CTV) D98%, HR-CTV D90%, and bladder D2cc.Significance.The developed dose prediction model demonstrates significant potential for application in hybrid applicator brachytherapy. This model can provide guidance for dose delivery during dwell time optimization. As a reference for optimization, it has the potential to streamline the planning process, reduce planning time, and improve consistency in adaptive workflows.
3 July 2026
Read appraisal →Physics in medicine and biology
Deep learning based time series analysis for breathing phase prediction in phase-gated proton therapy
Objective. Phase gating is a critical technique to mitigate tumor motion during radiotherapy, particularly in spot-scanned particle therapy where internal motion can interfere with dynamic spot scanning patterns and, simultaneously, introducing substantial range uncertainties. However, the current commercial state of the art in real-time phase prediction is challenged by patient-specific breathing variability as well as detection and delivery system latencies. This leads to suboptimal efficiency, mis-timed radiation delivery and requires frequent manual intervention. This study aims to improve phase prediction accuracy using deep learning (DL)-based time series forecasting to enable more accurate dose delivery.Approach. Retrospective breathing waveforms from 69 proton therapy patients, sampled at 30 Hz, were labeled with inspiratory peaks and assigned subjective regularity scores (four levels). DL models with various architectures were trained using waveform amplitude to predict current or future breathing phases. Model performance was evaluated using mean squared error, phase binning accuracy, and timing deviation for radiation on/off events. Bayesian optimization was used for hyperparameter tuning. Results were compared between models and against a commercial algorithm currently in clinical use.Main Results. The curated waveform dataset included 165 242 s for training, 24 057 s for validation, and 30 322 s for testing, with an additional 40 604 s from separate patients for extended validation. The long short-term memory and temporal fusion transformer models significantly outperformed the commercial algorithm, improving phase prediction accuracy by nearly 20% and reducing timing deviations across all regularity levels.Significance. DL-based time series forecasting may substantially improve breathing phase prediction accuracy over current clinically available methods, offering a more precise and reliable approach to phase-gated radiation delivery.
2 July 2026
Read appraisal →Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)
Advancing radiotherapy with deep learning: A review of dose prediction models
BACKGROUND: Artificial intelligence (AI), especially deep learning algorithms, holds significant promise in transforming radiation therapy by enabling more precise, personalized, and efficient treatment planning. In particular, deep learning models have demonstrated their utility in critical tasks such as dose prediction, helping to streamline complex processes and improve patient outcomes. METHODS: This paper provides a comprehensive review of recent research on deep learning applications for radiotherapy dose prediction, highlighting the architectures, datasets, and methodologies used. RESULTS: The review highlights the advancements in accuracy, efficiency, and robustness achieved by deep learning-based dose prediction models. These approaches help reduce treatment planning time and minimize human error, thereby improving clinical workflows. CONCLUSION: Deep learning offers promising solutions to enhance radiotherapy dose delivery. Future research should focus on developing the generalized dose prediction models, multi-institutional validation frameworks, explainable AI approaches for clinical trust, real-time adaptation capabilities, uncertainty quantification methods, and strategies for handling rare anatomical variations.
1 July 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 →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 →Physics in medicine and biology
Unsupervised multimodal deformable medical image registration based on feature perceptual contrast learning
Objective.Multimodal medical image registration has extensive applications in clinical diagnosis and is fundamental for a series of medical analysis tasks. However, the presence of modality differences makes the registration process challenging. Existing methods often employ modality-independent feature descriptors that are sensitive to noise, or attempt to bridge differences within networks, which typically results in translation inaccuracies and misaligned anatomical information.Approach.In this paper, we propose a novel unsupervised approach utilizing a Feature Perceptual Contrast Learning Network (FP-net) to learn descriptors that bridge modality differences while accurately capturing common details. We unify the feature representation of anatomical information under homogeneous and heterogeneous intensity distributions through local sampling-based feature perceptual contrast learning and image reconstruction learning. The trained FP-net is subsequently employed to drive an unsupervised registration framework without requiring ground-truth deformation fields.Main results.We extensively evaluated our method on two public benchmarks: the BraTS 2021 dataset for brain T2-T1 and T1-T1ce registration, and the Learn2Reg 2021 dataset for challenging abdominal CT-MR registration. By passing multimodal image pairs with shape differences through the fixed FP-net, we generate optimization gradients that successfully update the registration network. Quantitative evaluations demonstrate our method's superiority over state-of-the-art baselines. Specifically, our model achieved a dice similarity coefficient (DSC) of 76.3% and 77.7% in tumor-bearing T2-T1 and T1-T1ce tasks, respectively. Furthermore, in the complex abdominal CT-MR task, it reached a DSC of 50.1%, significantly improving structural alignment.Significance.Our method effectively shifts the burden of bridging the modality gap away from the registration network, enabling standard U-Net architectures to achieve state-of-the-art deformable registration. This provides a robust, accurate, and easily deployable unsupervised solution for complex clinical multimodal image analysis.
12 June 2026
Read appraisal →Physics in medicine and biology
Scan-wise generalized PET denoising with contrastive adversarial learning
Objective.Deep learning has significantly advanced low-count positron emission tomography (PET) denoising. However, models trained on specific distributions often yield biased outputs when applied to scans with different activity distributions caused by anatomical and physiological variations (distribution shifts). Existing methods fail to generalize well across these scan-wise variations. Our goal is to formulate PET denoising as a scan-wise domain generalization (DG) problem to mitigate these variations and achieve robust, unbiased denoising for unseen scans.Approach.We propose a contrastive adversarial DG (CADG) framework to learn scan-invariant features efficiently. We leverage the property that multiple low-count noise realizations can be generated from a single raw list-mode PET scan to form a scan-wise domain distribution. Unlike conventional adversarial training with cross-entropy (CE) loss, we propose a contrastive adversarial framework that minimizes the mutual information between feature and scan-wise domains. Considering that each subject can have multiple scans in longitudinal studies, we further propose an ordered and memory-queued contrastive adversarial framework. This method efficiently includes realizations from the same scan as positive pairs, different scans of the same subject as pseudo-positive pairs, and different subjects as negative pairs in a memory batch. We explicitly exploit their ordered relationship as prior knowledge using a novel noisy-robust multi-positive ordinal contrastive loss.Main results.We systematically validated the effectiveness of our methods using 1920 noise realizations derived from 80 subjects with 192 longitudinal scans of MK-6240 tau PET data. The proposed CADG approach demonstrated superior denoising performance compared to CE-based adversarial methods and standard baselines. The ordered contrastive loss successfully improved the peak signal-to-noise ratio and structural similarity index consistently while reducing bias and standard deviation in Alzheimer-related regions and the whole brain.Significance.To our knowledge, this is the first attempt to alleviate the performance degradation in cross-scan denoising from the perspective of DG. Our study is also a pioneering work in utilizing longitudinal scans as pseudo-positives within an ordered contrastive learning scheme to exploit fine-grained relationships for robust clinical PET imaging applications.
9 June 2026
Read appraisal →Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy
Multivariate feature analysis of early-stage laryngeal cancer serum components using surface-enhanced Raman spectroscopy
Laryngeal cancer is a common head-and-neck malignant tumor with geographically variable incidence. Its lack of specific early clinical symptoms often causes missed diagnosis, leading to most cases being identified at intermediate/advanced stages and thus poor treatment efficacy and prognosis. Early, accurate screening for high-risk populations is therefore critical to improving survival. This study systematically investigates the clinical application value of surface-enhanced Raman spectroscopy (SERS) combined with deep learning models for serum screening in early laryngeal cancer. It specifically examines the discriminative performance of one-dimensional convolutional neural network (1D-CNN) models, including CNN-attention with a fused attention mechanism and CNN-baseline without an attention mechanism, and compares these with traditional machine learning models.Serum samples were collected from three groups: Early laryngeal cancer, vocal fold polyps, and healthy controls. SERS was used to obtain serum molecular vibration fingerprint spectra. After spectral preprocessing, five models (CNN-attention, CNN-baseline, SVM, AdaBoost, KNN) were established to discriminate the three groups and compare performance. Leave-one-patient-out cross-validation (LOPO-CV) results indicate that the CNN-attention and CNN-baseline models significantly outperform other models in discrimination efficacy. Specifically, the CNN-attention model achieves a patient-level accuracy of 89.33%, while the CNN-baseline model reaches 88.67%. SVM, KNN, and AdaBoost had inferior performance. This study confirms that serum SERS-based 1D-CNN provides an efficient, accurate method for early laryngeal cancer screening, laying a foundation for clinical translation and offering new technical support for early screening.
7 June 2026
Read appraisal →European radiology experimental
Towards an accessible, centralised, searchable database for AI courses in Europe: the Artificial Intelligence in Medical Imaging and Radiation Oncology Education (AIMIROE) project.
OBJECTIVE: Artificial intelligence (AI) is transforming medical imaging and radiation oncology, yet limited understanding and access to education hinder adoption. This study, led by the European Society of Medical Imaging Informatics (EuSoMII) in collaboration with the European Federation of Radiographer Societies (EFRS), aimed to create an accessible, centralised, searchable database including all AI courses in Europe. MATERIALS AND METHODS: An electronic survey was developed to collect data on European AI course characteristics, such as format, delivery, content, target audience and European Qualifications Framework (EQF) level. This was disseminated via purposive sampling through social media and mailing lists of the EuSoMII and the EFRS between September 2024 and January 2025. Quantitative data were analysed using descriptive statistics and visual representations using Python Seaborn and Geopandas. RESULTS: This study identified 29 AI courses in Europe. Of them, 53.6% were offered by universities. Courses targeted radiographers (59%), medical physicists (52%), and radiologists (41%), mainly at EQF level 7 (44.4%). Most courses were standalone (65.6%) and online (55.1%), while 41.3% were free of charge. English was the primary language of delivery (79%). CONCLUSIONS: Different AI courses across Europe offer some entry-level knowledge but are often short in duration. Expanding formats, building practical competencies, providing multilingual access, and European-wide reach are essential for meaningful, practical, and equitable AI integration. RELEVANCE STATEMENT: With the scaling-up of AI adoption in medical imaging and radiation oncology, there is a variety of AI education provisions currently available. Accessing these options via an open, centralised, regularly updated database enables people to make an informed decision about their training and practise safely and meaningfully. KEY POINTS: We identified 29 different AI European courses varying in language, content, and delivery. Many clinical practitioners and researchers are unaware of these resources. We need a centralised database for customising AI learning choices and guiding future course design.
31 May 2026
Read appraisal →Biomedical physics & engineering express
RADIANT: A fully configurable radiotherapy dose prediction framework
Objective.Treatment planning is a multi-disciplinary effort that requires medical decision-making, specialized training, and access to specialized software. Recently, deep learning has arisen as a powerful method for predicting patient-specific dose distributions. This work presents the radiotherapy dose inference and analysis toolkit (RADIANT), an open-source, fully configurable framework for 3D radiotherapy dose prediction. Built upon the Medical Imaging Segmentation Toolkit, RADIANT supports diverse network architectures, loss functions, and training strategies.Approach.We demonstrate its capabilities on cervical and prostate treatment plans generated with the radiation planning assistant, and on head and neck cancer plans from the American Association of Physicists in Medicine OpenKBP challenge data. For cervical cancer, we trained and compared nnU-Net, FMG-Net, W-Net, ddU-Net, and Swin UNETR using clinical metrics such as dose score, homogeneity index, and percent errors inD95,D98, andD99. Benchmarking was also performed on the OpenKBP dataset using dose score and dose-volume histogram (DVH) score for comparison with top challenge submissions.Results.Our results indicate that RADIANT provides a scalable platform for the rapid development and benchmarking of dose prediction models for selected cancer sites (cervix, prostate, head and neck). For cervical cancer, the best configuration (nnU-Net architecture, mean absolute error loss, cosine learning rate scheduler) achieved a dose score of 1.31 and sub-1%errors inD95andD98on the training set, and a dose score of 1.20 on the test set. The same configuration performed best on prostate data with a dose score of 1.96 on a test set. On the head and neck OpenKBP data, RADIANT achieved a dose score of 2.702 and a DVH score of 1.495, competitive with top challenge results.Significance.This work provides an open-source, fully configurable framework for deep learning-based dose prediction. RADIANT facilitates reproducible experimentation across data preprocessing, model configuration, training, and evaluation for multiple cancer sites and anatomical structures.
30 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 →Acta oncologica (Stockholm, Sweden)
Prospective evaluation and clinical outcomes of adaptive radiotherapy for locally advanced non-small cell lung cancer (LA-NSCLC)
BACKGROUND AND PURPOSE: Locoregional tumor control is strongly associated with survival for non-small cell lung cancer, emphasizing the importance of precise radiotherapy delivery. This study aims to evaluate a traffic light adaptation protocol regarding target coverage, protocol performance and patient outcomes. MATERIAL AND METHODS: From 2019 to 2022, we prospectively enrolled inoperable non-small cell lung cancer patients. We acquired daily cone-beam computed tomography and traffic light registrations, classifying anatomical changes and need of action. Using repeated computed tomography (rCT) in week 1 and 3 for dosimetric evaluation, we recalculated clinical target volume (CTV) D98% and V95% with and without adaptation, and compared traffic light registrations with the actual dose distribution. Protocol performance was evaluated by the sensitivity and specificity in detecting CTV V95% < 98%. RESULTS: Among 45 patients with complete registrations, baseline shift and tumor shrinkage were most common changes, leading to corrections from bone to tumor match in 37.8% and replanning in 13.3% of patients. Among 38 patients with at least one rCT, 15.8% would have received insufficient CTV coverage without adaptation. Protocol sensitivity, specificity and balanced accuracy were 83.3, 88.6, and 85.7%, respectively. For 38 stage II-III patients, median overall survival was 43.5 months (95% confidence interval [CI]: 32.9-54.1), median time to locoregional failure 27.4 months (95% CI: 0-61.8) and median estimated time to distant failure 30.7 months (CI not estimated due to censoring). INTERPRETATION: The protocol identified relevant changes, improving target coverage without increasing organ at risk doses. With appropriate training, protocol performance was good, and clinical outcomes were consistent with international results.
28 May 2026
Read appraisal →Journal of radiation research
Feasibility of nonspinal bony landmark-based image registration in CyberKnife ® robotic radiotherapy for pelvic and femoral bone tumors
In stereotactic body radiotherapy for bone metastases using the CyberKnife system, spinal anatomy is generally employed as the alignment reference. However, when treating pelvic tumors such as those in the pubic bone or proximal femur, the spinal reference may be anatomically distant from the target, potentially compromising visualization and localization accuracy. This study evaluated the feasibility of using nonspinal bony landmarks, specifically the pubic bone and femoral neck, as reference points for image registration. Intrafractional positional deviations in six degrees of freedom and the frequency of intrafractional corrections were analyzed according to treatment site, including cases treated with conventional spine-based alignment. Alignment accuracy was visually and numerically verified by the treatment operator before beam delivery. Across all treatment sites, the mean translational and rotational deviations during treatment remained within ±0.5 mm and ± 0.5°, respectively. Furthermore, no substantial differences were observed in the mean frequency of intrafractional corrections among the different alignment approaches. These findings demonstrate that nonspinal tumor-adjacent bony landmarks can provide clinically acceptable accuracy comparable to conventional spine-based registration. To our knowledge, this is the first study to systematically assess the clinical feasibility of this approach in CyberKnife-based pelvic radiotherapy. The proposed method may serve as a practical and reliable alternative to spine-based alignment, particularly when the spine is remote from the target.
27 May 2026
Read appraisal →Journal of radiation research
Feasibility of online adaptive SBRT boost with 1.5-T MR-Linac for cervical cancer patients unsuitable for brachytherapy: a planning study
This study aimed to evaluate the effectiveness of online adaptive treatment (ADT) planning for stereotactic body radiotherapy (SBRT) boost on a 1.5-T MR-Linac in cervical cancer patients ineligible for brachytherapy, compared with the conventional position-alignment (PA) assumed dose distributions. This retrospective analysis included 15 treatment plans from five patients, each receiving 21.0 Gy in three fractions. Daily magnetic resonance imaging (MRIs) were used to compare target and organ-at-risk (OAR) doses between ADT and PA dose distributions. The planning target volume (PTV) was defined as the high-risk clinical target volume (HR-CTV) plus a 3 mm margin. OARs included the bladder, bowel bag, and planning organ-at-risk volume (PRV) for rectum and sigmoid. Reference plans prioritized OAR constraints while maximizing target coverage; the intended PTV D90% range was 18.9-21.6 Gy. PA doses were reconstructed by dose warping based on alignment of the anterior rectal wall between daily and pretreatment MRIs, whereas ADT plans were reoptimized on the daily MRIs. HR-CTV decreased by 1.6%-41.5% between the planning MRI and the first treatment fraction. ADT plans improved PTV D90%, achieved better target coverage and met all OAR constraints, whereas PA plans showed dose constraint exceedance across the three fractions, with mean excess doses of 6.89 ± 4.39 Gy to PRV-sigmoid and 5.76 ± 3.33 Gy to PRV-rectum. In conclusion, 1.5-T MR-Linac based SBRT boost with daily online adaptation enhanced tumor coverage and reduced OAR doses, supporting MR-guided online adaptive radiotherapy as a promising option for patients ineligible for brachytherapy.
27 May 2026
Read appraisal →Physics in medicine and biology
Lattice peak optimization: a mixed-integer framework for geometry-adaptive lattice radiotherapy
Objective.Lattice radiotherapy (LATTICE) delivers spatially distributed high-dose peaks within the tumor volume while maintaining lower doses in surrounding valley regions. Determining feasible peak locations is typically performed using heuristic or manual approaches, which may limit the number and spatial distribution of deliverable peaks. This work introduces a lattice peak optimization (LPO) framework that jointly optimizes peak placement and dose distribution to identify the maximum number of geometrically feasible peaks within the target.Approach.Proton LATTICE planning is formulated as a mixed-integer optimization problem that selects an optimal subset of peaks from a large set of candidate locations within the target. Binary variables represent peak selection and continuous variables model spot weights. The formulation enforces geometric feasibility between peaks while optimizing dosimetric objectives to improve peak-to-valley dose ratio (PVDR) and reduce organs-at-risk (OAR) dose. The resulting nonconvex problem is solved using iterative convex relaxation within an alternating direction method of multipliers framework.Main results.LPO was evaluated on three clinical cases with 150-400 candidate peak locations, from which 4-13 peaks were selected. Compared with 50-90 randomly generated LATTICE configurations per case, LPO consistently achieved higher PVDR and improved OAR sparing. In an abdominal case, the composite objective value was 2.93 (worst random), 2.40 (median random), 1.90 (best random), and 1.95 (LPO), with similar trends observed across all cases.Significance.A geometry-adaptive, mixed-integer optimization framework for lattice peak placement is presented, demonstrating improved PVDR and OAR sparing relative to manual and random LATTICE approaches. The present study evaluates performance of the proposed framework in the context of proton LATTICE planning; however, the framework is mathematically modality-agnostic and could in principle be applied to other radiation modalities.
27 May 2026
Read appraisal →Journal of radiation research
Deep learning-based dose prediction in proton beam therapy for hepatocellular carcinoma: comparison of network architectures and loss functions
In proton beam therapy (PBT) for hepatocellular carcinoma (HCC), deep learning (DL)-based dose prediction offers clinical value by providing immediate reference dose distributions as a guideline tool for treatment planners and enabling virtual PBT dose assessment at institutions lacking PBT facilities to support clinical decision-making. This study proposes a dose gradient-aware DL training approach and a beam arrangement-free framework that predicts dose distributions from computed tomography (CT) images and target/organs-at-risk structures without requiring beam arrangement inputs. Using data from 172 HCC patients, we systematically compared 20 DL models combining five architectures with four loss functions, including a novel dose gradient-aware loss capturing PBT-specific dose distribution characteristics arising from the Bragg peak. Prediction accuracy was evaluated using dose metrics for clinical target volume, planning target volume, and normal liver, 10% dose region volume assessment, visual examination, Dice similarity coefficient (DSC) for 10% dose region, and dose-volume histogram (DVH) analysis. DL models employing dose gradient-aware loss demonstrated reduced prediction errors in target volume dose metrics, achieved the lowest errors in 10% dose region volume when combined with U-Net (MAE: 35.4 cm3, RMSE: 51.3 cm3), attained the highest DSC (0.88 ± 0.05), showed the closest DVH agreement with clinical plans for both target structures and normal liver. A comprehensive evaluation consistently confirmed the superiority of dose gradient-aware loss across all metrics, demonstrating the importance of physics-informed, dose gradient-aware learning for accurate PBT dose distribution prediction. Particularly, DL models combining simple architectures with dose gradient-aware loss predicted doses that closely approximated clinical doses in PBT.
27 May 2026
Read appraisal →Journal of radiation research
Feasibility of retrieval-augmented generation for large language models with Japanese input in radiotherapy
Large language models (LLMs) have recently gained attention for their potential. However, concerns remain regarding their reliability due to limitations such as hallucinations and insufficient domain-specific knowledge. Retrieval-augmented generation (RAG) has emerged as a promising approach, enabling LLMs to reference external knowledge sources and generate accurate outputs. We aimed to clarify the potential of RAG-enhanced LLMs with Japanese input in the field of radiotherapy. This was assessed by evaluating performance on three certification examinations in Japan: the Japanese Medical Physicist Examination, the Japanese Board Examination for Radiologists, and the Japanese Board Examination for Radiation Oncologists. In this study, we constructed a RAG system named Rad-Hub, consisting of a Japanese Radiotherapy Knowledge Database (JRKD) and a retrieval framework built on Microsoft Azure. The JRKD was populated with 32 Japanese radiotherapy textbooks and clinical guidelines. We assessed its utility by inputting all multiple-choice questions from the three examinations into ChatGPT-4o, both with and without Rad-Hub, and recording the answers. They were then compared with reference answers determined by experienced medical physicists and radiation oncologists. Rad-Hub improved accuracy across all examinations. Accuracy increased from 77.0% ± 2.6% to 84.6% ± 1.5% in the Medical Physicist examination, from 74.9% ± 2.0% to 82.1% ± 1.1% in the Radiologist examination, and from 55.6% ± 4.4% to 71.7% ± 4.5% in the Radiation Oncologist examination. Performance gains ranged from 7.2% to 16.1%. These findings highlight the potential of RAG-enhanced LLMs, particularly ChatGPT-4o with Rad-Hub, for integration into radiotherapy applications, such as educational and clinical decision assistance.
27 May 2026
Read appraisal →Physics in medicine and biology
Retrofitting a clinical pencil beam scanning proton therapy unit for 2D ultra-high dose rate scanning
Purpose.This work aimed to demonstrate how existing clinical infrastructure can be adapted to enable ultra-high dose rate (UHDR) pencil beam scanning (PBS) for FLASH research. Leveraging available hardware and minimizing modifications, we extended the capabilities of PSI Gantry 1, previously used as a flexible UHDR fixed-beam delivery platform, by enabling true 2D PBS for UHDR small-field irradiations through the addition of a second scanning direction and multiple gantry angles.Methods.A second (vertical) scanning direction was implemented by repurposing an existing steering magnet and integrating it into the control system. Inter-spot dead times were minimized through software optimizations that synchronized control processes and magnet settling times, optimizing the local average dose rate. A precise spot map acquisition process ensured accurate dose delivery across different gantry angles. Additionally, a1kHzlogging system was introduced, enabling the reconstruction of lateral dose and dose-rate distributions from recorded beam parameters.Results.Gantry 1 was successfully commissioned for 2D scanning of small fields (100×24mm2) at gantry angles from 0∘(beam towards floor) to-120∘. Dose-uniform field deliveries were achieved at local average dose rates up to75Gys-1. The reconstructed lateral dose distributions were in good agreement with CCD measurements regarding the90%iso-dose contour, while the dose-rate distributions were validated againstmicro-Diamonddetector measurements, confirming the precision of the recalculated dose rates.Conclusions.By repurposing existing hardware and optimizing beam delivery, Gantry 1 has been upgraded to a true 2D PBS UHDR scanning system, capable of delivering fields at local average dose rates exceeding70Gys-1. The high-frequency logging system enables future reanalysis of data as the mechanisms underlying the FLASH effect become clearer. This transformation makes Gantry 1 a versatile platform for preclinical research and small animal irradiation, advancing the investigation of the FLASH effect.
27 May 2026
Read appraisal →Journal of radiological protection : official journal of the Society for Radiological Protection
The integration of artificial intelligence in radiation medical physics: insights from an international survey with regional variability
Artificial intelligence (AI) is considered to be a leading technology in radiation medical physics, which has the potential for improving efficiency and precision in imaging, radiotherapy, and nuclear medicine. Nonetheless, its application in the clinical setting is hindered by education, regulation, and ethical issues. To evaluate the views of medical physicists on AI adoption, potential issues, perceived advantages, ethical issues, and training needs. A cross-sectional survey in the form of an online questionnaire was distributed internationally to practicing medical physicists, representing specialties in radiation therapy, diagnostic imaging, and nuclear medicine. The instrument was used to capture demographic variables and AI familiarity, perceived benefits and barriers, ethical issues, training preferences, and future expectations. Descriptive statistics, chi-square tests, and binary logistic regression were performed. Open-ended responses were analyzed using thematic analysis. Most respondents were moderately familiar with AI, but nearly half had not incorporated AI into their practice despite being interested. Adoption patterns differed significantly across geographic regions, with higher usage reported in developed countries. AI familiarity was strongly associated with adoption. The most prominent benefits noted were dose calculation accuracy, patient safety, and workflow efficiency. In contrast, the main obstacles were inadequate training, high implementation costs, absence of standardized protocols, and low availability of advanced equipment. Ethical apprehensions focused on accountability and reduced human oversight. Preferred educational strategies included hands-on workshops and on-the-job training. Regional analysis and modeling revealed variability in AI adoption and identified key predictors, including AI familiarity and specialization. Results indicate that AI is considered an important technology in radiation medical physics. However, implementation was influenced by regional and professional differences. These findings highlight the necessity to expand AI education, create standard training programs, improve infrastructure, and provide clearer governance frameworks to support safe and responsible AI integration.
22 May 2026
Read appraisal →Acta oncologica (Stockholm, Sweden)
KaSARi: a national framework for standardized, automated, and predictive radiotherapy in Finland.
BACKGROUND AND PURPOSE: National radiotherapy (RT) data infrastructures are emerging to support treatment quality assurance and outcome research. However, prospective nationwide integration of full DICOM-RT data with toxicity and patient-reported outcome measures (PROMs) remains uncommon. KaSARi (Key advances in Standardizing, Automating, and predicting Risks in RT) was established to create national research infrastructure for prospective RT data collection and integration in Finland. MATERIALS AND METHODS: KaSARi is a prospective, consent-based multicenter cohort infrastructure involving Finnish university and central hospitals. All adult patients receiving RT are eligible. DICOM-RT datasets from treatment planning and oncology information systems are linked to clinician-graded toxicity, PROMs and relevant clinical variables. The infrastructure builds on previously validated multi-institutional DICOM workflows and follows FAIR (Findable, Accessible, Interoperable, Reusable) data principles. Predefined work packages support data harmonization, scalable data processing and enable downstream applications such as AI-based segmentation, dose prediction, and outcome modeling. RESULTS: Patient recruitment started in May 2025. By February 2026, 221 patients had been enrolled at the coordinating center, initially including breast cancer patients and subsequently expanding to all RT indications. Recruitment at a second center began in November 2025, with 37 patients enrolled. The infrastructure is projected to include approximately 29,000 patients over 15 years. Integration of dosimetric, clinical and PROM data is progressing through a phased national implementation as additional centers join the network. INTERPRETATION: KaSARi represents a national infrastructure prospectively integrating full DICOM-RT datasets with clinician-graded toxicity and PROMs across all RT indications within a unified research protocol. The study provides a foundation for nationwide outcome modeling, harmonization of RT practices and development and validation of data-driven AI-based methods.
19 May 2026
Read appraisal →Physics in medicine and biology
Nonperiodic dynamic CT reconstruction using backward-warping implicit neural representation with diffeomorphism regularization
Objective.Motion artifacts remain a major obstacle in dynamic computed tomography (CT) reconstruction, particularly for nonperiodic rapid motion such as cardiac imaging in patients with fast or irregular heart rates, where ECG-gated approaches are unreliable. The extreme limited-angle problem arising from insufficient angular coverage within a single cardiac phase makes accurate reconstruction of fine cardiac structures especially challenging. This work aims to develop a self-supervised framework that recovers high-resolution dynamic CT images from nonperiodic motion scenarios without external training datasets.Approach.We propose BIRD, an implicit neural representation (INR) framework for nonperiodic dynamic CT reconstruction, with three components: (1) a dual-feature representation decomposing the dynamic scene into topology-preserving and free-form features, enabling modeling of both deformable motion and residual variations such as contrast kinetics; (2) a backward-warping deformation model enabling direct ray-based training, overcoming the resolution limitations of prior forward-warping INR approaches at clinically relevant sub-millimeter resolution; and (3) a diffeomorphism-based regularization enforcing anatomically plausible deformation vector fields through bidirectional inverse consistency, without restricting representational capacity.Main results.BIRD was validated on digital and physical cardiac phantoms and retrospective patient data. In the XCAT phantom study under severe limited-angle conditions (0.5 s rot-1, 120 bpm), BIRD improved peak signal-to-noise ratio over the next-best method by 1.43 dB on the right coronary artery and 1.21 dB on the right ventricle. Curved planar reformation confirmed improved vessel continuity and boundary sharpness. On real projection data from a physical cardiac phantom and a retrospective patient scan, BIRD reduced motion artifacts and improved depiction of cardiac and vascular structures compared with conventional reconstructions.Significance.The proposed framework performs self-supervised reconstruction of nonperiodic dynamic CT images solely from projection data. It offers potential clinical applications including non-ECG-gated cardiac imaging for patients with arrhythmia, cinematic image sequences, and retrospective motion artifact correction in conventional CT scans.
19 May 2026
Read appraisal →Computers in biology and medicine
Mapping intratumoral heterogeneity through PET-derived washout and deep learning after proton therapy
The distribution of produced isotopes during proton therapy can be imaged with Positron Emission Tomography (PET) to verify dose delivery. However, biological washout, driven by tissue-dependent processes such as perfusion and cellular metabolism, reduces PET signal-to-noise ratio (SNR) and limits quantitative analysis. In this work, we propose an uncertainty-aware deep learning framework to improve the estimation of washout parameters in post-proton therapy PET, not only enabling accurate correction for washout effects, but also mapping intratumoral heterogeneity as a surrogate marker of tumor status and treatment response. We trained the models on Monte Carlo-simulated data from eight head-and-neck cancer patients, and tested them on four additional head-and-neck and one liver patient. Each patient was represented by 75 digital twins with distinct tumoral washout dynamics and imaged 15 min after treatment, when slow washout components dominate. We also introduced washed-out maps, quantifying the contribution of medium and fast washout components to the loss in activity between the end of treatment and the start of PET imaging. Trained models significantly improved resolution and accuracy, reducing average absolute errors by 60% and 28% for washout rate and washed-out maps, respectively. For intratumoral regions as small as 5.1 mL, errors predominantly fell below thresholds for differentiating vascular status, and the models generalized across anatomical areas and acquisition delays. This study shows the potential of deep learning in post-proton therapy PET to non-invasively map washout kinetics and reveal intratumoral heterogeneity, supporting dose verification, tumor characterization, and treatment personalization. The framework is available at https://github.com/pcabrales/ppw.git.
17 May 2026
Read appraisal →Journal of radiological protection : official journal of the Society for Radiological Protection
Fast occupational upper-limb radiation dose prediction using machine learning and Monte Carlo simulation
Interventional procedures expose physicians to scattered radiation, particularly to their upper extremities, posing occupational health risks. Existing extremity dosimeters such as thermoluminescents, optically stimulated luminescence rings and active personal dosimeters provide limited spatial information, exhibit angular and energy dependence and offer little or no real-time feedback. This study develops machine learning (ML) models to estimate radiation dose values at discrete upper-limb locations using Monte Carlo (MC)-derived data and procedure-specific parameters. A dataset of 10 000 MC dose maps was generated under varied clinical and geometric conditions. After log-transformation and normalisation, several ML models, including deep neural networks and tree-based regressor, were trained and assessed using five-fold cross-validation. Mean absolute error and relative error (RE) were evaluated on the original dose scale, and an ensemble of the three best-performing models was constructed to improve robustness. The ensemble consistently outperformed individual models, achieving an average RE of 3.69% and demonstrating stable performance across anatomical regions and dose levels. Highest accuracy was obtained for standard beam geometries, whereas larger discrepancies occurred in extreme configurations with steep dose gradients. Predicted dose patterns were consistent with the expected distributions across the upper-limb regions. The findings demonstrate the feasibility of ML-based extremity dose estimation in interventional environments. The proposed ensemble provides a rapid (around 10 ms), scalable alternative to full MC simulations, enabling near real-time predictions of upper-limb occupational dose and supporting optimisation of radiation protection practices in image-guided procedures.
16 May 2026
Read appraisal →Physics in medicine and biology
A novel deep-learning approach for monitoring gastrointestinal air variation during radiotherapy in young patients using radiographs
Objective.To develop deep-learning (DL) predictive models of internal gastrointestinal (GI) gas from radiographs, a surrogate for dose degradation in abdominal proton beam therapy (PBT).Approach.DL architectures (convolutional neural networks and U-Nets) were trained to predict GI air local path length and/or global volume from radiographs. Frontal/lateral radiographs with paired volume and path length labels were simulated from CTs and GI gas segmentations using the Tomographic Iterative GPU-based Reconstruction (TIGRE) toolbox. CTs from The Cancer Imaging Archive Paediatric-CT-SEG dataset (N= 349, 0-16 year, North America) were used for model development and internal evaluation; variation in GI filling, organ motion and body size were simulated for augmentation. External evaluation utilised data from two international radiotherapy institutions: one consisting mostly of children and young people (CYP) (N= 21, 2-19 year, Europe); the other predominantly of teenagers and young adults (TYAs) (N= 14, 10-24 year, Asia). Finally, real-life use case was demonstrated on two subjects treated with PBT.Main results.The optimal configuration was the dual U-Net, accurately predicting both volume (mean absolute error (MAE) = 24.0 ± 32.9 ml) and path length (MAE = 0.80 ± 0.59 mm) on the held-out Paediatric-CT-SEG dataset, while also generalising well to external radiotherapy datasets (volume MAE = {18.9 ± 22.4, 34.6 ± 35.2} ml, and path length MAE = {0.52 ± 0.38, 0.67 ± 0.55} mm on the CYP and TYA datasets, respectively). We found a lower Dice similarity coefficient for gas segmentations in TYA vs Paediatric-CT-SEG and CYP (0.56 ± 0.24 vs 0.87 ± 0.09 and 0.84 ± 0.16, respectively), reflecting cohort-specific gas morphology differences. When applied longitudinally, the network detected both monotonic and realistic intrasubject GI gas variation. Proof-of-concept evaluation on clinical radiographs showed promising performance (volume MAE = 29.5 ± 25.9 ml, and path length MAE = 1.10 ± 0.75 mm).Significance.DL-powered radiographs quantified internal GI gas changes with promising performance and generalisability to diverse ages and demographics. This was the first step towards a novel personalised image-guided radiotherapy traffic-light workflow for abdominal PBT with the goal of reducing the need for CBCT to required fractions.
14 May 2026
Read appraisal →Acta oncologica (Stockholm, Sweden)
Improving confidence in MRI-based auto-segmentation via uncertainty assessment.
BACKGROUND AND PURPOSE: Accurate delineation of organs of interest (OOIs, also commonly referred to as organs at risk, OARs) is crucial for safe radiotherapy. While deep learning-based segmentation using convolutional neural networks has achieved high geometric accuracy, clinical translation is hindered by overconfident, uncalibrated predictions in anatomically ambiguous regions. Uncertainty quantification and model calibration are prerequisites for safe clinical workflows. This study compared the standard nnU-Netv2 against its residual-encoding variant (ResEncM), hypothesizing that ResEncM would demonstrate superior reliability and calibration while maintaining comparable geometric accuracy. Patient/material and methods: T1-weighted contrast-enhanced MRI scans from 70 brain cancer patients were used (55 training/validation, 15 testing). Ground-truth contours for brainstem, hippocampi, chiasm, optic nerves, optic tracts, and pituitary were delineated per Danish Neuro Oncology Group guidelines. Both architectures were trained using five-fold cross-validation with identical preprocessing. Epistemic uncertainty was quantified using mutual information, and Expected Calibration Error (ECE) was computed within a 10-mm isotropic margin around reference contours. RESULTS: Both models achieved high geometric accuracy (brainstem dice similarity coefficient [DSC] > 0.93, hippocampi DSC > 0.81). No significant geometric differences were found for large structures. ResEncM showed significantly lower DSC for the pituitary (p = 0.003) and chiasm (p = 0.018). However, ResEncM demonstrated significantly lower epistemic uncertainty and ensemble variance across all structures (p < 0.05), and significantly reduced ECE for the optic chiasm, optic tracts, and pituitary. INTERPRETATION: Integrating a deep residual encoder into the standard U-Net framework significantly improves reliability and calibration of automated brain OOI contours while maintaining strong geometric performance. The ResEncM architecture provides a more trustworthy tool for clinical radiotherapy by reliably flagging high-uncertainty voxels, supporting confidence-aware clinical workflows.
13 May 2026
Read appraisal →Physics in medicine and biology
A delta-based multi-omics model to predict adaptive radiotherapy benefit in patients with non-small cell lung cancer during carbon-ion radiotherapy
Objective.Patients with non-small cell lung cancer (NSCLC) treated with carbon-ion radiotherapy (CIRT) are potential candidates for adaptive radiotherapy (ART). However, ART is time- and resource-intensive. This study aimed to develop a decision-support tool to estimate ART demand before treatment.Approach.This retrospective study included 69 patients with NSCLC treated with CIRT. Baseline clinical characteristics, dose-volume histogram (DVH) parameters, and radiomic and dosiomic features from the plan-computed tomography (CT) (1-2 weeks before treatment) and confirm-CT (1-2 d before treatment) were collected, and relative change rates in features (ΔDVH, Δradiomics, and Δdosiomics) were calculated. Feature selection involved univariable testing, correlation analysis, least absolute shrinkage and selection operator regression, and stepwise regression with 1000 bootstrap resamples. A multivariable logistic regression model was constructed and validated using 200 iterations of five-fold cross-validation.Main results.ART was triggered in 32 (46.4%) patients. A five-feature delta-omic model (one ΔDVH, two Δradiomic, and two Δdosiomic features) achieved a validated median area under the curve of 0.897 (interquartile range, 0.833-0.950) with good calibration. At a high-sensitivity threshold (0.11), the model identified all ART candidates while potentially reducing the frequency of weekly-CT evaluations in 21.4% of patients; at the maximum-Youden threshold (0.41), the median accuracy reached 78.6%, with up to 50.0% classified as low ART demand.Significance.A delta-omic model predicting ART demand in patients with NSCLC receiving CIRT was developed. The model may help optimize resource allocation and streamline ART workflows, although prospective validation in larger cohorts is warranted before widespread clinical adoption.
13 May 2026
Read appraisal →European radiology experimental
Reconstruction algorithms and arm positioning effects on abdominal CT image quality and radiation dose: a phantom study
OBJECTIVE: To evaluate the effects of arm positioning and reconstruction algorithms on radiation dose and image quality of abdominal CT. MATERIALS AND METHODS: Abdominal CT scans were performed using a customized body phantom at 100 kVp with automatic tube current modulation based on noise indices (NI) of 9, 11, and 13 across seven arm positions: arms up (AU), arms down (AD), arms down with one or two-layered air cushions (ADAC, ADAC2), arms on the belly (AB), and arms on the belly with one or two-layered air cushions (ABAC, ABAC2). Images were reconstructed using filtered back projection (FBP), iterative reconstruction, and deep learning-based reconstruction (DLIR). Radiation dose was recorded. Quantitative image quality metrics included image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), sharpness, and structural similarity. Qualitative assessment of sharpness, noise, artifacts, and overall image quality was performed using fixed-dose AU-FBP images as the reference standard. RESULTS: Compared with the AU position, radiation dose increased by up to 83% in non-AU configurations, with similar trends across all NI settings. In contrast, air cushion use caused only minor, configuration-dependent dose changes. Qualitatively, non-AU FBP images showed marked degradation, whereas DLIR enabled selected non-AU configurations to approach near-reference diagnostic quality. Air cushion-related benefits were modest overall but more apparent in AB than AD configurations. CONCLUSION: Arm positioning is the primary determinant of radiation dose and image quality in abdominal CT. When arm elevation is not feasible, DLIR effectively mitigates image quality degradation, while air cushions provide limited, configuration-dependent benefits. RELEVANCE STATEMENT: When arms cannot be raised during abdominal CT, avoiding arms-on-belly and using air cushions may help maintain image quality without substantially increasing radiation dose, while deep learning image reconstruction further enhances diagnostic performance under restricted positioning conditions. KEY POINTS: Arm positioning is a major determinant of radiation dose and image quality in abdominal CT. Arms-on-belly positioning produces poorer image quality despite increased radiation dose. DLIR improves image quality across arm positions but does not eliminate positioning-related degradation.
12 May 2026
Read appraisal →Physics in medicine and biology
Multi-model study of fast VMAT segment dose calculation with deep learning.
Objective.Deep learning (DL) methods enable photon dose calculation under two main coordinate representations: Beam's Eye View (BEV) and patient coordinates. We evaluate dose calculation accuracy and speed under these coordinate paradigms and with representative DL models within a unified dataset and pipeline, and introduce two lightweight models for fast photon dose calculation.Approach.Planning computed tomography (CT) scans and volumetric modulated arc therapy plans from 24 prostate cancer patients were used. Monte Carlo simulation generated 5940, 540, and 3053 segment doses for training (11 patients), validation (3), and testing (10), respectively. For BEV, we used a combination of convolutional neural network (CNN) and convolutional long short-term memory network (ConvLSTM) called CNN-ConvLSTM, a CNN-Mamba combination (CNN-Mamba), a transformer-based architecture (DoTA), and a cascaded 3D UNet (C3D). These were trained on CT and segment-projection BEV cuboids. For patient coordinates, the DeepDose individual segment dose prediction framework implemented with C3D (DeepDose-C3D) was trained on cropped CT volumes with four physical inputs. Segment and plan dose accuracy were assessed using local gamma passing ratesγPR(2%/3 mm and 1%/3 mm) and dose-volume histogram metrics. Dose calculation times (inference plus pre/post-processing) were measured on three different graphics processing unit (GPUs).Results.All five models achieved mean localγPRvalues⩾91.0% (2%/3 mm) for segment doses and⩾99.0% (1%/3 mm) for plan doses. Mean per-segment dose calculation times were 79, 67, 298, 490, 356 ms for CNN-ConvLSTM, CNN-Mamba, DoTA, C3D, and DeepDose-C3D, respectively. On the latest-generation GPU available, the corresponding per-plan (average 305 segments) dose calculation times were 5.5, 6.2, 33.6, 38.7, 35.4 s.Significance.Both BEV- and patient-coordinate DL methods achieved accurate photon plan dose calculation, with BEV-based approaches showing more robust segment performance. CNN-ConvLSTM and CNN-Mamba retain comparable accuracy at lower computational cost, enabling fast photon dose calculation.
12 May 2026
Read appraisal →PloS one
An exploratory dosimetric and treatment-time analysis of tangent-arc and continuous semi-arc VMAT in deep inspiration breath-hold radiotherapy for stage I left-sided breast cancer
BACKGROUND: The use of the deep inspiration breath-hold (DIBH) technique reduces cardiac and lung radiation exposure during left breast cancer radiotherapy. However, the optimal beam delivery technique and the effects of patient adaptation during DIBH remain incompletely understood. OBJECTIVE: In this study, the dosimetric differences between continuous semi-arc and tangent-arc plans in stage I left-sided breast cancer patients using DIBH were compared, and the treatment session duration was descriptively analyzed to characterize treatment-time trends during routine DIBH delivery. METHODS: Twenty patients treated at our hospital from 01/05/2022-31/05/2023 were retrospectively selected from the institutional database for exploratory dosimetric analysis. Two radiotherapy plans were created on the basis of each patient's computed tomography (CT) images. Dosimetric parameters for the planning target volume (PTV) and organs at risk (OARs), and beam-on and total treatment times, were compared. RESULTS: The conformity index (CI) for the PTV was significantly better with the continuous semi-arc plan (P < 0.05), whereas the other PTV parameters did not significantly differ between the plans (P > 0.05). The doses and beam-on time for all OARs (except the left ventricle) were significantly lower for the tangent-arc plan (P < 0.05). Treatment time tended to stabilize across fractions, with a significant difference between the 15th and 16th sessions (P < 0.05). CONCLUSION: With the tangent-arc plan, the beam-on time and radiation exposure to OARs were observed to be lower, while adequate PTV coverage was maintained in patients with stage I left-sided breast cancer using DIBH. Treatment times tended to stabilize with increasing treatment fractions. This observation suggests gradual patient adaptation during routine DIBH rather than a predefined training effect. Given the exploratory nature of these findings and the limited sample size from a single institution, these findings should be interpreted with caution and warrant further investigation in larger, multicenter studies.
11 May 2026
Read appraisal →Lasers in medical science
Machine learning enhanced optical spectroscopy for breast cancer diagnosis: A review
This literature review examines the transformative role of machine learning (ML) and deep learning (DL) in enhancing optical spectroscopy for breast cancer diagnosis. By synthesizing advancements from peer-reviewed studies (2015-2025), we evaluate how ML/DL integration improves the detection of malignancy-associated biochemical changes, enabling noninvasive, rapid, and accurate differentiation between healthy and cancerous tissues. This review highlights key spectroscopic modalities, such as Raman, fluorescence, diffusive optical spectroscopy (DOS), and photoacoustic spectroscopy (PAS), and their integration with AI-driven models, such as convolutional neural networks (CNNs), support vector machines (SVMs), and logistic regression. These techniques achieve diagnostic accuracies of up to 94% in subtype classification (e.g., luminal A, HER2-positive) by analyzing spectral biomarkers such as hemoglobin, lipids, and collagen. Challenges such as data variability, model interpretability, and clinical integration barriers are critically assessed. These findings underscore the potential of ML/DL-enhanced spectroscopy to standardize diagnostics, reduce unnecessary biopsies, and personalize treatment monitoring. Future directions emphasize the need for explainable AI (XAI), multimodal data fusion, and large-scale, diverse datasets to bridge translational gaps. By addressing technical, ethical, and regulatory hurdles, this integration promises to advance early detection, improve clinical outcomes, and reshape precision oncology.
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
Dosimetric evaluation of simultaneous multi-energy (2-18 MV) and intensity optimization for IMRT and VMAT.
Objective.This study aimed to develop and evaluate a framework for the simultaneous optimization of beam fluence and multiple photon energies beyond dual-energy configurations for intensity modulated radiotherapy (IMRT) and volumetric modulated arc therapy (VMAT), with the goal of improving treatment plan quality and normal tissue sparing.Approach.An Elekta Versa HD linear accelerator (linac) was modeled using the BEAMnrc/EGSnrc Monte Carlo platform to simulate 2 MV, 4 MV, and 6 MV photon beams, complemented with measured beam data for 10 MV and 18 MV. A custom MATLAB-based framework was developed to perform simultaneous optimization of energy and fluence, allowing energy weighting of individual beamlets. A total of 12 various energy configurations including single (SE), dual (DE), triple (TE), and quadruple (QE)-energy combinations for IMRT and VMAT were generated for thirteen prostate cancer patients. Plans were evaluated using dose-volume histograms, homogeneity index, conformity index, and organ-at-risk (OAR) dose metrics.Main results.Gamma analysis confirmed the high degree of agreement between measured and simulated beam data, which validated our Monte Carlo linac model. Target coverage remained comparable across all energy configurations. Compared with 6 SE, multi-energy (ME) IMRT and VMAT achieved superior OAR sparing, with the greatest benefits for bladder and rectum in the 5-40 Gy range. TE-IMRT reduced bladder and rectal mean doses by up to 1.6 Gy, with V10 reductions of ∼8%; on average, mean doses were reduced by 0.9 Gy (p= 0.001) and 1.0 Gy (p= 0.001). For VMAT, the 6&18 DE-VMAT plan yielded the largest sparing, lowering bladder and rectal mean doses by ∼1.0 Gy. Relative to 10 SE, all ME plans achieved equal or lower OAR doses, with TE-IMRT and 6&18 DE-VMAT showing the most consistent benefit, reducing mean doses to the bladder, rectum, right femoral head, and left femoral head by up to 1.26, 0.77, 0.6, and 0.55 Gy, respectively.Significance.This study presents the first assessment of the feasibility and potential clinical value of simultaneous optimization of beam intensity and more than two photon energies for IMRT and VMAT plans, producing optimized ME fluence maps that require subsequent conversion into clinically deliverable treatment plans. The findings demonstrate that ME optimization can enhance OAR sparing without compromising target coverage, supporting its promise for future clinical application.
10 May 2026
Read appraisal →Medical physics
Spectral deep learning-based patient and bowtie scatter correction for clinical photon-counting CT
BACKGROUND: The presence of scatter in computed tomography degrades image quality, and can be caused by the patient and by other components in the beam path, such as the bowtie filter. While conventional energy-integrating detectors do not provide spectral distinction, photon-counting (PC) detectors are energy-selective and provide spectral information about the incoming X-ray photons. Since each energy threshold is affected differently by scatter, this spectral information implicitly encodes the scatter content of a projection. PURPOSE: The purpose of this work is to investigate how the spectral information can be exploited to improve deep learning (DL)-based scatter correction. Furthermore, the performance of joint and separate patient and bowtie scatter correction will be investigated, addressing that bowtie scatter has not been considered in current DL-based approaches. METHODS: We present a DL-based approach that can estimate bowtie and patient scatter jointly and compare it against a separate correction. We also introduce neural network-based methods that incorporate the spectral information inherent in PCCT for scatter correction. We present networks that estimate scatter for up to four energy thresholds simultaneously. Training and validation was performed with Monte Carlo data as well as with real data measured by a clinical PCCT system. RESULTS: When comparing joint and separate patient and bowtie scatter estimation, both methods reduce the mean absolute error (MAE) from 8 HU to 1 HU. All proposed DSE methods effectively reduce scatter artifacts and perform better than the convolution-based reference approach. Incorporating the spectral information further improves the performance, with the DSE variant with four energy thresholds achieving the best overall results for all thresholds. For all energy thresholds tested, the spectral DSE methods reduced scatter errors originating from the patient and the bowtie in PCCT from up to 8 HU to below 1 HU. In addition to the global MAE, we report a critical MAE (MAE10) restricted to voxels with uncorrected errors > $>$ 10 HU, as such deviations are visually perceptible in soft tissue and exceed the noise level of modern CT systems. In all test cases, the proposed spectral methods reduced the MAE10 from 23.8 HU in the uncorrected images to 1.6 HU after spectral correction. The affected voxels comprised on average 25 % of the image volume, indicating a significant reduction in artifact intensity in the most affected areas. In virtual monoenergetic images (VMI), the application of spectral neural networks resulted in a significant reduction in MAE from ∼ $\sim$ 16 HU to ∼ $\sim$ 2 HU at 45 keV, from ∼ $\sim$ 8 HU to ∼ $\sim$ 1 HU at 70 keV, and from 5 HU to under 1 HU at 100 keV. CONCLUSIONS: This paper presents a combined method for correcting patient and bowtie scatter that delivers results equivalent to separate corrections and thus eliminates the need for multiple networks. Further, we demonstrate that deep scatter estimation can effectively exploit the spectral information available to improve scatter correction, especially for spectral applications, like VMIs. Spectral DSE networks slightly outperformed non-spectral variants, with multiple energy thresholds lead to more accurate estimations. This enables the use of one network for scatter correction and eliminates the need for multiple ones, thereby saving computational cost and complexity.
10 May 2026
Read appraisal →Nuclear medicine communications
Refining deep learning segmentation in gallium-68-prostate-specific membrane antigen-11 positron emission tomography: evaluation of small lesion filtering and intersection-over-union thresholds
PURPOSE: Evaluate how small lesion filtering and different intersection-over-union (IoU) thresholds influence deep learning segmentation of Ga-68-PSMA-11 PET images in prostate cancer. METHODS: A 3D U-Net was trained on 115 patient scans with manual contours as ground truth. Performance was assessed at voxel, lesion and patient levels. Lesions less than 8 voxels (195 mm 3 ) or less than 27 voxels (658 mm 3 ) were optionally discarded, and lesion-level metrics were computed across 10-50% IoU thresholds. RESULTS: Excluding lesions less than 27 voxels increased voxel-level Dice from 0.7975 to 0.8173 and improved precision. Lesion-level metrics were stable across IoU thresholds of 20-40% after 27-voxel filtering, while sensitivity declined at higher overlap thresholds. Patient-level sensitivity and positive predictive value reached 96.6 and 94.5%, respectively. CONCLUSION: Implementing small lesion filtering criteria improves the reliability of automated segmentation outputs, particularly for quantitative evaluation. For lesion-level metrics, defining true positives within the range of 20-40% IoU thresholds is optimal. Further validation through multicenter studies and larger datasets is essential to ensure the generalizability of these findings.
9 May 2026
Read appraisal →Magnetic resonance in medicine
Accelerating Multiparametric Quantitative MRI Using Self-Supervised Scan-Specific Implicit Neural Representation With Model Reinforcement
PURPOSE: To develop a self-supervised scan-specific deep learning framework for reconstructing accelerated multiparametric quantitative MRI (qMRI). METHODS: We propose REFINE-MORE (REference-Free Implicit NEural representation with MOdel REinforcement), combining an implicit neural representation (INR) architecture with a model reinforcement module that incorporates MR physics constraints. The INR component enables informative learning of spatiotemporal correlations to initialize multiparametric quantitative maps, which are then further refined through an unrolled optimization scheme enforcing data consistency. To improve computational efficiency, REFINE-MORE integrates a low-rank adaptation strategy that promotes rapid model convergence. We evaluated REFINE-MORE on accelerated multiparametric quantitative magnetization transfer imaging for simultaneous estimation of free water spin-lattice relaxation, tissue macromolecular proton fraction, and magnetization exchange rate, using both phantom and in vivo brain data. RESULTS: Under 4× and 5× accelerations on in vivo data, REFINE-MORE achieved superior reconstruction quality, demonstrating the lowest normalized root-mean-square error and highest structural similarity index compared to baseline methods and other state-of-the-art model-based and deep learning approaches. Phantom experiments further showed strong agreement with reference values, underscoring the robustness and generalizability of the proposed framework. Additionally, the model adaptation strategy improved reconstruction efficiency by approximately fivefold. CONCLUSION: REFINE-MORE enables accurate and efficient scan-specific multiparametric qMRI reconstruction, providing a flexible solution for high-dimensional, accelerated qMRI applications.
6 May 2026
Read appraisal →Journal of nuclear medicine : official publication, Society of Nuclear Medicine
Validation of a Deep-Learning Coregistration Framework for Long-Axial-Field-of-View PET/CT Using Low-Radiation-Exposure Protocols Across Various Tracers
The advent of long-axial-field-of-view (LAFOV) PET/CT systems has significantly improved whole-body imaging by providing higher sensitivity and extended torso coverage. However, PET/CT potential misalignment remains a challenge, potentially introducing artifacts and quantification errors. Moreover, PET protocols with reduced scanning duration and dose, as well as the use of ultra-low-dose CT (ULD-CT), are increasingly relevant in clinical practice and research. This study aimed to evaluate the robustness and generalizability of a deep-learning coregistration framework for PET/CT alignment using low-dose PET and ULD-CT across various tracers with a LAFOV system. Methods: In total, 63 scans with 4 different tracers (89Zr-trastuzumab, 15O-H2O, 18F-MC225, and 18F-FDG) were included to assess PET and CT alignment improvements. Further evaluation was performed by comparing CT scans coregistered to the original PET images (rCT) with those coregistered to low-count (50%, 25%, and 12.5% of original counts) PET images (LC-rCT). Dice similarity coefficient, Jaccard similarity coefficient, Hausdorff distance, and average surface distance were used as evaluation metrics. Furthermore, ULD-CT coregistered to PET (rULD-CT) was compared with low-dose CT coregistered to the same PET (rLD-CT) using the same metrics. PET accuracy was evaluated by calculating SUVs. Results: The robustness of the deep-learning coregistration framework was demonstrated in reduced PET counts and ULD-CT scenarios across tracers. All metrics indicated robust performance when comparing LC-rCT with rCT and rULD-CT with rLD-CT. Consistent SUVs across varying PET counts and ULD-CT conditions further validated the quantitative accuracy of the approach. Conclusion: This work highlights that neither the use of low-dose PET protocols nor ULD-CT compromise the performance of this coregistration framework across 4 tracers. For LAFOV PET, these findings support the feasibility of such a framework in imaging protocols with reduced radiation exposure.
5 May 2026
Read appraisal →The British journal of radiology
Automatic segmentation of clinical target volume for radiation therapy in breast-conserving patients and exploration of clinical factors influential to its performance
OBJECTIVES: To develop and validate a deep learning model for whole breast clinical target volume (CTV) contouring and evaluate clinical features affecting its performance. METHODS: Five datasets with 857 patients from a single center were used. Dataset 1 (n = 300) trained and tested the model. Dataset 2 (n = 10) evaluated contouring time and dosimetric parameters. Datasets 3 (n = 20) and 4 (n = 10) were for clinical evaluation. Dataset 5 (n = 517) identified clinical factors influencing auto-contouring accuracy. Model performance was assessed using Dice Similarity Coefficient (DSC) and 95th percentile Hausdorff Distance (HD95). RESULTS: The median DSC and HD95 for left- and right-sided models in Dataset 1 were 0.941, 1.75 mm and 0.937, 2.47 mm, respectively. In Dataset 2, both auto-contouring and auto-contouring with manual corrections were significantly faster than manual contouring (P = .005 for both), while still achieving clinically acceptable dosimetric results. In Dataset 3, two physicians rated automatic and manual contours as equivalent (P = .214, P = .075), while the other rated auto-contouring higher (P < .001). In Dataset 4, the auto-contouring model outperformed 1/5 physicians by DSC (P = .009) and 3/5 by HD95 (P = .015, P = .007, P = .017). In Dataset 5, peripheral tumor-bed and low-density breast tissue were associated with lower DSC (P < .001 for both) and higher HD95 (P < .001 for both). Cases without unfavorable factors performed better than those with (P < .001 for both). CONCLUSIONS: The proposed model demonstrated acceptable accuracy, consistency, and efficiency in breast CTV contouring. Peripheral tumor-bed and low-density breast tissue reduced auto-contouring performance. ADVANCES IN KNOWLEDGE: The characteristics of challenging cases in whole breast CTV auto-contouring should be identified.
5 May 2026
Read appraisal →Annual review of biomedical engineering
Physics-Informed Machine Learning in Biomedical Science and Engineering
Physics-informed machine learning (PIML) is emerging as a potentially transformative paradigm for modeling complex biomedical systems by integrating parameterized physical laws with data-driven methods. Here, we review three main classes of PIML frameworks: physics-informed neural networks (PINNs), neural ordinary differential equations (NODEs), and neural operators (NOs), highlighting their growing role in biomedical science and engineering. We begin with PINNs, which embed governing equations into deep learning models and have been successfully applied to biosolid and biofluid mechanics, mechanobiology, and medical imaging, among other areas. We then review NODEs, which offer continuous-time modeling, especially suited to dynamic physiological systems, pharmacokinetics, and cell signaling. Finally, we discuss deep NOs as powerful tools for learning mappings between function spaces, enabling efficient simulations across multiscale and spatially heterogeneous biological domains. Throughout, we emphasize applications where physical interpretability, data scarcity, or system complexity make conventional black-box learning insufficient. We conclude by identifying open challenges and future directions for advancing PIML in biomedical science and engineering, including issues of uncertainty quantification, generalization, and integration of PIML and large language models.
5 May 2026
Read appraisal →Journal of medical imaging and radiation sciences
Explainability-informed benchmarking of two deep learning models for organ-at-risk segmentation in MR-guided adaptive radiotherapy
INTRODUCTION/BACKGROUND: Segmentation of gastrointestinal (GI) organs-at-risk (OARs) is a critical yet time-consuming step in MR-guided adaptive radiotherapy (MRgRT), with manual delineation prone to inter- and intra-observer variability. While deep learning approaches have shown promise, their clinical adoption requires not only accuracy but also interpretability and reliability. This study benchmarks two widely used convolutional architectures, U-Net and Residual U-Net (ResUNet), for abdominal OAR segmentation, with an emphasis on explainability-oriented quantitative analysis. METHODS: An anonymized abdominal MRI dataset was used to train and evaluate U-Net and ResUNet using a 5-fold stratified group cross-validation strategy. Segmentation performance was assessed using the Dice Similarity Coefficient (DSC), Intersection-over-Union (IoU), and the 95th percentile Hausdorff Distance (HD95). Explainability was investigated using Gradient-weighted Class Activation Mapping (Grad-CAM) computed from the final convolutional layer of each network. To enable objective analysis beyond qualitative visualization, Grad-CAM activation maps were quantified using numerical localization metrics relative to ground-truth organ masks, including in-organ energy ratio, boundary energy ratio, pointing accuracy, activation Dice coefficient, centroid distance and activation entropy. Grad-CAM metrics were aggregated across gastrointestinal organs and averaged over the five validation folds. RESULTS: Both architectures demonstrated comparable segmentation performance across organs, with no statistically significant differences across evaluated metrics. Grad-CAM analysis showed similar region-level attention patterns, with in-organ activation ratios of 71.4 ± 8.6% for U-Net and 66.2 ± 9.1% for ResUNet, boundary energy ratios of 24.1 ± 4.9% and 21.8 ± 5.2%, respectively, and pointing accuracies exceeding 70% for both models. Uncertainty analysis based on inter-fold variability and boundary error dispersion indicated comparable stability and bounded worst-case behavior. DISCUSSION/CONCLUSION: By integrating performance, uncertainty and explainability quantitative indicators, this study provides an informed benchmarking of two deep learning models for abdominal OAR segmentation. The results suggest that both U-Net and ResUNet exhibit stable and interpretable behavior under the evaluated configurations, supporting their potential use in MR-guided adaptive radiotherapy workflows where reliability and clinical trust are essential.
4 May 2026
Read appraisal →Physics in medicine and biology
FLIP-HEDOS: a patient-specific blood dose quantification model during radiotherapy treatments
Objective.To introduce FLIP-HEDOS, a blood dose modeling framework that combines patient-specific and generic circulatory data to enable individualized blood dose estimation during radiotherapy (RT) treatments and to overcome limitations of non-personalized approaches.Approach.Patient-specific images of vasculature were obtained from patients with thorax-abdomen or head-neck tumors treated with proton or photon RT. Large vessels from the tumor location were segmented, and their blood flow velocities were extracted from phase-contrast MRI. Movement of blood particles (BPs) was simulated using a Lagrangian approach along patient-specific flowlines in these vessels, forming the FLIP method. This circulation was incorporated into a standardized model (HEDOS) to form a closed-loop whole-body model that computes the spatiotemporal BP distribution and associated blood dose accumulation, accounting for dose delivery dynamics, dose rate and beam-on/beam-off times. Cardiac output (CO) was individualized to match each patient blood flow characteristics. FLIP-HEDOS retains the modular HEDOS architecture, extending its large vessel compartments with the FLIP approach patient-specific vessels represented as new compartments. Remaining compartments were adapted to preserve the standardized connectivity of the circulatory network.Main Results.The study quantified mean blood dose values and tracked the number of times BPs entered patient-specific compartments during dose delivery. Simulations were performed across a range of inter-beam intervals, and the three models FLIP (patient-specific vessels), HEDOS (generic whole-body), and FLIP-HEDOS (integrated model) were compared with respect to their resulting blood dose values. The comparison shows that when patient-specific information is incorporated in blood dose assessment, BPs experience higher radiation doses.Significance.FLIP-HEDOS proves that standardized vascular data can be effectively combined with patient-specific parameters to achieve physiologically realistic modeling of circulating blood. By enabling individualized CO and blood flow dynamics, the framework adapts to the anatomical and hemodynamic characteristics of each patient.
3 May 2026
Read appraisal →Physics in medicine and biology
Few shots transfer learning for universal SPECT denoising across diverse acquisition protocols
Objective.Accelerated single photon emission computed tomography (SPECT) imaging, achieved by reducing either the number of projection angles or the acquisition time per angle, enhances clinical workflow efficiency but introduces elevated noise. This study aims to develop and validate a universal DL-based reconstruction framework that effectively generalizes across diverse, clinically-realistic SPECT acceleration protocols by overcoming the data scarcity challenge.Approach.SPECT bone scans from 103 patients were acquired under a standard scan (60 views, 12 s/view, 60v12s) followed by a fast scan using one of five acceleration protocols (60v6s, 60v3s, 30v12s, 30v6s, 16v12s). AU-Net-based reconstruction framework was implemented using three strategies: (1) single model, trained on individual acceleration protocol), (2) base model, trained on aggregated datasets from five acceleration protocols, and (3) transfer model, fine-tuned from the base model for protocol-specific optimization. Pixel-level accuracy and structural similarity were assessed using peak signal-to-noise ratio (PSNR), structural similarity index (SSIM) metrics, and maximum pixel value of lesions. Clinical evaluation of image quality, radionuclide detail, artifacts, and diagnostic confidence was conducted using a 5-point system.Main results.Quantitative evaluation showed the transfer model achieved better PSNR and SSIM across all protocols (highest 48.02 PSNR and 0.9918 SSIM in 30v6 s protocol). Qualitative analysis confirmed enhanced structural fidelity. Clinical evaluations rated the transfer model highest across metrics, with scores of 4.667 ± 0.508 (image quality, 30v12 s), 4.800 ± 0.250 (radionuclide detail, 60v6 s), 1.150 ± 0.173 (artifact reduction, 60v6 s), and 4.800 ± 0.250 (diagnostic confidence, 60v6 s), surpassing full-scan results in most cases.Significance. The proposed transfer learning (TL) framework effectively addressed data scarcity and improved reconstruction performance across diverse SPECT acceleration scenarios. The adoption of a TL strategy mitigates data scarcity by utilizing shared features and fine-tuning for specific protocols. The framework demonstrates potential for integration into fast SPECT workflows, facilitating reliable use across diverse imaging scenarios.
2 May 2026
Read appraisal →Biomedical physics & engineering express
Kali MC: an open-source toolkit for intraoperative electron radiation therapy treatment planning
Intraoperative electron radiation therapy (IOERT) is commonly delivered without intraoperative imaging, limiting patient-specific planning and requiring fast, reliable treatment calculations in the operating room. As a result, monitor unit (MU) calculations are often performed using spreadsheets and static look-up tables derived from measurements in water. We present Kali MC, an open source, Python-based software developed to streamline IOERT absorbed dose visualization, MU calculation and report generation for treatments delivered with the Liac HWL mobile accelerator. The software provides a graphical interface to visualize precomputed Monte Carlo absorbed dose distributions in water and performs MU calculations using experimentally determined output factors. Optional atmospheric pressure correction and predefined rescaling factors are supported to improve consistency of dose delivery and target coverage with the prescription isodose. Kali MC also generates customizable PDF treatment reports and exports DICOM RT Plan objects to facilitate integration with record-and-verify systems. By integrating validated dosimetric data, correction methods, and 3D dose visualization into a transparent platform, Kali MC supports efficient intraoperative decision-making; however, its use should be locally commissioned and evaluated according to institution-specific procedures and equipment characteristics.
28 Apr 2026
Read appraisal →Physics in medicine and biology
MRDT-GAN: generative adversarial network with multi-scale residual dense transformer generator for low-dose CT denoising
Objective.Low-dose computed tomography (LDCT) reduces radiation exposure but introduces noise and artifacts that degrade diagnostic quality. Existing deep learning-based denoising methods still face challenges such as over-smoothing, loss of fine structures, and uneven contrast. This study aims to develop an LDCT denoising framework that enhances noise suppression while preserving anatomical details and structural fidelity.Approach.We propose a multi-scale residual dense transformer generative adversarial network (MRDT-GAN). In the generator, we adopt the MRDT Block as the core unit, which introduces multi-scale strategy into residual dense network to reduce over-smoothing and preserve fine details, and also patching transformer block to capture long-range dependencies, mitigating distortions caused by localized receptive fields in convolutional neural network-based approaches. A hybrid attention module is also introduced in the generator to process spatial, frequency, and contrast information, enabling the network to focus on critical regions for noise suppression, improve contrast uniformity, and maintain texture consistency. In the discriminator, we adversarially explore differences on global, pixel, and also sub-scale between denoised LDCT and normal dose CT to better capture structural variations, reduce local noise and distortions, and ensure more realistic texture reconstruction while minimizing artifacts.Main results.We validate MRDT-GAN on both the NIH-AAPM-Mayo Clinic LDCT dataset and a real-world dataset. Experimental results indicate that MRDT-GAN achieves superior denoising performance compared with existing methods, effectively preserves details, enhances visual quality, and achieves a better balance between noise suppression and structural integrity.Significance.MRDT-GAN provides an effective and generalizable LDCT denoising solution that balances noise reduction with fine-detail preservation. By integrating MRDT modeling, hybrid attention mechanisms, and multi-difference adversarial learning, the framework offers improved clinical applicability and supports high-quality image reconstruction for downstream diagnostic tasks.
27 Apr 2026
Read appraisal →Biomedical physics & engineering express
Evaluating the impact of reconstruction algorithms on digital breast tomosynthesis system optimization for microcalcification detection
Early detection of microcalcifications in digital breast tomosynthesis (DBT) depends on optimizing both image reconstruction algorithms and system design parameters. Thisin-silicostudy evaluates the combined effects of x-ray tube motion, angular dose distribution, and detector characteristics on reconstruction algorithms for microcalcification detectability. A synthetic breast phantom containing 127 microcalcification clusters was generated and imaged under four acquisition conditions varying in tube motion (continuous vs. step-and-shot), angular dose distribution (uniform vs. non-uniform), and detector performance (noise level and pixel size). Projection data were reconstructed using filtered back-projection (FBP) and the simultaneous algebraic reconstruction technique (SART). Detection performance was assessed using a 2D Filtered Channel Observer in a multi-reader, multi-case study. Evaluation metrics included signal-to-noise ratio and area under the receiver operating characteristic (ROC) curve. Results show that SART performs best under step-and-shot acquisition by minimizing motion blur and enhancing fine detail, while FBP benefits more from non-uniform angular dose distributions. Detector improvements-lower noise and finer resolution-enhance detectability across all configurations, with FBP showing the largest gains. These findings highlight the interdependence of reconstruction algorithm, tube motion, dose strategy, and detector design in DBT system optimization. This study provides a detailed investigation into classical reconstruction strategies and establishes a methodological baseline for future DBT optimization research, offering actionable guidance for acquisition protocol design and hardware development.
24 Apr 2026
Read appraisal →Physics in medicine and biology
A surface-conforming flexible collimator for improving electron radiotherapy.
Objective.We aim to simplify the traditional method of patient-specific skin collimation and to improve the precision of electron radiotherapy treatment with a new surface-conforming collimation system.Method.A surface-conforming collimation device for electron radiotherapy, consisting of parallel steel cables, was created. The cables move freely relative to each other and can be fixed and reshaped with a clamp system along the length of the device. The cables do not completely fill the space; thus, their packing fraction was determined to characterize dosimetric effects. The cable collimator was tested with a 10 × 10 cm cone with four electron energies (6, 9, 12, and 15 MeV) at three SSDs (100 cm, 105 cm, and 110 cm). Radiochromic film was placed at the surface and at the maximum dose depth (dmax) for each energy. Penumbral width, defined as the distance between 20% and 80% of the maximum dose, was measured for each energy and depth.Results.The largest improvement with respect to traditional collimation was seen for 6 MeV with 110 cm SSD at the surface. The penumbra at the surface for the conventional collimator in this case was 18.7 mm, while the cable collimator penumbra was 1.4 mm. The smallest improvement was seen for 15 MeV with 100 cm SSD atdmax(2.7 cm), where the penumbra for the traditional collimator was 11.1 mm, while the cable collimator penumbra was 9.8 mm. In all cases, the cable collimator reduced penumbral width. Surface dose inhomogeneities due to scatter were most pronounced at higher energies. The packing fraction was measured to be 0.551 ± 0.016.Significance.The prototype shows significant improvement in penumbra compared to conventional collimation. The system aims to serve as a replacement for current skin collimation techniques and could be used with Cerrobend applicators for additional surface blocking.
17 Apr 2026
Read appraisal →Theory in biosciences = Theorie in den Biowissenschaften
Analytical and AINN-based investigation of surface wave propagation in dry long bones with initial stress, magnetic field, and rotation effects
This study presents a comprehensive analytical and artificial intelligence neural network (AINN)-based investigation of wave propagation in dry long bones, modeled as an orthotropic hollow cylindrical structure. The proposed model incorporates the combined effects of initial stress, magnetic field, and rotational motion to capture the complex behavior of bone-like media under coupled physical influences. The governing equations are formulated within a continuum mechanics framework and solved analytically using displacement potential methods, yielding solutions in terms of Bessel functions that satisfy the cylindrical geometry and boundary conditions. Two distinct cases, corresponding to the absence and presence of rotation, are examined to assess the influence of rotational effects on wave dynamics. A detailed parametric analysis is carried out to evaluate the variation of phase velocity and frequency with respect to wave number, initial stress, magnetic parameter, density, and geometric ratios. The analytical results indicate that initial stress enhances wave propagation, while magnetic effects introduce damping and rotation significantly modifies dispersion characteristics. To improve computational efficiency and predictive capability, an AINN model is developed and trained using analytically generated data. The AINN predictions show excellent agreement with the analytical results, as confirmed through parity plots, error analysis, residual distribution, and loss convergence behavior. The novelty of the study lies in the unified analytical-AINN framework that integrates mechanical, electromagnetic, and rotational effects within a single model. The findings provide important insights for wave-based characterization of bone structures and have potential applications in non-destructive evaluation, ultrasonic diagnostics, and advanced biomedical sensing systems.
17 Apr 2026
Read appraisal →Science advances
Enhancing biomedical optical volumetric imaging via self-supervised orthogonal learning
Optical volumetric imaging grapples with inherent noise problems arising from photon budget constraints, light scattering, and space-bandwidth product bottlenecks, all of which degrade structural fidelity and become even more pronounced than in planar imaging. While deep learning presents potential for denoising, supervised methods are hindered by the impracticality of paired datasets, and existing self-supervised approaches fail to fully exploit the intrinsic volumetric structural redundancy inherent to optical imaging. Here, we present a self-supervised volumetric biomedical imaging denoiser (VALID) that leverages intrinsic three-dimensional spatial coherence for highly efficient volumetric denoising through a self-supervised orthogonal learning framework. VALID demonstrates robust denoising performance across diverse imaging modalities, including two- and three-photon microscopy, light-field microscopy, and optical coherence tomography, substantially enhancing structural fidelity in deep-tissue, multimodal, and dynamic imaging scenarios. By combining computational efficiency with zero-shot adaptability, VALID establishes a transformative approach to volumetric image enhancement with structure-aware precision.
16 Apr 2026
Read appraisal →Physics in medicine and biology
A deep learning-based framework for patient-specific radiation dose prediction in beta-emitting radionuclide therapies
Objective.Conventional image-based models for radionuclide therapy dosimetry are typically radionuclide-specific and rely on nuclear medicine (NM) images for training. We developed a deep learning (DL) model that predicts doses for not only training radionuclides but also radionuclides not included in the training data without patient NM images.Approach.The DL model was trained to predict voxel dose kernels (VDKs) for beta-emitters using CT-derived density maps and energy spectra. The DL model-derived VDKs were convolved with time-integrated activity to generate patient-specific dose maps. Zero-shot prediction was tested on Ho-166 and Lu-177. The performance of DL model was validated at kernel, phantom, and patient levels. The proposed DL model, conventional DL model trained on Y-90 NM/CT images of 22 patients, voxelS-value (VSV), and organ-level dosimetry (OLINDA/EXM) were benchmarked against Monte Carlo simulation (MC).Main results.Training utilized a single CT image, circumventing large patient cohort requirements. The DL model-based VDKs showed strong correlation with MC-based VDKs (R2: 0.99 and 0.91 for test Ho-166 and Lu-177) and, at the phantom level, achieved overall lower errors than VSV in heterogeneous region. At the patient level, the proposed DL model predicted organ doses with the smallest differences from MC while reducing computation time from 4.6 h to 2.6 min. For the test Lu-177, the proposed model exhibited good agreement with MC (2.1 Gy, 11.6%), while the conventional model trained using Y-90 showed large discrepancies (129.4 Gy, 657.4%). For the mean tumor dose averaged across the patient cohort for test Ho-166, the proposed DL model yielded the most accurate results with a difference of only 1.1 Gy (2.9%), outperforming multiple VSV (3.8 Gy, 7.2%), single VSV (3.8 Gy, 7.3%), and OLINDA/EXM (1.4 Gy, 4.5%).Significance.The proposed DL model enables dose prediction for radionuclides not included in the training data without NM images.
16 Apr 2026
Read appraisal →European radiology experimental
Impact of deep learning image reconstruction on ADC quantification and histogram metrics: a phantom study
OBJECTIVE: Recently, deep learning (DL)-based reconstruction methods have been introduced into clinical magnetic resonance imaging (MRI) systems to enhance image quality and reduce acquisition time. However, their effects on apparent diffusion coefficient (ADC) maps remain unclear. We investigated whether DL-based image reconstruction influences ADC quantification and histogram-based ADC metrics using a calibrated diffusion-weighted imaging (DWI) phantom. MATERIALS AND METHODS: A phantom containing vials with known ADC values was scanned on a 3-T system using full (fFOV) and reduced (rFOV) field-of-view DWI sequences. Each acquisition was performed using conventional (DL-OFF) and three DL-based strength levels (low, medium, high). Median ADC values were analyzed for repeatability (coefficient of variation (CV)) and accuracy. Histogram changes and first-order radiomic features were assessed using the Wasserstein distance, Friedman, and Wilcoxon tests. RESULTS: ADC estimates showed high repeatability (CV 0.1-1.2%) and good accuracy (deviation -2 to 7%) across all DL levels and sequences. DL reconstruction progressively reduced histogram dispersion, particularly in high-ADC vials. Wasserstein distances increased with DL strength, confirming a progressive effect on ADC value distributions, while median ADC values remained unchanged. Entropy and interquartile range decreased significantly (p < 0.001), whereas kurtosis and skewness increased, with differences showing less stable and sequence-dependent statistical significance. CONCLUSION: DL-based reconstruction maintained accurate and repeatable ADC quantification while reducing the dispersion of ADC values. The effect was more evident for high-ADC regions and the rFOV sequence, resulting in narrower distributions of ADC values. Further investigations comparing different DL-based solutions are warranted to assess the generalizability of these findings in clinical settings. RELEVANCE STATEMENT: Over the past decade, ADC histogram analysis has proven valuable for quantifying tumor heterogeneity, differentiating tumor grade, and evaluating early treatment response. Deep learning reconstruction narrows ADC distributions and reduces dispersion, supporting its potential in oncologic DWI, while highlighting the need for patient-based validation studies. KEY POINTS: DL reconstruction preserved ADC accuracy in both full FOV and reduced FOV DWI. ADC repeatability remained high across DL levels for both DWI sequences. Histogram dispersion progressively reduced across DL levels, particularly in high-ADC vials. Entropy and interquartile ranges decreased progressively with increasing DL strength.
14 Apr 2026
Read appraisal →PloS one
Voxel-wise deep learning segmentation of hydroxyapatite and iodine in spectral photon-counting CT: A quantitative phantom study
Accurate non-invasive identification of hydroxyapatite (HA) deposits is important for diagnosing calcific musculoskeletal disease and quantifying vascular calcification, but conventional and dual-energy CT often struggle to distinguish HA from iodinated contrast because of overlapping attenuation, noise, and beam-hardening artifacts. Spectral photon-counting CT (SPCCT) offers improved energy resolution and spatial fidelity, yet most deep-learning approaches in spectral CT focus on continuous density regression or anatomical segmentation rather than direct voxel-wise material labeling. We developed SPFF-UNet, a spectral-preserving 3D segmentation model for direct classification of HA and iodine concentrations from five-bin SPCCT volumes without material-decomposition preprocessing. A cylindrical phantom containing twelve materials was scanned at 0.1 mm isotropic resolution, including five HA concentrations, three iodine concentrations, three soft-tissue equivalents, and water. SPFF-UNet integrates spectral squeeze-excitation, EnergyFiLM, and FourierGate to preserve and exploit multi-energy information throughout the network. The model was trained for thirteen-class voxel-wise segmentation and compared with five established 3D architectures under matched training conditions. SPFF-UNet achieved the best macro-averaged performance on a held-out phantom scan (Dice 0.72 ± 0.01, IoU 0.59 ± 0.01, sensitivity 0.73 ± 0.01, precision 0.71 ± 0.01), outperforming the strongest comparator, ResUNet++ (Dice 0.66 ± 0.02, IoU 0.46 ± 0.02, sensitivity 0.67 ± 0.02, precision 0.61 ± 0.03). Performance gains were concentrated in mid/low-contrast HA and low-concentration iodine, with reduced slice-wise variability and fewer HA-iodine misclassifications. These results suggest that preserving spectral information and applying targeted spectral modulation can improve concentration-aware voxel classification from SPCCT. This phantom-based proof-of-concept provides a basis for future in vivo validation.
11 Apr 2026
Read appraisal →Biomedical physics & engineering express
The impact of data consistency on deep learning models for nasopharyngeal cancer organ auto-segmentation
Purpose. To investigate how annotation consistency influences deep learning-based auto-contouring performance for organs-at-risk (OARs) in nasopharyngeal cancer radiotherapy.Methods. We evaluated CT scans from 1,301 nasopharyngeal carcinoma patients: 65 contoured by Physician A, 76 by Physician B, and 1,160 by heterogeneous multi-physician teams. Three cohorts (50 samples each for Physicians A/B; 1,000 for multi-physician) with standardized U-Net training protocols generated Models A, B, and C. Model C underwent physician-specific fine-tuning. Performance was quantified via Dice similarity coefficients (DSC) against ground-truth contours across 14 critical OARs.Results. Each model achieved peak accuracy on physician-matched test data. Critically, small-consistency models (A/B) outperformed large-heterogeneous Model C on target cohorts (Model A: 0.777 versus Model C's 0.743 on Test A; Model B: 0.806 versus 0.765 on Test B). Physician-specific fine-tuning closed institutional data gaps, boosting Model C's DSC to 0.795 (+7.08% versus original) on Test A and 0.814 (+6.32%) on Test B-surpassing both original Model C and dedicated small-data models (Model A: +2.39%; Model B: +0.97%).Conclusion. Annotation consistency supersedes dataset scale as the primary performance driver for OAR auto-contouring. Small high-consistency datasets enable optimal native model accuracy, whereas fine-tuning large pre-trained models with targeted physician data closes domain adaptation gaps and delivers state-of-the-art segmentation, advancing precision radiotherapy for head and neck oncology..
11 Apr 2026
Read appraisal →Biomedical physics & engineering express
Efficient machine learning models leveraging DCE-MRI morphological and dynamic features allow accurate breast lesion classification.
We propose an ensemble learning approach to classify malignant versus benign breast lesions by leveraging morphological and dynamic features derived from Magnetic Resonance Images (MRI). The analysis was performed on 164 breast lesions of the publicly available 'Advanced MRI Breast Lesions' dataset from The Cancer Imaging Archive, containing T2-weighted and Dynamic Contrast-Enhanced (DCE)-MRI sequences, along with the segmentation masks of suspicious lesions. After extracting radiomic features using the Pyradiomics Python package, we computed dynamic features from DCE-MRI kinetic curves, which describe the contrast agent wash-in and wash-out. These features have been defined as the derivatives of image intensity measures, such as mean and standard deviation, computed within the masks on the five DCE-MRI time steps. We trained and evaluated an eXtreme Gradient Boosting (XGBoost) classifier, experimenting with different combinations of features and segmentation masks in a stratified 5-fold cross-validation. The best model trained on T2-weighted MRI morphological features achieved an Area Under the Curve (AUC) score of 0.83 ± 0.04 (95% C.I. 0.826-0.835) on the independent test set consisting of 20 lesions, while the model using only dynamic features performed an AUC of 0.91 ± 0.03 (95% C.I. 0.907-0.915). Despite being obtained on a small test sample, these results show the potential of features derived from DCE images for breast lesions classification.
10 Apr 2026
Read appraisal →Physics in medicine and biology
Fraction-variant VMAT planning for patients with complex gynecological and head-and-neck cancer.
Objective. Increasing the number of arcs in volumetric modulated arc therapy (VMAT) allows for better intensity modulation and may improve plan quality. However, this leads to longer delivery times, which may cause patient discomfort and increase intra-fractional motion. In this study, it was investigated whether the delivery of different VMAT plans in different fractions may improve the dosimetric quality and delivery efficiency for the treatment of patients with complex tumor geometries.Approach. A direct aperture optimization algorithm was developed which allows for the simultaneous optimization of different VMAT plans to be delivered in different fractions, based on their cumulative physical dose. Each VMAT plan is constrained to deliver a uniform dose within the target volume, such that the entire treatment does not alter the fractionation scheme and is robust against inter-fractional setup errors. This approach was evaluated in-silico for five patients with gynecological and five patients with head-and-neck cancer.Main results. For all patients, fraction-variant treatments achieved significantly better target coverage and reduced the dose to critical organs-at-risk compared to fraction-invariant treatments that deliver the same plan in every fraction, where the dosimetric benefit was shown to increase with the number of different plans to be delivered. In addition, 1-arc and 2-arc fraction-variant treatments could approximate the dosimetric quality of 3-arc fraction-invariant treatments, while reducing the delivery time.Significance.Fraction-variant VMAT treatments may achieve excellent dosimetric quality for patients with complex tumor geometries, while keeping the delivery time per fraction viable.
9 Apr 2026
Read appraisal →Physics in medicine and biology
SSI-Net: a hybrid physics-constrained deep learning framework for quantitative ultrasound speed-of-sound reconstruction
Objective.Quantitative ultrasound tomography faces challenges in reconstructing speed-of-sound (SoS) distributions due to the ill-posed nature of the inverse problem and the computational complexity of full-waveform inversion. This study aims to develop an efficient and physically consistent deep learning framework for accurate SoS mapping from ultrasound signals.Approach. We propose speed of sound inversion network (SSI-Net), a dual data-physics-driven framework that integrates a bidirectional gated recurrent unit encoder for temporal feature extraction, a U-Net decoder for high-resolution spatial mapping, and a physics-constraint module based on an exact, differentiable finite-difference time-domain solver of the nonlinear Westervelt equation. The network model is trained through a joint optimization strategy that minimizes both data-fidelity loss and physics-informed residual loss, with a two-phase training schedule to ensure stable convergence.Main results.SSI-Net was validated across simulated, tissue-mimicking phantom, andin vivomouse datasets. It achieved superior reconstruction accuracy, with peak signal-to-noise ratio improvements of 7.4%-18.9% over state-of-the-art methods, while reducing the physics-based residual by 25.6%-57.5%. The framework demonstrated strong generalization to different transducer geometries (ring and linear arrays) and maintained stable performance across a ten-fold frequency range. Inference was completed within 109.4 ms per sample.Significance.By embedding an exact wave solver into a trainable architecture, SSI-Net combines the representational capacity of deep learning with strict physical consistency. It provides a robust, efficient, and clinically translatable solution for quantitative SoS imaging, offering a promising tool for tissue characterization in diagnostic ultrasound.
9 Apr 2026
Read appraisal →Physics in medicine and biology
End-to-end testing of an online adaptive radiotherapy workflow for liver tumors using a dynamic Thoraco-abdominal anthropomorphic phantom.
Objective.Adaptive radiotherapy (ART) requires robust end-to-end (E2E) testing tools capable of reproducing organ deformation, physiological motion, and multimodal imaging properties. TheToraco-abdominalAnthropomorphic Phantom withMotion forAdaptiveRadiotherapy (TAM-ARa) is a dynamic anthropomorphic phantom developed to support the design, validation, and quality assurance of online ART workflows.Approach.The phantom was constructed with anatomically realistic bone, lung, and abdominal organ models fabricated from tissue equivalent materials. Modular components allowed simulation of interfractional and intrafractional anatomical variations, including ventilator driven respiratory motion, abdominal deformation, and variable gastric filling. CT, CBCT, and 3T MRI scans were acquired to assess imaging performance. Two E2E tests of an online adaptive intensity-modulated radiotherapy (IMRT) workflow for liver tumors were performed on a Varian Ethos (ETHOS, Varian, USA) system. Multiple deformation scenarios were investigated, including a static reference configuration, two abdominal and one thoracic deformation for ionization chamber (IC) dosimetry, and a static plus abdominal deformation scenarios for radiochromic film dosimetry.Main results.The TAM-ARa phantom demonstrated realistic radiological characteristics, with CT Hounsfield units and MRI relaxation times closely matching reportedin vivovalues. The modular architecture allowed reproducible and controlled abdominal deformations, while setup and dosimeter placement were completed within minutes. In E2E tests for adaptive IMRT of liver tumors, excellent agreement was achieved between measured and planned dose distributions after the treatment plan was adapted. IC E2E measurements showed that online adaptation consistently restored accurate dose delivery under deformation, reducing deviations to below 3%. Independent film measurements confirmed sub-millimeter geometric accuracy and full planning target volume coverage after adaptation, demonstrating effective compensation of deformation-induced errors.Significance.The TAM-ARa phantom provides a versatile and reproducible platform for multimodal E2E testing and validation of online ART workflows. Employing its realistic anatomical design, modular structure, and motion capabilities, TAM-ARa was successfully applied for E2E tests to validate a workflow for adaptive IMRT of liver tumors.
8 Apr 2026
Read appraisal →Computer methods in biomechanics and biomedical engineering
Reconstruction of blood flow velocity with deep learning information fusion from spectral ct projections and vessel geometry
In this work, we investigate a new deep learning reconstruction method of blood flow velocity within deformed vessels from contrast enhanced X-ray projections and vessel geometry. The principle of the method is to perform linear or nonlinear dimension reductions on the Radon projections and on the mesh of the vessel. These low dimensional projections are then fused to obtain the velocity field in the vessel. The accuracy of the reconstruction method is proved using various neural network architectures with realistic unsteady blood flows. The approach leverages the vessel geometry information and outperforms the simple PCA-net.
4 Apr 2026
Read appraisal →