Human brain fiber tractography using diffusion magnetic resonance imaging is a crucial stage in mapping brain white matter structures, pre-surgical planning, and extracting connectivity patterns. Accurate and reliable tractography, by providing detailed geometric information about the position of neural pathways, minimizes the risk of damage during neurosurgical procedures. Both tractography itself and its post-processing steps such as bundle segmentation are usually used in these contexts. Many approaches have been put forward in the past decades and recently, multiple data-driven tractography algorithms and automatic segmentation pipelines have been proposed to address the limitations of traditional methods. Several of these recent methods are based on learning algorithms that have demonstrated promising results. In this study, in addition to introducing diffusion MRI datasets, we review learning-based algorithms such as conventional machine learning, deep learning, reinforcement learning and dictionary learning methods that have been used for white matter tract, nerve and pathway recognition as well as whole brain streamlines or whole brain tractogram creation. The contribution is to discuss both tractography and tract recognition methods, in addition to extending previous related reviews with most recent methods, covering architectures as well as network details, assess the efficiency of learning-based methods through a comprehensive comparison in this field, and finally demonstrate the important role of learning-based methods in tractography.

We present ReXVQA, the largest and most comprehensive benchmark for visual question answering (VQA) in chest radiology, comprising approximately 696,000 questions paired with 160,000 chest X-rays studies across training, validation, and test sets. Unlike prior efforts that rely heavily on template based queries, ReXVQA introduces a diverse and clinically authentic task suite reflecting five core radiological reasoning skills: presence assessment, location analysis, negation detection, differential diagnosis, and geometric reasoning. We evaluate eight state-of-the-art multimodal large language models, including MedGemma-4B-it, Qwen2.5-VL, Janus-Pro-7B, and Eagle2-9B. The best-performing model (MedGemma) achieves 83.24% overall accuracy. To bridge the gap between AI performance and clinical expertise, we conducted a comprehensive human reader study involving 3 radiology residents on 200 randomly sampled cases. Our evaluation demonstrates that MedGemma achieved superior performance (83.84% accuracy) compared to human readers (best radiology resident: 77.27%), representing a significant milestone where AI performance exceeds expert human evaluation on chest X-ray interpretation. The reader study reveals distinct performance patterns between AI models and human experts, with strong inter-reader agreement among radiologists while showing more variable agreement patterns between human readers and AI models. ReXVQA establishes a new standard for evaluating generalist radiological AI systems, offering public leaderboards, fine-grained evaluation splits, structured explanations, and category-level breakdowns. This benchmark lays the foundation for next-generation AI systems capable of mimicking expert-level clinical reasoning beyond narrow pathology classification. Our dataset will be open-sourced at https://huggingface.co/datasets/rajpurkarlab/ReXVQA

Current risk stratification for stage II colorectal cancer (CRC) has limited accuracy in identifying patients who would benefit from adjuvant chemotherapy, leading to potential over- or under-treatment. We aimed to develop a more precise risk stratification system by integrating artificial intelligence-based imaging analysis with pathological markers. We analyzed 2,992 stage II CRC patients from 12 centers. A deep learning classifier (Swin Transformer Assisted Risk-stratification for CRC, STAR-CRC) was developed using multi-planar CT images from 1,587 patients (training:internal validation=7:3) and validated in 1,405 patients from 8 independent centers, which stratified patients into low-, uncertain-, and high-risk groups. To further refine the uncertain-risk group, a composite score based on pathological markers (pT4 stage, number of lymph nodes sampled, perineural invasion, and lymphovascular invasion) was applied, forming the intelligent risk integration system for stage II CRC (IRIS-CRC). IRIS-CRC was compared against the guideline-based risk stratification system (GRSS-CRC) for prediction performance and validated in the validation dataset. IRIS-CRC stratified patients into four prognostic groups with distinct 3-year disease-free survival rates (≥95%, 95-75%, 75-55%, ≤55%). Upon external validation, compared to GRSS-CRC, IRIS-CRC downstaged 27.1% of high-risk patients into Favorable group, while upstaged 6.5% of low-risk patients into Very Poor prognosis group who might require more aggressive treatment. In the GRSS-CRC intermediate-risk group of the external validation dataset, IRIS-CRC reclassified 40.1% as Favorable prognosis and 7.0% as Very Poor prognosis. IRIS-CRC's performance maintained generalized in both chemotherapy and non-chemotherapy cohorts. IRIS-CRC offers a more precise and personalized risk assessment than current guideline-based risk factors, potentially sparing low-risk patients from unnecessary adjuvant chemotherapy while identifying high-risk individuals for more aggressive treatment. This novel approach holds promise for improving clinical decision-making and outcomes in stage II CRC.

BackgroundOsteoporosis is underdiagnosed and undertreated prompting the exploration of opportunistic screening using CT and artificial intelligence (AI). PurposeTo develop a reproducible deep learning-based convolutional neural network to automatically place a 3D region of interest (ROI) in trabecular bone, develop a correction method to normalize attenuation across different CT protocols or and scanner models, and to establish thresholds for osteoporosis in a large diverse population. MethodsA deep learning-based method was developed to automatically quantify trabecular attenuation using a 3D ROI of the thoracic and lumbar spine on chest, abdomen, or spine CTs, adjusted for different tube voltages and scanner models. Normative values, thresholds for osteoporosis of trabecular attenuation of the spine were established across a diverse population, stratified by age, sex, race, and ethnicity using reported prevalence of osteoporosis by the WHO. Results538,946 CT examinations from 283,499 patients (mean age 65 years{+/-}15, 51.2% women and 55.5% White), performed on 50 scanner models using six different tube voltages were analyzed. Hounsfield Units at 80 kVp versus 120 kVp differed by 23%, and different scanner models resulted in differences of values by < 10%. Automated ROI placement of 1496 vertebra was validated by manual radiologist review, demonstrating >99% agreement. Mean trabecular attenuation was higher in young women (<50 years) than young men (p<.001) and decreased with age, with a steeper decline in postmenopausal women. In patients older than 50 years, trabecular attention was higher in males than females (p<.001). Trabecular attenuation was highest in Blacks, followed by Asians and lowest in Whites (p<.001). The threshold for L1 in diagnosing osteoporosis was 80 HU. ConclusionDeep learning-based automated opportunistic osteoporosis screening can identify patients with low bone mineral density that undergo CT scans for clinical purposes on different scanners and protocols. Key Results 3 main results/conclusionsO_LIIn a study of 538,946 CT examinations performed in 283,499 patients using different scanner models and imaging protocols, an automated deep learning-based convolutional neural network was able to accurately place a three-dimensional regions of interest within thoracic and lumbar vertebra to measure trabecular attenuation. C_LIO_LITube voltage had a larger influence on attenuation values (23%) than scanner model (<10%). C_LIO_LIA threshold of 80 HU was identified for L1 to diagnose osteoporosis using an automated three-dimensional region of interest. C_LI

To develop and validate a deep-learning-based automatic method for vessel walls and atherosclerotic plaques segmentation for quantitative evaluation in MR vessel wall images. A total of 193 patients (107 patients for training and validation, 39 patients for internal test, 47 patients for external test) with atherosclerotic plaque from five centers underwent T1-weighted MRI scans and were included in the dataset. The first step of the proposed method was constructing a purely learning-based convolutional neural network (CNN) named Vessel-SegNet to segment the lumen and the vessel wall. The second step is using the vessel wall priors (including manual prior and Tversky-loss-based automatic prior) to improve the plaque segmentation, which utilizes the morphological similarity between the vessel wall and the plaque. The Dice similarity coefficient (DSC), intraclass correlation coefficient (ICC), etc., were used to evaluate the similarity, agreement, and correlations. Most of the DSCs for lumen and vessel wall segmentation were above 90%. The introduction of vessel wall priors can increase the DSC for plaque segmentation by over 10%, reaching 88.45%. Compared to dice-loss-based vessel wall priors, the Tversky-loss-based priors can further improve DSC by nearly 3%, reaching 82.84%. Most of the ICC values between the Vessel-SegNet and manual methods in the 6 quantitative measurements are greater than 85% (p-value < 0.001). The proposed CNN-based segmentation model can quickly and accurately segment vessel walls and plaques for quantitative evaluation. Due to the lack of testing with other equipment, populations, and anatomical studies, the reliability of the research results still requires further exploration. Question How can the accuracy and efficiency of vessel component segmentation for quantification, including the lumen, vessel wall, and plaque, be improved? Findings Improved CNN models, manual/automatic vessel wall priors, and Tversky loss can improve the performance of semi-automatic/automatic vessel components segmentation for quantification. Clinical relevance Manual segmentation of vessel components is a time-consuming yet important process. Rapid and accurate segmentation of the lumen, vessel walls, and plaques for quantification assessment helps patients obtain more accurate, efficient, and timely stroke risk assessments and clinical recommendations.

Compound figures, which are multi-panel composites containing diverse subfigures, are ubiquitous in biomedical literature, yet large-scale subfigure extraction remains largely unaddressed. Prior work on subfigure extraction has been limited in both dataset size and generalizability, leaving a critical open question: How does high-fidelity image-text alignment via large-scale subfigure extraction impact representation learning in vision-language models? We address this gap by introducing a scalable subfigure extraction pipeline based on transformer-based object detection, trained on a synthetic corpus of 500,000 compound figures, and achieving state-of-the-art performance on both ImageCLEF 2016 and synthetic benchmarks. Using this pipeline, we release OPEN-PMC-18M, a large-scale high quality biomedical vision-language dataset comprising 18 million clinically relevant subfigure-caption pairs spanning radiology, microscopy, and visible light photography. We train and evaluate vision-language models on our curated datasets and show improved performance across retrieval, zero-shot classification, and robustness benchmarks, outperforming existing baselines. We release our dataset, models, and code to support reproducible benchmarks and further study into biomedical vision-language modeling and representation learning.

The incidence of Alzheimer's disease is rising with the increasing elderly population worldwide. While no cure exists, early diagnosis can significantly slow disease progression. Computer-aided diagnostic systems are becoming critical tools for assisting in the early detection of Alzheimer's disease. In this systematic review, we aim to evaluate recent advancements in computer-aided decision support systems for Alzheimer's disease diagnosis, focusing on data modalities, machine learning methods, and performance metrics. We conducted a systematic review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Studies published between 2021 and 2024 were retrieved from PubMed, IEEEXplore and Web of Science, using search terms related to Alzheimer's disease classification, neuroimaging, machine learning, and diagnostic performance. A total of 39 studies met the inclusion criteria, focusing on the use of Magnetic Resonance Imaging, Positron Emission Tomography, and biomarkers for Alzheimer's disease classification using machine learning models. Multimodal approaches, combining Magnetic Resonance Imaging with Positron Emission Tomography and Cognitive assessments, outperformed single-modality studies in diagnostic accuracy reliability. Convolutional Neural Networks were the most commonly used machine learning models, followed by hybrid models and Random Forest. The highest accuracy reported for binary classification was 100%, while multi-class classification achieved up to 99.98%. Techniques like Synthetic Minority Over-sampling Technique and data augmentation were frequently employed to address data imbalance, improving model generalizability. Our review highlights the advantages of using multimodal data in computer-aided decision support systems for more accurate Alzheimer's disease diagnosis. However, we also identified several limitations, including data imbalance, small sample sizes, and the lack of external validation in most studies. Future research should utilize larger, more diverse datasets, incorporate longitudinal data, and validate models in real-world clinical trials. Additionally, there is a growing need for explainability in machine learning models to ensure they are interpretable and trusted in clinical settings. While computer-aided decision support systems show great promise in improving the early diagnosis of Alzheimer's disease, further work is needed to enhance their robustness, generalizability, and clinical applicability. By addressing these challenges, computer-aided decision support systems could play a pivotal role in the early detection and management of Alzheimer's disease, potentially improving patient outcomes and reducing healthcare costs.

During radiation therapy, the natural movement of organs can lead to underdosing the cancer and overdosing the healthy tissue, compromising treatment efficacy. Real-time image-guided adaptive radiation therapy can track the tumour and account for the motion. Typically, fiducial markers are implanted as a surrogate for the tumour position due to the low radiographic contrast of soft tissues in kilovoltage (kV) images. A segmentation approach that does not require markers would eliminate the costs, delays, and risks associated with marker implantation. We trained patient-specific conditional Generative Adversarial Networks for prostate segmentation in kV images. The networks were trained using synthetic kV images generated from each patient's own imaging and planning data, which are available prior to the commencement of treatment. We validated the networks on two treatment fractions from 30 patients using multi-centre data from two clinical trials. Here, we present a large-scale proof-of-principle study of x-ray-based markerless prostate segmentation for globally available cancer therapy systems. Our results demonstrate the feasibility of a deep learning approach using kV images to track prostate motion across the entire treatment arc for 30 patients with prostate cancer. The mean absolute deviation is 1.4 and 1.6 mm in the anterior-posterior/lateral and superior-inferior directions, respectively. Markerless segmentation via deep learning may enable real-time image guidance on conventional cancer therapy systems without requiring implanted markers or additional hardware, thereby expanding access to real-time adaptive radiation therapy.

Novel artificial intelligence tools have the potential to significantly enhance productivity in medicine, while also maintaining or even improving treatment quality. In this study, we aimed to evaluate the current capability of ChatGPT-4.0 to accurately interpret multimodal musculoskeletal tumor cases.We created 25 cases, each containing images from X-ray, computed tomography, magnetic resonance imaging, or scintigraphy. ChatGPT-4.0 was tasked with classifying each case using a six-option, two-choice question, where both a primary and a secondary diagnosis were allowed. For performance evaluation, human raters also assessed the same cases.When only the primary diagnosis was taken into account, the accuracy of human raters was greater than that of ChatGPT-4.0 by a factor of nearly 2 (87% vs. 44%). However, in a setting that also considered secondary diagnoses, the performance gap shrank substantially (accuracy: 94% vs. 71%). Power analysis relying on Cohen's w confirmed the adequacy of the sample set size (n: 25).The tested artificial intelligence tool demonstrated lower performance than human raters. Considering factors such as speed, constant availability, and potential future improvements, it appears plausible that artificial intelligence tools could serve as valuable assistance systems for doctors in future clinical settings. · ChatGPT-4.0 classifies musculoskeletal cases using multimodal imaging inputs.. · Human raters outperform AI in primary diagnosis accuracy by a factor of nearly two.. · Including secondary diagnoses improves AI performance and narrows the gap.. · AI demonstrates potential as an assistive tool in future radiological workflows.. · Power analysis confirms robustness of study findings with the current sample size.. · Bosbach WA, Schoeni L, Beisbart C et al. Evaluating the Diagnostic Accuracy of ChatGPT-4.0 for Classifying Multimodal Musculoskeletal Masses: A Comparative Study with Human Raters. Rofo 2025; DOI 10.1055/a-2594-7085.

This paper describes PARADIM, a digital infrastructure designed to support research at the interface of data science and medical imaging, with a focus on Research Data Management best practices. The platform is built from open-source components and rooted in the FAIR principles through strict compliance with the DICOM standard. It addresses key needs in data curation, governance, privacy, and scalable resource management. Supporting every stage of the data science discovery cycle, the platform offers robust functionalities for user identity and access management, data de-identification, storage, annotation, as well as model training and evaluation. Rich metadata are generated all along the research lifecycle to ensure the traceability and reproducibility of results. PARADIM hosts several medical image collections and allows the automation of large-scale, computationally intensive pipelines (e.g., automatic segmentation, dose calculations, AI model evaluation). The platform fills a gap at the interface of data science and medical imaging, where digital infrastructures are key in the development, evaluation, and deployment of innovative solutions in the real world.