Four-dimensional MRI (4D-MRI) is an promising technique for capturing respiratory-induced motion in radiation therapy planning and delivery. Conventional 4D reconstruction methods, which typically rely on phase binning or separate template scans, struggle to capture temporal variability, complicate workflows, and impose heavy computational loads. We introduce a neural representation framework that considers respiratory motion as a smooth, continuous deformation steered by a 1D surrogate signal, completely replacing the conventional discrete sorting approach. The new method fuses motion modeling with image reconstruction through two synergistic networks: the Spatial Anatomy Network (SAN) encodes a continuous 3D anatomical representation, while a Temporal Motion Network (TMN), guided by Transformer-derived respiratory signals, produces temporally consistent deformation fields. Evaluation using a free-breathing dataset of 19 volunteers demonstrates that our template- and phase-free method accurately captures both regular and irregular respiratory patterns, while preserving vessel and bronchial continuity with high anatomical fidelity. The proposed method significantly improves efficiency, reducing the total processing time from approximately five hours required by conventional discrete sorting methods to just 15 minutes of training. Furthermore, it enables inference of each 3D volume in under one second. The framework accurately reconstructs 3D images at any respiratory state, achieves superior performance compared to conventional methods, and demonstrates strong potential for application in 4D radiation therapy planning and real-time adaptive treatment.

Integrated Gradients (IG) is a widely used attribution method in explainable artificial intelligence (XAI). In this paper, we introduce Path-Weighted Integrated Gradients (PWIG), a generalization of IG that incorporates a customizable weighting function into the attribution integral. This modification allows for targeted emphasis along different segments of the path between a baseline and the input, enabling improved interpretability, noise mitigation, and the detection of path-dependent feature relevance. We establish its theoretical properties and illustrate its utility through experiments on a dementia classification task using the OASIS-1 MRI dataset. Attribution maps generated by PWIG highlight clinically meaningful brain regions associated with various stages of dementia, providing users with sharp and stable explanations. The results suggest that PWIG offers a flexible and theoretically grounded approach for enhancing attribution quality in complex predictive models.

Diffusion-based inverse problem solvers (DIS) have recently shown outstanding performance in compressed-sensing parallel MRI reconstruction by combining diffusion priors with physical measurement models. However, they typically rely on pre-calibrated coil sensitivity maps (CSMs) and ground truth images, making them often impractical: CSMs are difficult to estimate accurately under heavy undersampling and ground-truth images are often unavailable. We propose Calibration-free Measurement Score-based diffusion Model (C-MSM), a new method that eliminates these dependencies by jointly performing automatic CSM estimation and self-supervised learning of measurement scores directly from k-space data. C-MSM reconstructs images by approximating the full posterior distribution through stochastic sampling over partial measurement posterior scores, while simultaneously estimating CSMs. Experiments on the multi-coil brain fastMRI dataset show that C-MSM achieves reconstruction performance close to DIS with clean diffusion priors -- even without access to clean training data and pre-calibrated CSMs.

The automatic diagnosis of Parkinson's disease is in high clinical demand due to its prevalence and the importance of targeted treatment. Current clinical practice often relies on diagnostic biomarkers in QSM and NM-MRI images. However, the lack of large, high-quality datasets makes training diagnostic models from scratch prone to overfitting. Adapting pre-trained 3D medical models is also challenging, as the diversity of medical imaging leads to mismatches in voxel spacing and modality between pre-training and fine-tuning data. In this paper, we address these challenges by leveraging 2D vision foundation models (VFMs). Specifically, we crop multiple key ROIs from NM and QSM images, process each ROI through separate branches to compress the ROI into a token, and then combine these tokens into a unified patient representation for classification. Within each branch, we use 2D VFMs to encode axial slices of the 3D ROI volume and fuse them into the ROI token, guided by an auxiliary segmentation head that steers the feature extraction toward specific brain nuclei. Additionally, we introduce multi-ROI supervised contrastive learning, which improves diagnostic performance by pulling together representations of patients from the same class while pushing away those from different classes. Our approach achieved first place in the MICCAI 2025 PDCADxFoundation challenge, with an accuracy of 86.0% trained on a dataset of only 300 labeled QSM and NM-MRI scans, outperforming the second-place method by 5.5%.These results highlight the potential of 2D VFMs for clinical analysis of 3D MR images.

Persistent working memory decline (PWMD) is a common sequela of mild traumatic brain injury (mTBI), yet reliable biomarkers for predicting long-term working memory outcomes remain lacking. The glymphatic system, a brain-wide waste clearance network, plays a crucial role in cognitive recovery. The diffusion tensor imaging analysis along the perivascular space (DTI-ALPS) index, a noninvasive magnetic resonance imaging (MRI)-based technique, offers a promising approach to evaluate perivascular fluid dynamics-a key component of glymphatic function. However, its role in long-term working memory dysfunction remains underexplored, particularly in the presence of traumatic cerebral microbleeds (CMBs) and poor sleep quality-as measured by Pittsburgh Sleep Quality Index (PSQI)-both of which have been suggested to disrupt glymphatic clearance, exacerbate neurovascular impairment, and contribute to cognitive decline. This study aims to investigate the interplay between CMBs, sleep quality, and perivascular fluid dynamics in predicting PWMD after mTBI. We further assess the feasibility of a machine learning-based approach to enhance individualized working memory outcome prediction. Between September 2015 and October 2022, 3,068 patients presenting with concussion were screened, and 471 met the inclusion criteria for mTBI. A total of 184 patients provided informed consent, and 61 completed both baseline and 1-year follow-up assessments. In addition, 61 demographically matched healthy controls were recruited. Susceptibility-weighted imaging was used to detect CMBs, while perivascular fluid dynamics was assessed using the DTI-ALPS index. Sleep quality was evaluated using the PSQI, and working memory was measured with the Digit Span test at baseline and 1-year post-injury. Mediation analysis was conducted to examine the indirect effects of perivascular fluid dynamics on cognitive outcomes, and a machine learning model incorporating DTI-ALPS, CMBs, sleep quality, and baseline cognitive scores was developed for individualized prediction. CMBs were present in 29.5% of mTBI patients and were associated with significantly lower DTI-ALPS index values (<i>p</i> < 0.001), suggesting compromised perivascular fluid dynamics and glymphatic impairment. Poor sleep quality (PSQI > 8) correlated with lower 1-year Digit Span scores (<i>r</i> = -0.551, <i>p</i> < 0.001), supporting the link between disrupted glymphatic function and cognitive decline. Mediation analysis revealed that the DTI-ALPS index partially mediated the relationship between CMBs and PWMD (Sobel test, <i>p</i> = 0.031). Machine learning-based predictive modeling achieved a high accuracy in forecasting 1-year working memory outcomes (<i>R</i>² = 0.78). These findings highlight the potential of noninvasive MRI-based assessment of perivascular fluid dynamics as an early biomarker for PWMD. Given the essential role of the glymphatic system in sleep and memory, integrating DTI-ALPS with CMB detection and sleep quality evaluation may enhance prognostic accuracy and inform personalized rehabilitation strategies for mTBI patients.

To investigate MRI-based habitat analysis for its value in predicting pathologic response following neoadjuvant chemoradiotherapy (nCRT) in rectal cancer (RC) patients. 1021 RC patients in three hospitals were divided into the training and test sets (n = 319), the internal validation set (n = 317), and external validation sets 1 (n = 158) and 2 (n = 227). Deep learning was performed to automatically segment the entire lesion on high-resolution MRI. Simple linear iterative clustering was used to divide each tumor into subregions, from which radiomics features were extracted. The optimal number of clusters reflecting the diversity of the tumor ecosystem was determined. Finally, four models were developed: clinical, intratumoral heterogeneity (ITH)-based, radiomics, and fusion models. The performance of these models was evaluated. The impact of nCRT on disease-free survival (DFS) was further analyzed. The Delong test revealed the fusion model (AUCs of 0.867, 0.851, 0.852, and 0.818 in the four cohorts, respectively), the radiomics model (0.831, 0.694, 0.753, and 0.705, respectively), and the ITH model (0.790, 0.786, 0.759, and 0.722, respectively) were all superior to the clinical model (0.790, 0.605, 0.735, and 0.704, respectively). However, no significant differences were detected between the fusion and ITH models. Patients stratified using the fusion model showed significant differences in DFS between the good and poor response groups (all p < 0.05 in the four sets). The fusion model combining clinical factors, radiomics features, and ITH features may help predict pathologic response in RC cases receiving nCRT. Question Identifying rectal cancer (RC) patients likely to benefit from neoadjuvant chemoradiotherapy (nCRT) before treatment is crucial. Findings The fusion model shows the best performance in predicting response after neoadjuvant chemoradiotherapy. Clinical relevance The fusion model integrates clinical characteristics, radiomics features, and intratumoral heterogeneity (ITH)features, which can be applied for the prediction of response to nCRT in RC patients, offering potential benefits in terms of personalized treatment strategies.

Brain metastases represent one of the most common intracranial malignancies, yet early and accurate detection remains challenging, particularly in clinical datasets with limited availability of healthy controls. In this study, we developed a feature-based machine learning framework to classify patients with and without brain metastases using multi-modal clinical MRI scans. A dataset of 50 subjects from the UCSF Brain Metastases collection was analyzed, including pre- and post-contrast T1-weighted images and corresponding segmentation masks. We designed advanced feature extraction strategies capturing intensity, enhancement patterns, texture gradients, and histogram-based metrics, resulting in 44 quantitative descriptors per subject. To address the severe class imbalance (46 metastasis vs. 4 non-metastasis cases), we applied minority oversampling and noise-based augmentation, combined with stratified cross-validation. Among multiple classifiers, Random Forest consistently achieved the highest performance with an average accuracy of 96.7% and an area under the ROC curve (AUC) of 0.99 across five folds. The proposed approach highlights the potential of handcrafted radiomic-like features coupled with machine learning to improve metastasis detection in heterogeneous clinical MRI cohorts. These findings underscore the importance of methodological strategies for handling imbalanced data and support the integration of feature-based models as complementary tools for brain metastasis screening and research.

Alterations in brain connectivity provide early indications of neurodegenerative diseases like Alzheimer's disease (AD). Here, we present a novel framework that integrates a Hidden Markov Model (HMM) within the architecture of a convolutional neural network (CNN) to analyze dynamic functional connectivity (dFC) in resting-state functional magnetic resonance imaging (rs-fMRI). Our unsupervised approach captures recurring connectivity states in a large cohort of subjects spanning the Alzheimer's disease continuum, including healthy controls, individuals with mild cognitive impairment (MCI), and patients with clinically diagnosed AD. We propose a deep neural model with embedded HMM dynamics to identify stable recurring brain states from resting-state fMRI. These states exhibit distinct connectivity patterns and are differentially expressed across the Alzheimer's disease continuum. Our analysis shows that the fraction of time each state is active varies systematically with disease severity, highlighting dynamic network alterations that track neurodegeneration. Our findings suggest that the disruption of dynamic connectivity patterns in AD may follow a two-stage trajectory, where early shifts toward integrative network states give way to reduced connectivity organization as the disease progresses. This framework offers a promising tool for early diagnosis and monitoring of AD, and may have broader applications in the study of other neurodegenerative conditions.

Alzheimer's disease, the most prevalent form of dementia, leads to a fatal progression after progressively destroying memory at each stage. This irreversible disease appears more frequently in older populations. Even though research on Alzheimer's disease has risen over the past few years, the intricacy of brain structure and function creates challenges for accurate disease diagnosis. As a neuroimaging technology, resting-state functional magnetic resonance imaging enables researchers to study debilitating neural diseases while scanning the brain. The research investigates resting-state functional magnetic resonance imaging approaches and deep learning methods to distinguish between Alzheimer's patients and normal individuals. resting-state functional magnetic resonance imaging of 97 participants is obtained from the Alzheimer's disease neuroimaging initiative database, with 56 participants classified in the Alzheimer's disease group and 41 in the normal control group. Extensive preprocessing is applied to the resting-state functional magnetic resonance imaging data before classification. Using transfer learning, classification between the normal control and Alzheimer's disease groups is conducted with proposed VGG19, AlexNet, and ResNet50 algorithms; the classification accuracy of them is 96.91 %, 98.71 %, and 98.20 %, respectively. For evaluation, precision, recall, and F1-score are utilized as additional assessment metrics. The AlexNet model exhibits higher accuracy than the other models and outperforms them in other evaluation metrics, including precision, recall, and F1-score. While AlexNet achieves the highest overall classification performance, ResNet50 demonstrates superior interpretability through Grad-CAM visualizations, producing more anatomically focused and clinically meaningful attention maps.

High-quality reference standard image data creation by neuroradiology experts for automated clinical tools can be a powerful tool for neuroradiology & artificial intelligence education. We developed a multimodal educational approach for students and trainees during the MICCAI Brain Tumor Segmentation Lighthouse Challenge 2025, a landmark initiative to develop accurate brain tumor segmentation algorithms. Fifty-six medical students & radiology trainees volunteered to annotate brain tumor MR images for the BraTS challenges of 2023 & 2024, guided by faculty-led didactics on neuropathology MRI. Among the 56 annotators, 14 select volunteers were then paired with neuroradiology faculty for guided one-on-one annotation sessions for BraTS 2025. Lectures on neuroanatomy, pathology & AI, journal clubs & data scientist-led workshops were organized online. Annotators & audience members completed surveys on their perceived knowledge before & after annotations & lectures respectively. Fourteen coordinators, each paired with a neuroradiologist, completed the data annotation process, averaging 1322.9+/-760.7 hours per dataset per pair and 1200 segmentations in total. On a scale of 1-10, annotation coordinators reported significant increase in familiarity with image segmentation software pre- and post-annotation, moving from initial average of 6+/-2.9 to final average of 8.9+/-1.1, and significant increase in familiarity with brain tumor features pre- and post-annotation, moving from initial average of 6.2+/-2.4 to final average of 8.1+/-1.2. We demonstrate an innovative offering for providing neuroradiology & AI education through an image segmentation challenge to enhance understanding of algorithm development, reinforce the concept of data reference standard, and diversify opportunities for AI-driven image analysis among future physicians.