Simulating aging in 3D brain MRI scans can reveal disease progression patterns in neurological disorders such as Alzheimer's disease. Current deep learning-based generative models typically approach this problem by predicting future scans from a single observed scan. We investigate modeling brain aging via linear models in the latent space of convolutional autoencoders (MRExtrap). Our approach, MRExtrap, is based on our observation that autoencoders trained on brain MRIs create latent spaces where aging trajectories appear approximately linear. We train autoencoders on brain MRIs to create latent spaces, and investigate how these latent spaces allow predicting future MRIs through linear extrapolation based on age, using an estimated latent progression rate $\boldsymbol{\beta}$. For single-scan prediction, we propose using population-averaged and subject-specific priors on linear progression rates. We also demonstrate that predictions in the presence of additional scans can be flexibly updated using Bayesian posterior sampling, providing a mechanism for subject-specific refinement. On the ADNI dataset, MRExtrap predicts aging patterns accurately and beats a GAN-based baseline for single-volume prediction of brain aging. We also demonstrate and analyze multi-scan conditioning to incorporate subject-specific progression rates. Finally, we show that the latent progression rates in MRExtrap's linear framework correlate with disease and age-based aging patterns from previously studied structural atrophy rates. MRExtrap offers a simple and robust method for the age-based generation of 3D brain MRIs, particularly valuable in scenarios with multiple longitudinal observations.

Accurate prediction of major adverse cardiac events (MACE) remains a central challenge in cardiovascular prognosis. We present PRISM (Prompt-guided Representation Integration for Survival Modeling), a self-supervised framework that integrates visual representations from non-contrast cardiac cine magnetic resonance imaging with structured electronic health records (EHRs) for survival analysis. PRISM extracts temporally synchronized imaging features through motion-aware multi-view distillation and modulates them using medically informed textual prompts to enable fine-grained risk prediction. Across four independent clinical cohorts, PRISM consistently surpasses classical survival prediction models and state-of-the-art (SOTA) deep learning baselines under internal and external validation. Further clinical findings demonstrate that the combined imaging and EHR representations derived from PRISM provide valuable insights into cardiac risk across diverse cohorts. Three distinct imaging signatures associated with elevated MACE risk are uncovered, including lateral wall dyssynchrony, inferior wall hypersensitivity, and anterior elevated focus during diastole. Prompt-guided attribution further identifies hypertension, diabetes, and smoking as dominant contributors among clinical and physiological EHR factors.

Recent advances in molecular genetics have revolutionized the classification of pediatric-type high-grade gliomas in the 2021 World Health Organization central nervous system tumor classification. This narrative review synthesizes current evidence on the following four tumor types: diffuse midline glioma, H3 K27-altered; diffuse hemispheric glioma, H3 G34-mutant; diffuse pediatric-type high-grade glioma, H3-wildtype and IDH-wildtype; and infant-type hemispheric glioma. We conducted a comprehensive literature search for articles published through January 2025. For each tumor type, we analyze characteristic clinical presentations, molecular alterations, conventional and advanced magnetic resonance imaging features, radiological-molecular correlations, and current therapeutic approaches. Emerging radiogenomic approaches utilizing artificial intelligence, including radiomics and deep learning, show promise in identifying imaging biomarkers that correlate with molecular features. This review highlights the importance of integrating radiological and molecular data for accurate diagnosis and treatment planning, while acknowledging limitations in current methodologies and the need for prospective validation in larger cohorts. Understanding these correlations is crucial for advancing personalized treatment strategies for these challenging tumors.

Enhancing the resolution of Magnetic Resonance Imaging (MRI) through super-resolution (SR) reconstruction is crucial for boosting diagnostic precision. However, current SR methods primarily rely on single LR images or multi-contrast features, limiting detail restoration. Inspired by video frame interpolation, this work utilizes the spatiotemporal correlations between adjacent slices to reformulate the SR task of anisotropic 3D-MRI image into the generation of new high-resolution (HR) slices between adjacent 2D slices. The generated SR slices are subsequently combined with the HR adjacent slices to create a new HR 3D-MRI image. We propose a innovative network architecture termed DGWMSR, comprising a backbone network and a feature supplement module (FSM). The backbone's core innovations include the displacement former block (DFB) module, which independently extracts structural and displacement features, and the maskdisplacement vector network (MDVNet) which combines with Warp mechanism to facilitate edge pixel detailing. The DFB integrates the inter-slice attention (ISA) mechanism into the Transformer, effectively minimizing the mutual interference between the two types of features and mitigating volume effects during reconstruction. Additionally, the FSM module combines self-attention with feed-forward neural network, which emphasizes critical details derived from the backbone architecture. Experimental results demonstrate the DGWMSR network outperforms current MRI SR methods on Kirby21, ANVIL-adult, and MSSEG datasets. Our code has been made publicly available on GitHub at https://github.com/Dohbby/DGWMSR.

Rectal cancer is a major cause of cancer-related mortality, requiring accurate diagnosis via MRI scans. However, detecting rectal cancer in MRI scans is challenging due to image complexity and the need for precise localization. While transformer-based object detection has excelled in natural images, applying these models to medical data is hindered by limited medical imaging resources. To address this, we propose the Spatially Prioritized Detection Transformer (SP DETR), which incorporates a Spatially Prioritized (SP) Decoder to constrain anchor boxes to regions of interest (ROI) based on anatomical maps, focusing the model on areas most likely to contain cancer. Additionally, the SP cross-attention mechanism refines the learning of anchor box offsets. To improve small cancer detection, we introduce the Global Context-Guided Feature Fusion Module (GCGFF), leveraging a transformer encoder for global context and a Globally-Guided Semantic Fusion Block (GGSF) to enhance high-level semantic features. Experimental results show that our model significantly improves detection accuracy, especially for small rectal cancers, demonstrating the effectiveness of integrating anatomical priors with transformer-based models for clinical applications.

To determine whether deep learning (DL)-based image quality (IQ) assessment of T2-weighted images (T2WI) could be biased by the presence of clinically significant prostate cancer (csPCa). In this three-center retrospective study, five abdominal radiologists categorized IQ of 2,105 transverse T2WI series into optimal, mild, moderate, and severe degradation. An IQ classification model was developed using 1,719 series (development set). The agreement between the model and radiologists was assessed using the remaining 386 series with a quadratic weighted kappa. The model was applied to 11,723 examinations that were not included in the development set and without documented prostate cancer at the time of MRI (patient age, 65.5 ± 8.3 years [mean ± standard deviation]). Examinations categorized as mild to severe degradation were used as target groups, whereas those as optimal were used to construct matched control groups. Case-control matching was performed to mitigate the effects of pre-MRI confounding factors, such as age and prostate-specific antigen value. The proportion of patients with csPCa was compared between the target and matched control groups using the chi-squared test. The agreement between the model and radiologists was moderate with a quadratic weighted kappa of 0.53. The mild-moderate IQ-degraded groups had significantly higher csPCa proportions than the matched control groups with optimal IQ: moderate (N = 126) vs. optimal (N = 504), 26.3% vs. 22.7%, respectively, difference = 3.6% [95% confidence interval: 0.4%, 6.8%], p = 0.03; mild (N = 1,399) vs. optimal (N = 1,399), 22.9% vs. 20.2%, respectively, difference = 2.7% [0.7%, 4.7%], p = 0.008. The DL-based IQ tended to be worse in patients with csPCa, raising concerns about its clinical application.

Accurate prediction of clinical scores is critical for early detection and prognosis of Alzheimers disease (AD). While existing approaches primarily focus on forecasting the ADAS-Cog global score, they often overlook the predictive value of its sub-scores (13 items), which capture domain-specific cognitive decline. In this study, we propose a multi task learning (MTL) framework that jointly predicts the global ADAS-Cog score and its sub-scores (13 items) at Month 24 using baseline MRI and longitudinal clinical scores from baseline and Month 6. The main goal is to examine how each sub scores particularly those associated with MRI features contribute to the prediction of the global score, an aspect largely neglected in prior MTL studies. We employ Vision Transformer (ViT) and Swin Transformer architectures to extract imaging features, which are fused with longitudinal clinical inputs to model cognitive progression. Our results show that incorporating sub-score learning improves global score prediction. Subscore level analysis reveals that a small subset especially Q1 (Word Recall), Q4 (Delayed Recall), and Q8 (Word Recognition) consistently dominates the predicted global score. However, some of these influential sub-scores exhibit high prediction errors, pointing to model instability. Further analysis suggests that this is caused by clinical feature dominance, where the model prioritizes easily predictable clinical scores over more complex MRI derived features. These findings emphasize the need for improved multimodal fusion and adaptive loss weighting to achieve more balanced learning. Our study demonstrates the value of sub score informed modeling and provides insights into building more interpretable and clinically robust AD prediction frameworks. (Github repo provided)

Vision foundation models (FMs) have become the predominant architecture in computer vision, providing highly transferable representations learned from large-scale, multimodal corpora. Nonetheless, they exhibit persistent limitations on tasks that require explicit reasoning over entities, roles, and spatio-temporal relations. Such relational competence is indispensable for fine-grained human activity recognition, egocentric video understanding, and multimodal medical image analysis, where spatial, temporal, and semantic dependencies are decisive for performance. We advance the position that next-generation FMs should incorporate explicit relational interfaces, instantiated as dynamic relational graphs (graphs whose topology and edge semantics are inferred from the input and task context). We illustrate this position with cross-domain evidence from recent systems in human manipulation action recognition and brain tumor segmentation, showing that augmenting FMs with lightweight, context-adaptive graph-reasoning modules improves fine-grained semantic fidelity, out of distribution robustness, interpretability, and computational efficiency relative to FM only baselines. Importantly, by reasoning sparsely over semantic nodes, such hybrids also achieve favorable memory and hardware efficiency, enabling deployment under practical resource constraints. We conclude with a targeted research agenda for FM graph hybrids, prioritizing learned dynamic graph construction, multi-level relational reasoning (e.g., part object scene in activity understanding, or region organ in medical imaging), cross-modal fusion, and evaluation protocols that directly probe relational competence in structured vision tasks.

Prognostic modeling is essential for forecasting future clinical scores and enabling early detection of Alzheimers disease (AD). While most existing methods focus on predicting the ADAS-Cog global score, they often overlook the predictive value of its 13 sub-scores, which reflect distinct cognitive domains. Some sub-scores may exert greater influence on determining global scores. Assigning higher loss weights to these clinically meaningful sub-scores can guide the model to focus on more relevant cognitive domains, enhancing both predictive accuracy and interpretability. In this study, we propose a weighted Vision Transformer (ViT)-based multi-task learning (MTL) framework to jointly predict the ADAS-Cog global score using baseline MRI scans and its 13 sub-scores at Month 24. Our framework integrates ViT as a feature extractor and systematically investigates the impact of sub-score-specific loss weighting on model performance. Results show that our proposed weighting strategies are group-dependent: strong weighting improves performance for MCI subjects with more heterogeneous MRI patterns, while moderate weighting is more effective for CN subjects with lower variability. Our findings suggest that uniform weighting underutilizes key sub-scores and limits generalization. The proposed framework offers a flexible, interpretable approach to AD prognosis using end-to-end MRI-based learning. (Github repo link will be provided after review)

Artificial intelligence (AI) chatbots have emerged as promising tools for enhancing medical communication, yet their efficacy in interpreting complex radiological reports remains underexplored. This study evaluates the performance of AI chatbots in translating magnetic resonance imaging (MRI) reports into patient-friendly language and providing clinical recommendations. A cross-sectional analysis was conducted on 6174 MRI reports from tumor patients across three hospitals. Two AI chatbots, GPT o1-preview (Chatbot 1) and Deepseek-R1 (Chatbot 2), were tasked with interpreting reports, classifying tumor characteristics, assessing surgical necessity, and suggesting treatments. Readability was measured using Flesch-Kincaid and Gunning Fog metrics, while accuracy was evaluated by medical reviewers. Statistical analyses included Friedman and Wilcoxon signed-rank tests. Both chatbots significantly improved readability, with Chatbot 2 achieving higher Flesch-Kincaid Reading Ease scores (median: 58.70 vs. 46.00, p < 0.001) and lower text complexity. Chatbot 2 outperformed Chatbot 1 in diagnostic accuracy (92.05% vs. 89.03% for tumor classification; 95.12% vs. 84.73% for surgical necessity, p < 0.001). Treatment recommendations from Chatbot 2 were more clinically relevant (98.10% acceptable vs. 75.41%), though both demonstrated high empathy (92.82-96.11%). Errors included misinterpretations of medical terminology and occasional hallucinations. AI chatbots, particularly Deepseek-R1, effectively enhance the readability and accuracy of MRI report interpretations for patients. However, physician oversight remains critical to mitigate errors. These tools hold potential to reduce healthcare burdens but require further refinement for clinical integration.