We propose a cascaded 3D diffusion model framework to synthesize high-fidelity 3D PET/CT volumes directly from demographic variables, addressing the growing need for realistic digital twins in oncologic imaging, virtual trials, and AI-driven data augmentation. Unlike deterministic phantoms, which rely on predefined anatomical and metabolic templates, our method employs a two-stage generative process. An initial score-based diffusion model synthesizes low-resolution PET/CT volumes from demographic variables alone, providing global anatomical structures and approximate metabolic activity. This is followed by a super-resolution residual diffusion model that refines spatial resolution. Our framework was trained on 18-F FDG PET/CT scans from the AutoPET dataset and evaluated using organ-wise volume and standardized uptake value (SUV) distributions, comparing synthetic and real data between demographic subgroups. The organ-wise comparison demonstrated strong concordance between synthetic and real images. In particular, most deviations in metabolic uptake values remained within 3-5% of the ground truth in subgroup analysis. These findings highlight the potential of cascaded 3D diffusion models to generate anatomically and metabolically accurate PET/CT images, offering a robust alternative to traditional phantoms and enabling scalable, population-informed synthetic imaging for clinical and research applications.

Alzheimer's disease (AD) is a devastating neurological disorder that affects humans and is a major contributor to dementia. It is characterized by cognitive dysfunction, impairing an individual's ability to perform daily tasks. In AD, nerve cells in areas of the brain related to cognitive function are damaged. Despite extensive research, there is currently no specific therapeutic or diagnostic approach for this fatal disease. However, scientists worldwide have developed effective techniques for diagnosing and managing this challenging disorder. Among the various methods used to diagnose AD are feedback from blood relatives and observations of changes in an individual's behavioral and cognitive abilities. Biomarkers, such as amyloid beta and measures of neurodegeneration, aid in the early detection of Alzheimer's disease (AD) through cerebrospinal fluid (CSF) samples and brain imaging techniques like Magnetic Resonance Imaging (MRI). Advanced medical imaging technologies, including X-ray, CT, MRI, ultrasound, mammography, and PET, provide valuable insights into human anatomy and function. MRI, in particular, is non-invasive and useful for scanning both the structural and functional aspects of the brain. Additionally, Machine Learning (ML) and deep learning (DL) technologies, especially Convolutional Neural Networks (CNNs), have demonstrated high accuracy in diagnosing AD by detecting brain changes. However, these technologies are intended to support, rather than replace, clinical assessments by medical professionals.

Occupational health assessment is critical for detecting respiratory issues caused by harmful exposures, such as cement dust. Quantitative computed tomography (QCT) imaging provides detailed insights into lung structure and function, enhancing the diagnosis of lung diseases. However, its high dimensionality poses challenges for traditional machine learning methods. In this study, Kolmogorov-Arnold networks (KANs) were used for the binary classification of QCT imaging data to assess respiratory conditions associated with cement dust exposure. The dataset comprised QCT images from 609 individuals, including 311 subjects exposed to cement dust and 298 healthy controls. We derived 141 QCT-based variables and employed KANs with two hidden layers of 15 and 8 neurons. The network parameters, including grid intervals, polynomial order, learning rate, and penalty strengths, were carefully fine-tuned. The performance of the model was assessed through various metrics, including accuracy, precision, recall, F1 score, specificity, and the Matthews Correlation Coefficient (MCC). A five-fold cross-validation was employed to enhance the robustness of the evaluation. SHAP analysis was applied to interpret the sensitive QCT features. The KAN model demonstrated consistently high performance across all metrics, with an average accuracy of 98.03 %, precision of 97.35 %, recall of 98.70 %, F1 score of 98.01 %, and specificity of 97.40 %. The MCC value further confirmed the robustness of the model in managing imbalanced datasets. The comparative analysis demonstrated that the KAN model outperformed traditional methods and other deep learning approaches, such as TabPFN, ANN, FT-Transformer, VGG19, MobileNets, ResNet101, XGBoost, SVM, random forest, and decision tree. SHAP analysis highlighted structural and functional lung features, such as airway geometry, wall thickness, and lung volume, as key predictors. KANs significantly improved the classification of QCT imaging data, enhancing early detection of cement dust-induced respiratory conditions. SHAP analysis supported model interpretability, enhancing its potential for clinical translation in occupational health assessments.

Valid non-invasive biomarkers for Parkinson's disease (PD) and Parkinson-plus syndrome (PPS) are urgently needed. Based on our recent self-supervised vision foundation model the Shift Window UNET TRansformer (Swin UNETR), which uses clinical multi-contrast whole brain MRI, we aimed to develop an efficient and practical model ('SwinClassifier') for the discrimination of PD vs PPS using routine clinical MRI scans. We used 75,861 clinical head MRI scans including T1-weighted, T2-weighted and fluid attenuated inversion recovery imaging as a pre-training dataset to develop a foundation model, using self-supervised learning with a cross-contrast context recovery task. Then clinical head MRI scans from n = 1992 participants with PD and n = 1989 participants with PPS were used as a downstream PD vs PPS classification dataset. We then assessed SwinClassifier's performance in confusion matrices compared to a comparative self-supervised vanilla Vision Transformer (ViT) autoencoder ('ViTClassifier'), and to two convolutional neural networks (DenseNet121 and ResNet50) trained from scratch. SwinClassifier showed very good performance (F1 score 0.83, 95% confidence interval [CI] [0.79-0.87], AUC 0.89) in PD vs PPS discrimination in independent test datasets (n = 173 participants with PD and n = 165 participants with PPS). This self-supervised classifier with pretrained weights outperformed the ViTClassifier and convolutional classifiers trained from scratch (F1 score 0.77-0.82, AUC 0.83-0.85). Occlusion sensitivity mapping in the correctly-classified cases (n = 160 PD and n = 114 PPS) highlighted the brain regions guiding discrimination mainly in sensorimotor and midline structures including cerebellum, brain stem, ventricle and basal ganglia. Our self-supervised digital model based on routine clinical head MRI discriminated PD vs PPS with good accuracy and sensitivity. With incremental improvements the approach may be diagnostically useful in early disease. National Key Research and Development Program of China.

The radiology specialty examination assesses clinical decision-making, image interpretation, and diagnostic reasoning. With the expansion of medical knowledge, traditional test design faces challenges in maintaining accuracy and relevance. Large language models (LLMs) demonstrate potential in medical education. This study evaluates LLM performance in radiology specialty exams, explores their role in assessing question difficulty, and investigates their reasoning processes, aiming to develop a more objective and efficient framework for exam design. This study compared the performance of LLMs and human examinees in a radiology specialty examination. Three LLMs (GPT-4o, o1-preview, and GPT-3.5-turbo-1106) were evaluated under zero-shot conditions. Exam accuracy, examinee accuracy, discrimination index, and point-biserial correlation were used to assess LLMs' ability to predict question difficulty and reasoning processes. The data provided by the Taiwan Radiological Society ensures comparability between AI and human performance. As for accuracy, GPT-4o (88.0%) and o1-preview (90.9%) outperformed human examinees (76.3%), whereas GPT-3.5-turbo-1106 showed significantly lower accuracy (50.2%). Question difficulty analysis revealed that newer LLMs excel in solving complex questions, while GPT-3.5-turbo-1106 exhibited greater performance variability. Discrimination index and point-biserial Correlation analyses demonstrated that GPT-4o and o1-preview accurately identified key differentiating questions, closely mirroring human reasoning patterns. These findings suggest that advanced LLMs can assess medical examination difficulty, offering potential applications in exam standardization and question evaluation. This study evaluated the problem-solving capabilities of GPT-3.5-turbo-1106, GPT-4o, and o1-preview in a radiology specialty examination. LLMs should be utilized as tools for assessing exam question difficulty and assisting in the standardized development of medical examinations.

Recent vision-language foundation models deliver state-of-the-art results on natural image classification but falter on medical images due to pronounced domain shifts. At the same time, training a medical foundation model requires substantial resources, including extensive annotated data and high computational capacity. To bridge this gap with minimal overhead, we introduce MedBridge, a lightweight multimodal adaptation framework that re-purposes pretrained VLMs for accurate medical image diagnosis. MedBridge comprises three key components. First, a Focal Sampling module that extracts high-resolution local regions to capture subtle pathological features and compensate for the limited input resolution of general-purpose VLMs. Second, a Query Encoder (QEncoder) injects a small set of learnable queries that attend to the frozen feature maps of VLM, aligning them with medical semantics without retraining the entire backbone. Third, a Mixture of Experts mechanism, driven by learnable queries, harnesses the complementary strength of diverse VLMs to maximize diagnostic performance. We evaluate MedBridge on five medical imaging benchmarks across three key adaptation tasks, demonstrating its superior performance in both cross-domain and in-domain adaptation settings, even under varying levels of training data availability. Notably, MedBridge achieved over 6-15% improvement in AUC compared to state-of-the-art VLM adaptation methods in multi-label thoracic disease diagnosis, underscoring its effectiveness in leveraging foundation models for accurate and data-efficient medical diagnosis. Our code is available at https://github.com/ai-med/MedBridge.

Predicting the risk of developing breast cancer is an important clinical tool to guide early intervention and tailoring personalized screening strategies. Early risk models have limited performance and recently machine learning-based analysis of mammogram images showed encouraging risk prediction effects. These models however are limited to the use of a single exam or tend to overlook nuanced breast tissue evolvement in spatial and temporal details of longitudinal imaging exams that are indicative of breast cancer risk. In this paper, we propose STA-Risk (Spatial and Temporal Asymmetry-based Risk Prediction), a novel Transformer-based model that captures fine-grained mammographic imaging evolution simultaneously from bilateral and longitudinal asymmetries for breast cancer risk prediction. STA-Risk is innovative by the side encoding and temporal encoding to learn spatial-temporal asymmetries, regulated by a customized asymmetry loss. We performed extensive experiments with two independent mammogram datasets and achieved superior performance than four representative SOTA models for 1- to 5-year future risk prediction. Source codes will be released upon publishing of the paper.

The automated generation of radiology reports from chest X-ray images holds significant promise in enhancing diagnostic workflows while preserving patient privacy. Traditional centralized approaches often require sensitive data transfer, posing privacy concerns. To address this, the study proposes a Multimodal Federated Learning framework for chest X-ray report generation using the IU-Xray dataset. The system utilizes a Vision Transformer (ViT) as the encoder and GPT-2 as the report generator, enabling decentralized training without sharing raw data. Three Federated Learning (FL) aggregation strategies: FedAvg, Krum Aggregation and a novel Loss-aware Federated Averaging (L-FedAvg) were evaluated. Among these, Krum Aggregation demonstrated superior performance across lexical and semantic evaluation metrics such as ROUGE, BLEU, BERTScore and RaTEScore. The results show that FL can match or surpass centralized models in generating clinically relevant and semantically rich radiology reports. This lightweight and privacy-preserving framework paves the way for collaborative medical AI development without compromising data confidentiality.

Machine learning, particularly through advanced imaging techniques such as three-dimensional Magnetic Resonance Imaging (MRI), has significantly improved medical diagnostics. This is especially critical for diagnosing complex conditions like Alzheimer's disease. Our study introduces Triamese-ViT, an innovative Tri-structure of Vision Transformers (ViTs) that incorporates a built-in interpretability function, it has structure-aware explainability that allows for the identification and visualization of key features or regions contributing to the prediction, integrates information from three perspectives to enhance brain age estimation. This method not only increases accuracy but also improves interoperability with existing techniques. When evaluated, Triamese-ViT demonstrated superior performance and produced insightful attention maps. We applied these attention maps to the analysis of natural aging and the diagnosis of Autism Spectrum Disorder (ASD). The results aligned with those from occlusion analysis, identifying the Cingulum, Rolandic Operculum, Thalamus, and Vermis as important regions in normal aging, and highlighting the Thalamus and Caudate Nucleus as key regions for ASD diagnosis.

The differential diagnosis of neurodegenerative dementias is a challenging clinical task, mainly because of the overlap in symptom presentation and the similarity of patterns observed in structural neuroimaging. To improve diagnostic efficiency and accuracy, deep learning-based methods such as Convolutional Neural Networks and Vision Transformers have been proposed for the automatic classification of brain MRIs. However, despite their strong predictive performance, these models find limited clinical utility due to their opaque decision making. In this work, we propose a framework that integrates two core components to enhance diagnostic transparency. First, we introduce a modular pipeline for converting 3D T1-weighted brain MRIs into textual radiology reports. Second, we explore the potential of modern Large Language Models (LLMs) to assist clinicians in the differential diagnosis between Frontotemporal dementia subtypes, Alzheimer's disease, and normal aging based on the generated reports. To bridge the gap between predictive accuracy and explainability, we employ reinforcement learning to incentivize diagnostic reasoning in LLMs. Without requiring supervised reasoning traces or distillation from larger models, our approach enables the emergence of structured diagnostic rationales grounded in neuroimaging findings. Unlike post-hoc explainability methods that retrospectively justify model decisions, our framework generates diagnostic rationales as part of the inference process-producing causally grounded explanations that inform and guide the model's decision-making process. In doing so, our framework matches the diagnostic performance of existing deep learning methods while offering rationales that support its diagnostic conclusions.