Multi-sequence Magnetic Resonance Imaging (MRI) offers remarkable versatility, enabling the distinct visualization of different tissue types. Nevertheless, the inherent heterogeneity among MRI sequences poses significant challenges to the generalization capability of deep learning models. These challenges undermine model performance when faced with varying acquisition parameters, thereby severely restricting their clinical utility. In this study, we present PRISM, a foundation model PRe-trained with large-scale multI-Sequence MRI. We collected a total of 64 datasets from both public and private sources, encompassing a wide range of whole-body anatomical structures, with scans spanning diverse MRI sequences. Among them, 336,476 volumetric MRI scans from 34 datasets (8 public and 26 private) were curated to construct the largest multi-organ multi-sequence MRI pretraining corpus to date. We propose a novel pretraining paradigm that disentangles anatomically invariant features from sequence-specific variations in MRI, while preserving high-level semantic representations. We established a benchmark comprising 44 downstream tasks, including disease diagnosis, image segmentation, registration, progression prediction, and report generation. These tasks were evaluated on 32 public datasets and 5 private cohorts. PRISM consistently outperformed both non-pretrained models and existing foundation models, achieving first-rank results in 39 out of 44 downstream benchmarks with statistical significance improvements. These results underscore its ability to learn robust and generalizable representations across unseen data acquired under diverse MRI protocols. PRISM provides a scalable framework for multi-sequence MRI analysis, thereby enhancing the translational potential of AI in radiology. It delivers consistent performance across diverse imaging protocols, reinforcing its clinical applicability.

Bronchial artery chemoembolization (BACE) is a new treatment method for lung cancer. This study aimed to investigate the ability of dual-energy computed tomography (DECT) to predict early recurrence (ER) after BACE among patients with non-small cell lung cancer (NSCLC) who failed first-line therapy. Clinical and imaging data from NSCLC patients undergoing BACE at Wenzhou Medical University Affiliated Fifth *** Hospital (10/2023-06/2024) were retrospectively analyzed. Logistic regression (LR) machine learning models were developed using 5 arterial-phase (AP) virtual monoenergetic images (VMIs; 40, 70, 100, 120, and 150 keV), while deep learning models utilized ResNet50/101/152 architectures with iodine maps. A combined model integrating optimal Rad-score, DL-score, and clinical features was established. Model performance was assessed via area under the receiver operating characteristic curve analysis (AUC), with SHapley Additive exPlanations (SHAP) framework applied for interpretability. A total of 196 patients were enrolled in this study (training cohort: n=158; testing cohort: n=38). The 100 keV machine learning model demonstrated superior performance (AUC=0.751) compared to other VMIs. The deep learning model based on the ResNet101 method (AUC=0.791) performed better than other approaches. The hybrid model combining Rad-score-100keV-A, Rad-score-100keV-V, DL-score-ResNet101-A, DL-score-ResNet101-V, and clinical features exhibited the best performance (AUC=0.798) among all models. DECT holds promise for predicting ER after BACE among NSCLC patients who have failed first-line therapy, offering valuable guidance for clinical treatment planning.

We developed a machine learning model comprising morphological characteristics, enhancement dynamics, and extracellular volume (ECV) fractions for distinguishing malignant and benign small renal masses (SRMs), supporting personalised management. This retrospective analysis involved 230 patients who underwent SRM resection with preoperative imaging, including 185 internal and 45 external cases. The internal cohort was split into training (n=136) and validation (n=49) sets. Histopathological evaluation categorised the lesions as renal cell carcinomas (n=183) or benign masses (n=47). Eleven multiphasic contrast-enhanced computed tomography (CT) parameters, including the ECV fraction, were manually measured, along with clinical and laboratory data. Feature selection involved univariate analysis and least absolute shrinkage and selection operator regularisation. Feature selection informed various machine learning classifiers, and performance was evaluated using receiver operating characteristic curves and classification tests. The optimal model was interpreted using SHapley Additive exPlanations (SHAP). The analysis included 183 carcinoma and 47 benign SRM cases. Feature selection identified seven discriminative parameters, including the ECV fraction, which informed multiple machine learning models. The Extreme Gradient Boosting model incorporating ECV exhibited optimal performance in distinguishing malignant and benign SRMs, achieving area under the curve values of 0.993 (internal training set), 0.986 (internal validation set), and 0.951 (external test set). SHAP analysis confirmed ECV as the top contributor to SRM characterisation. The integration of multiphase contrast-enhanced CT-derived ECV fraction with conventional contrast-enhanced CT parameters demonstrated diagnostic efficacy in differentiating malignant and benign SRMs.

This review synthesizes current evidence regarding optimal breast cancer screening strategies for women with dense breasts, a population at increased risk due to decreased mammographic sensitivity. A systematic literature review was performed in accordance with PRISMA criteria, covering MEDLINE, EMBASE, CINAHL Plus, Scopus, and Web of Science until May 2025. The analysis examines advanced imaging techniques such as digital breast tomosynthesis (DBT), contrast-enhanced spectral mammography (CESM), ultrasound, and magnetic resonance imaging (MRI), assessing their effectiveness in addressing the shortcomings of traditional mammography in dense breast tissue. The review rigorously evaluates the incorporation of risk stratification models, such as the BCSC, in customizing screening regimens, in conjunction with innovative technologies like liquid biopsy and artificial intelligence-based image analysis for improved risk prediction. A key emphasis is placed on the heterogeneity in international screening guidelines and the challenges in translating research findings to diverse clinical settings, particularly in resource-constrained environments. The discussion includes ethical implications regarding compulsory breast density notification and the possibility of intensifying disparities in health care. The review ultimately encourages the development of evidence-based, context-specific guidelines that facilitate equitable access to effective breast cancer screening for all women with dense breasts.

Functional Magnetic Resonance Imaging (fMRI) is an imaging technique widely used to study human brain activity. fMRI signals in areas across the brain transiently synchronise and desynchronise their activity in a highly structured manner, even when an individual is at rest. These functional connectivity dynamics may be related to behaviour and neuropsychiatric disease. To model these dynamics, temporal brain connectivity representations are essential, as they reflect evolving interactions between brain regions and provide insight into transient neural states and network reconfigurations. However, conventional graph neural networks (GNNs) often struggle to capture long-range temporal dependencies in dynamic fMRI data. To address this challenge, we propose BrainATCL, an unsupervised, nonparametric framework for adaptive temporal brain connectivity learning, enabling functional link prediction and age estimation. Our method dynamically adjusts the lookback window for each snapshot based on the rate of newly added edges. Graph sequences are subsequently encoded using a GINE-Mamba2 backbone to learn spatial-temporal representations of dynamic functional connectivity in resting-state fMRI data of 1,000 participants from the Human Connectome Project. To further improve spatial modeling, we incorporate brain structure and function-informed edge attributes, i.e., the left/right hemispheric identity and subnetwork membership of brain regions, enabling the model to capture biologically meaningful topological patterns. We evaluate our BrainATCL on two tasks: functional link prediction and age estimation. The experimental results demonstrate superior performance and strong generalization, including in cross-session prediction scenarios.

Accurate and interpretable classification of brain tumors from magnetic resonance imaging (MRI) is critical for effective diagnosis and treatment planning. This study presents an ensemble-based deep learning framework that combines MobileNetV2 and DenseNet121 convolutional neural networks (CNNs) using a soft voting strategy to classify three common brain tumor types: glioma, meningioma, and pituitary adenoma. The models were trained and evaluated on the Figshare dataset using a stratified 5-fold cross-validation protocol. To enhance transparency and clinical trust, the framework integrates an Explainable AI (XAI) module employing Grad-CAM++ for class-specific saliency visualization, alongside a symbolic Clinical Decision Rule Overlay (CDRO) that maps predictions to established radiological heuristics. The ensemble classifier achieved superior performance compared to individual CNNs, with an accuracy of 91.7%, precision of 91.9%, recall of 91.7%, and F1-score of 91.6%. Grad-CAM++ visualizations revealed strong spatial alignment between model attention and expert-annotated tumor regions, supported by Dice coefficients up to 0.88 and IoU scores up to 0.78. Clinical rule activation further validated model predictions in cases with distinct morphological features. A human-centered interpretability assessment involving five board-certified radiologists yielded high Likert-scale scores for both explanation usefulness (mean = 4.4) and heatmap-region correspondence (mean = 4.0), reinforcing the framework's clinical relevance. Overall, the proposed approach offers a robust, interpretable, and generalizable solution for automated brain tumor classification, advancing the integration of deep learning into clinical neurodiagnostics.

Accurate, noninvasive detection of isocitrate dehydrogenase (IDH) mutation is essential for effective glioma management. Traditional methods rely on invasive tissue sampling, which may fail to capture a tumor's spatial heterogeneity. While deep learning models have shown promise in molecular profiling, their performance is often limited by scarce annotated data. In contrast, foundation deep learning models offer a more generalizable approach for glioma imaging biomarkers. We propose a Foundation-based Biomarker Network (FoundBioNet) that utilizes a SWIN-UNETR-based architecture to noninvasively predict IDH mutation status from multi-parametric MRI. Two key modules are incorporated: Tumor-Aware Feature Encoding (TAFE) for extracting multi-scale, tumor-focused features, and Cross-Modality Differential (CMD) for highlighting subtle T2-FLAIR mismatch signals associated with IDH mutation. The model was trained and validated on a diverse, multi-center cohort of 1705 glioma patients from six public datasets. Our model achieved AUCs of 90.58%, 88.08%, 65.41%, and 80.31% on independent test sets from EGD, TCGA, Ivy GAP, RHUH, and UPenn, consistently outperforming baseline approaches (p <= 0.05). Ablation studies confirmed that both the TAFE and CMD modules are essential for improving predictive accuracy. By integrating large-scale pretraining and task-specific fine-tuning, FoundBioNet enables generalizable glioma characterization. This approach enhances diagnostic accuracy and interpretability, with the potential to enable more personalized patient care.

This study aims to construct and evaluate 8 machine learning models by integrating ultrasound imaging features, clinical characteristics, and serological features to assess the risk of gallbladder cancer (GBC) occurrence in patients. A retrospective analysis was conducted on ultrasound and clinical data of 300 suspected GBC patients who visited the Second Affiliated Hospital of Fujian Medical University from January 2020 to January 2024 and 69 patients who visited the Zhongshan Hospital Affiliated to Xiamen University from January 2024 to January 2025. Key relevant features were selected using Least Absolute Shrinkage and Selection Operator (LASSO) regression. Predictive models were constructed using XGBoost, logistic regression, support vector machine, k-nearest neighbors, random forest, decision tree, naive Bayes, and neural network, with the SHapley Additive exPlanations (SHAP) method employed to explain model interpretability. The LASSO regression demonstrated that gender, age, alkaline phosphatase (ALP), clarity of interface with liver, stratification of the gallbladder wall, intracapsular anechoic lesions, and intracapsular punctiform strong lesions were key features for GBC. The XGBoost model demonstrated an area under receiver operating characteristic curve (AUC) of 0.934, 0.916, and 0.813 in the training, validating, and test sets. SHAP analysis revealed the importance ranking of factors as clarity of interface with liver, stratification of the gallbladder wall, intracapsular anechoic lesions, and intracapsular punctiform strong lesions, ALP, gender, and age. Personalized prediction explanations through SHAP values demonstrated the contribution of each feature to the final prediction, enhancing result interpretability. Furthermore, decision plots were generated to display the influence trajectory of each feature on model predictions, aiding in analyzing which features had the greatest impact on these mispredictions; thereby facilitating further model optimization or feature adjustment. This study proposed a GBC ML model based on ultrasound, clinical, and serological characteristics, indicating the superior performance of the XGBoost model and enhancing the interpretability of the model through the SHAP method.

Although the use of artificial intelligence (AI) in healthcare is increasing, stakeholder engagement remains poor, particularly relating to understanding parent/carer acceptance of AI tools in paediatric imaging. We explore these perceptions and compare them to the opinions of children and young people (CYAP). A UK national online survey was conducted, inviting parents, carers and guardians of children to participate. The survey was "live" from June 2022 to 2023. The survey included questions asking about respondents' views of AI in general, as well as in specific circumstances (e.g. fractures) with respect to children's healthcare. One hundred forty-six parents/carers (mean age = 45; range = 21-80) from all four nations of the UK responded. Most respondents (93/146, 64%) believed that AI would be more accurate at interpreting paediatric musculoskeletal radiographs than healthcare professionals, but had a strong preference for human supervision (66%). Whilst male respondents were more likely to believe that AI would be more accurate (55/72, 76%), they were twice as likely as female parents/carers to believe that AI use could result in their child's data falling into the wrong hands. Most respondents would like to be asked permission before AI is used for the interpretation of their child's scans (104/146, 71%). Notably, 79% of parents/carers prioritised accuracy over speed compared to 66% of CYAP. Parents/carers feel positively about AI for paediatric imaging but strongly discourage autonomous use. Acknowledging the diverse opinions of the patient population is vital in aiding the successful integration of AI for paediatric imaging. Parents/carers demonstrate a preference for AI use with human supervision that prioritises accuracy, transparency and institutional accountability. AI is welcomed as a supportive tool, but not as a substitute for human expertise. Parents/carers are accepting of AI use, with human supervision. Over half believe AI would replace doctors/nurses looking at bone X-rays within 5 years. Parents/carers are more likely than CYAP to trust AI's accuracy. Parents/carers are also more sceptical about AI data misuse.

Anxiety is a common yet often underdiagnosed and undertreated comorbidity in multiple sclerosis (MS). While altered fear processing is a hallmark of anxiety in other populations, its neurobehavioral mechanisms in MS remain poorly understood. This study investigates the extent to which neurobehavioral mechanisms of fear generalization contribute to anxiety in MS. We recruited 18 persons with MS (PwMS) and anxiety, 36 PwMS without anxiety, and 23 healthy persons (HPs). Participants completed a functional MRI (fMRI) fear generalization task to assess fear processing and diffusion-weighted MRI for graph-based structural connectome analyses. Consistent with findings in non-MS anxiety populations, PwMS with anxiety exhibit fear overgeneralization, perceiving non-threating stimuli as threatening. A machine learning model trained on HPs in a multivariate pattern analysis (MVPA) cross-decoding approach accurately predicts behavioral fear generalization in both MS groups using whole-brain fMRI fear response patterns. Regional fMRI prediction and graph-based structural connectivity analyses reveal that fear response activity and structural network integrity of partially overlapping areas, such as hippocampus (for fear stimulus comparison) and anterior insula (for fear excitation), are crucial for MS fear generalization. Reduced network integrity in such regions is a direct indicator of MS anxiety. Our findings demonstrate that MS anxiety is substantially characterized by fear overgeneralization. The fact that a machine learning model trained to associate fMRI fear response patterns with fear ratings in HPs predicts fear ratings from fMRI data across MS groups using an MVPA cross-decoding approach suggests that generic fear processing mechanisms substantially contribute to anxiety in MS.