This retrospective study aims to develop a machine learning model integrating preoperative CT radiomics and clinicopathological data to predict 3-year recurrence and recurrence patterns in postoperative oesophageal squamous cell carcinoma. Tumour regions were segmented using 3D-Slicer, and radiomic features were extracted via Python. LASSO regression selected prognostic features for model integration. Clinicopathological data include tumour length, lymph node positivity, differentiation grade, and neurovascular infiltration. Ultimately, a machine learning model was established by combining the screened imaging feature data and clinicopathological data and validating model performance. A nomogram was constructed for survival prediction, and risk stratification was carried out through the prediction results of the machine learning model and the nomogram. Survival analysis was performed for stage-based patient subgroups across risk stratifications to identify adjuvant therapy-benefiting cohorts. Patients were randomly divided into a 7:3 ratio of 368 patients in the training cohorts and 158 patients in the validation cohorts. The LASSO regression screens out 6 recurrence prediction and 9 recurrence pattern prediction features, respectively. Among 526 patients (mean age 63; 427 males), the model achieved high accuracy in predicting recurrence (training cohort AUC: 0.826 [logistic regression]/0.820 [SVM]; validation cohort: 0.830/0.825) and recurrence patterns (training:0.801/0.799; validation:0.806/0.798). Risk stratification based on a machine learning model and nomogram predictions revealed that adjuvant therapy significantly improved disease-free survival in stages II-III patients with predicted recurrence and low survival (HR 0.372, 95% CI: 0.206-0.669; p < 0.001). Machine learning models exhibit excellent performance in predicting recurrence after surgery for squamous oesophageal cancer. Radiomic features of contrast-enhanced CT imaging can predict the prognosis of patients with oesophageal squamous cell carcinoma, which in turn can help clinicians stratify risk and screen out patient populations that could benefit from adjuvant therapy, thereby aiding medical decision-making. There is a lack of prognostic models for oesophageal squamous cell carcinoma in current research. The prognostic prediction model that we have developed has high accuracy by combining radiomics features and clinicopathologic data. This model aids in risk stratification of patients and aids clinical decision-making through predictive outcomes.

Out-of-distribution (OOD) generalization remains a central challenge in deploying deep learning models to real-world scenarios, particularly in domains such as biomedical images, where distribution shifts are both subtle and pervasive. While existing methods often pursue domain invariance through complex generative models or adversarial training, these approaches may overlook the underlying causal mechanisms of generalization.In this work, we propose Causally-Guided Gaussian Perturbations (CGP)-a lightweight framework that enhances OOD generalization by injecting spatially varying noise into input images, guided by soft causal masks derived from Vision Transformers. By applying stronger perturbations to background regions and weaker ones to foreground areas, CGP encourages the model to rely on causally relevant features rather than spurious correlations.Experimental results on the challenging WILDS benchmark Camelyon17 demonstrate consistent performance gains over state-of-the-art OOD baselines, highlighting the potential of causal perturbation as a tool for reliable and interpretable generalization.

The error is caused by special characters that arXiv's system doesn't recognize. Here's the cleaned version with all problematic characters replaced: Breast magnetic resonance imaging is a critical tool for cancer detection and treatment planning, but its clinical utility is hindered by poor specificity, leading to high false-positive rates and unnecessary biopsies. This study introduces a transformer-based framework for automated classification of breast lesions in dynamic contrast-enhanced MRI, addressing the challenge of distinguishing benign from malignant findings. We implemented a SegFormer architecture that achieved an AUC of 0.92 for lesion-level classification, with 100% sensitivity and 67% specificity at the patient level - potentially eliminating one-third of unnecessary biopsies without missing malignancies. The model quantifies malignant pixel distribution via semantic segmentation, producing interpretable spatial predictions that support clinical decision-making. To establish reproducible benchmarks, we curated BreastDCEDL_AMBL by transforming The Cancer Imaging Archive's AMBL collection into a standardized deep learning dataset with 88 patients and 133 annotated lesions (89 benign, 44 malignant). This resource addresses a key infrastructure gap, as existing public datasets lack benign lesion annotations, limiting benign-malignant classification research. Training incorporated an expanded cohort of over 1,200 patients through integration with BreastDCEDL datasets, validating transfer learning approaches despite primary tumor-only annotations. Public release of the dataset, models, and evaluation protocols provides the first standardized benchmark for DCE-MRI lesion classification, enabling methodological advancement toward clinical deployment.

Patient satisfaction after one year of distal radius fracture fixation is influenced by various aspects such as the surgical approach, the patient's physical functioning, and psychological factors. Hence, a multimodal machine learning prediction model combining traditional rating scales and postoperative X-ray images of patients was developed to predict patient satisfaction one year after surgery for personalized clinical treatment. In this study, we reviewed 385 patients who underwent internal fixation with a palmar plate or external fixation bracket fixation in 2018-2020. After one year of postoperative follow-up, 169 patients completed the patient wrist evaluation (PRWE), EuroQol5D (EQ-5D), and forgotten joint score-12 (FJS-12) questionnaires and were subjected to X-ray capture. The region of interest (ROI) of postoperative X-rays was outlined using 3D Slicer, and the training and test sets were divided based on the satisfaction of the patients. Python was used to extract 848 image features, and random forest embedding was used to reduce feature dimensionality. Also, a machine learning model combining the patient's functional rating scale with the downscaled X-ray-related image features was built, followed by hyperparameter debugging using the grid search method during the modeling process. The stability of the Radiomics and Integrated models was first verified using the five-fold cross-validation method, and then receiver operating characteristic curves, calibration curves, and decision curve analysis were used to evaluate the performance of the model on the training and test sets. The feature dimensionality reduction yielded 16 imaging features. The accuracy of the two models was 0.831, 0.784 and 0.966, 0.804 on the training and test sets, respectively. The area under the curve (AUC) values for the Radiomics and Integrated model were 0.937, 0.673 and 0.997, 0.823 for the training and test sets, respectively. The calibration curves and decision curve analysis (DCA) of the Integrated model for the training and test sets had a more accurate prediction probability and clinical significance than the Radiomics model. A multimodal machine learning predictive model combining imaging and patient functional rating scales demonstrated optimal predictive performance for one-year postoperative satisfaction in patients with radial fractures, providing a basis for personalized postoperative patient management.

Parkinson's disease (PD) is a chronic neurodegenerative disorder characterized by progressive loss of dopaminergic neurons in substantia nigra, resulting in both motor impairments and cognitive decline. Traditional PD classification methods are expert-dependent and time-intensive, while existing deep learning (DL) models often suffer from inconsistent accuracy, limited interpretability, and inability to fully capture PD's clinical heterogeneity. This study proposes a novel framework Enhanced EfficientNet-Extended Multimodal PD Classification with Hybrid Particle Swarm and Grey Wolf Optimizer (EEFN-XM-PDC-HybPS-GWO) to overcome these challenges. The model integrates T1-weighted MRI, DaTscan images, and gait scores from NTUA and PhysioNet repository respectively. Denoising is achieved via Multiscale Attention Variational Autoencoders (MSA-VAE), and critical regions are segmented using Semantic Invariant Multi-View Clustering (SIMVC). The Enhanced EfficientNet-Extended Multimodal (EEFN-XM) model extracts and fuses image and gait features, while HybPS-GWO optimizes classification weights. The system classifies subjects into early-stage PD, advanced-stage PD, and healthy controls (HCs). Ablation analysis confirms the hybrid optimizer's contribution to performance gains. The proposed model achieved 99.2% accuracy with stratified 5-fold cross-validation, outperforming DMFEN-PDC, MMT-CA-PDC, and LSTM-PDD-GS by 7.3%, 15.97%, and 10.43%, respectively, and reduced execution time by 33.33%. EEFN-XM-PDC-HybPS-GWO demonstrates superior accuracy, computational efficiency, and clinical relevance, particularly in early-stage diagnosis and PD classification.

<i>Objective.</i>Alzheimer's disease (AD) is the most prevalent form of dementia worldwide, encompassing a prodromal stage known as mild cognitive impairment (MCI), where patients may either progress to AD or remain stable. The objective of the work was to capture structural and functional modulations of brain structure and function relying on multimodal MRI data and single nucleotide polymorphisms, also in case of missing views, with the twofold goal of classifying AD patients versus healthy controls and detecting MCI converters.<i>Approach.</i>We propose a multimodal deep learning (DL)-based classification framework where a generative module employing cycle generative adversarial networks was introduced in the latent space for imputing missing data (a common issue of multimodal approaches). Explainable AI method was then used to extract input features' relevance allowing for post-hoc validation and enhancing the interpretability of the learned representations.<i>Main results.</i>Experimental results on two tasks, AD detection and MCI conversion, showed that our framework reached competitive performance in the state-of-the-art with an accuracy of0.926±0.02(CI [0.90, 0.95]) and0.711±0.01(CI [0.70, 0.72]) in the two tasks, respectively. The interpretability analysis revealed gray matter modulations in cortical and subcortical brain areas typically associated with AD. Moreover, impairments in sensory-motor and visual resting state networks along the disease continuum, as well as genetic mutations defining biological processes linked to endocytosis, amyloid-beta, and cholesterol, were identified.<i>Significance.</i>Our integrative and interpretable DL approach shows promising performance for AD detection and MCI prediction while shedding light on important biological insights.

Diabetic retinopathy is a leading cause of vision loss, necessitating early, accurate detection. Automated deep learning models show promise but struggle with the complexity of retinal images and limited labeled data. Due to domain differences, traditional transfer learning from datasets like ImageNet often fails in medical imaging. Self-supervised learning (SSL) offers a solution by enabling models to learn directly from medical data, but its success depends on the backbone architecture. Convolutional Neural Networks (CNNs) focus on local features, which can be limiting. To address this, we propose the Multi-scale Self-Supervised Learning (MsSSL) model, combining Vision Transformers (ViTs) for global context and CNNs with a Feature Pyramid Network (FPN) for multi-scale feature extraction. These features are refined through a Deep Learner module, improving spatial resolution and capturing high-level and fine-grained information. The MsSSL model significantly enhances DR grading, outperforming traditional methods, and underscores the value of domain-specific pretraining and advanced model integration in medical imaging.

This study aims to develop and assess an optimized three-dimensional convolutional neural network model (3D CNN) for predicting major cardiac events from coronary computed tomography angiography (CCTA) images in patients with suspected coronary artery disease. Patients undergoing CCTA with suspected coronary artery disease (CAD) were retrospectively included in this single-center study and split into training and test sets. The endpoint was defined as a composite of all-cause death, myocardial infarction, unstable angina, or revascularization events. Cardiovascular risk assessment relied on Morise score and the extent of CAD (eoCAD). An optimized 3D CNN mimicking the DenseNet architecture was trained on CCTA images to predict the clinical endpoints. The data was unannotated for presence of coronary plaque. A total of 5562 patients were assigned to the training group (66.4% male, median age 61.1 ± 11.2); 714 to the test group (69.3% male, 61.5 ± 11.4). Over a 7.2-year follow-up, the composite endpoint occurred in 760 training group and 83 test group patients. In the test cohort, the CNN achieved an AUC of 0.872 ± 0.020 for predicting the composite endpoint. The predictive performance improved in a stepwise manner: from an AUC of 0.652 ± 0.031 while using Morise score alone to 0.901 ± 0.016 when adding eoCAD and finally to 0.920 ± 0.015 when combining Morise score, eoCAD, and CNN (p < 0.001 and p = 0.012, respectively). Deep learning-based analysis of CCTA images improves prognostic risk stratification when combined with clinical and imaging risk factors in patients with suspected CAD.

Carotid atherosclerosis is a key predictor of cardiovascular disease (CVD), necessitating early detection. While foundation models (FMs) show promise in medical imaging, their optimal selection and fine-tuning strategies for classifying carotid atherosclerosis from retinal images remain unclear. Using data from 39,620 individuals, we evaluated four vision FMs with three fine-tuning methods. Performance was evaluated by predictive performance, clinical utility by survival analysis for future CVD mortality, and explainability by Grad-CAM with vessel segmentation. DINOv2 with low-rank adaptation showed the best overall performance (area under the receiver operating characteristic curve = 0.71; sensitivity = 0.87; specificity = 0.44), prognostic relevance (hazard ratio = 2.20, P-trend < 0.05), and vascular alignment. While further external validation on a broader clinical context is necessary to improve the model's generalizability, these findings support the feasibility of opportunistic atherosclerosis and CVD screening using retinal imaging and highlight the importance of a multi-dimensional evaluation framework for optimal FM selection in medical artificial intelligence.

While deep convolutional neural networks (DCNNs) have achieved remarkable performance in chest X-ray interpretation, their success typically depends on access to large-scale, expertly annotated datasets. However, collecting such data in real-world clinical settings can be difficult because of limited labeling resources, privacy concerns, and patient variability. In this study, we applied a multimodal Transformer pretrained on free-text reports and their paired CXRs to evaluate the effectiveness of this method in settings with limited labeled data. Our dataset consisted of more than 1 million CXRs, each accompanied by reports from board-certified radiologists and 31 structured labels. The results indicated that a linear model trained on embeddings from the pretrained model achieved AUCs of 0.907 and 0.903 on internal and external test sets, respectively, using only 128 cases and 384 controls; the results were comparable those of DenseNet trained on the entire dataset, whose AUCs were 0.908 and 0.903, respectively. Additionally, we demonstrated similar results by extending the application of this approach to a subset annotated with structured echocardiographic reports. Furthermore, this multimodal model exhibited excellent small sample learning capabilities when tested on external validation sets such as CheXpert and ChestX-ray14. This research significantly reduces the sample size necessary for future artificial intelligence advancements in CXR interpretation.