This study aims to develop and validate a multi-modal machine learning model for preoperative risk stratification in papillary thyroid carcinoma (PTC), addressing limitations of current systems that rely on postoperative pathological features. We analyzed 974 PTC patients from three medical centers in China using a multi-modal approach integrating: (1) clinical indicators, (2) immunological indices, (3) ultrasound radiomics features, and (4) CT radiomics features. Our methodology employed gradient boosting machine for feature selection and random forest for classification, with model interpretability provided through SHapley Additive exPlanations (SHAP) analysis. The model was validated on internal (n = 225) and two external cohorts (n = 51, n = 174). The final 15-feature model achieved AUCs of 0.91, 0.84, and 0.77 across validation cohorts, improving to 0.96, 0.95, and 0.89 after cohort-specific refitting. SHAP analysis revealed CT texture features, ultrasound morphological features, and immune-inflammatory markers as key predictors, with consistent patterns across validation sites despite center-specific variations. Subgroup analysis showed superior performance in tumors > 1 cm and patients without extrathyroidal extension. Our multi-modal machine learning approach provides accurate preoperative risk stratification for PTC with robust cross-center applicability. This computational framework for integrating heterogeneous imaging and clinical data demonstrates the potential of multi-modal joint learning in healthcare imaging to transform clinical decision-making by enabling personalized treatment planning.

<b><i>Objective:</i></b> Cardiovascular risk stratification based on traditional risk factors lacks precision at the individual level. While coronary artery calcium (CAC) scoring enhances risk prediction by detecting calcified atherosclerotic plaques, it may underestimate risk in individuals with noncalcified plaques-a pattern common in younger type 1 diabetes (T1D) patients. Understanding the prevalence of noncalcified atherosclerosis in T1D is crucial for developing more effective screening strategies. Therefore, this study aimed to assess the burden of clinically significant atherosclerosis in T1D patients with CAC <100 using artificial intelligence (AI)-guided quantitative coronary computed tomographic angiography (AI-QCT). <b><i>Methods:</i></b> This study enrolled T1D patients aged ≥30 years with disease duration ≥10 years and no manifest or symptomatic atherosclerotic cardiovascular disease (ASCVD). CAC and carotid ultrasound were assessed in all participants. AI-QCT was performed in patients with CAC 0 and at least one plaque in the carotid arteries or those with CAC 1-99. <b><i>Results:</i></b> Among the 167 participants (mean age 52 ± 10 years; 44% women; T1D duration 29 ± 11 years), 93 (56%) had CAC = 0, 46 (28%) had CAC 1-99, 8 (5%) had CAC 100-299, and 20 (12%) had CAC ≥300. AI-QCT was performed in a subset of 52 patients. Only 11 (21%) had no evidence of coronary artery disease. Significant coronary stenosis was identified in 17% of patients, and 30 (73%) presented with at least one high-risk plaque. Compared with CAC-based risk categories, AI-QCT reclassified 58% of patients, and 21% compared with the STENO1 risk categories. There was only fair agreement between AI-QCT and CAC (κ = 0.25), and a slight agreement between AI-QCT and STENO1 risk categories (κ = 0.02). <b><i>Conclusion:</i></b> AI-QCT may reveal subclinical atherosclerotic burden and high-risk features that remain undetected by traditional risk models or CAC. These findings challenge the assumption that a low CAC score equates to a low cardiovascular risk in T1D.

Accurate prediction of post-stroke language outcomes using machine learning offers the potential to enhance clinical treatment and rehabilitation for aphasic patients. This study of 758 English speaking stroke patients from the PLORAS project explores the impact of sample size on the performance of logistic regression and a deep learning (ResNet-18) model in predicting language outcomes from neuroimaging and impairment-relevant tabular data. We assessed the performance of both models on two key language tasks from the Comprehensive Aphasia Test: Spoken Picture Description and Naming, using a learning curve approach. Contrary to expectations, the simpler logistic regression model performed comparably or better than the deep learning model (with overlapping confidence intervals), with both models showing an accuracy plateau around 80% for sample sizes larger than 300 patients. Principal Component Analysis revealed that the dimensionality of the neuroimaging data could be reduced to as few as 20 (or even 2) dominant components without significant loss in accuracy, suggesting that classification may be driven by simple patterns such as lesion size. The study highlights both the potential limitations of current dataset size in achieving further accuracy gains and the need for larger datasets to capture more complex patterns, as some of our results indicate that we might not have reached an absolute classification performance ceiling. Overall, these findings provide insights into the practical use of machine learning for predicting aphasia outcomes and the potential benefits of much larger datasets in enhancing model performance.

Interstitial lung disease (ILD) prognostication incorporates clinical history, pulmonary function testing (PFTs), and chest CT pattern classifications. The machine learning classifier, Fibresolve, includes a model to help detect CT patterns associated with idiopathic pulmonary fibrosis (IPF). We developed and tested new Fibresolve software to predict outcomes in patients with ILD. Fibresolve uses a transformer (ViT) algorithm to analyze CT imaging that additionally embeds PFTs, age, and sex to produce an overall risk score. The model was trained to optimize risk score in a dataset of 602 subjects designed to maximize predictive performance via Cox proportional hazards. Validation was completed with the first hazard ratio assessment dataset, then tested in a second datatest set. 61 % of 220 subjects died in the validation set's study period, whereas 40 % of the 407 subjects died in the second dataset's. The validation dataset's mortality hazard ratio (HR) was 3.66 (95 % CI: 2.09-6.42) and 4.66 (CI: 2.47-8.77) for the moderate and high-risk groups. In the second dataset, Fibresolve was a predictor of mortality at initial visit, with a HR of 2.79 (1.73-4.49) and 5.82 (3.53-9.60) in the moderate and high-risk groups. Similar predictive performance was seen at follow-up visits, as well as with changes in the Fibresolve scores over sequential visits. Fibresolve predicts mortality by automatically assessing combined CT, PFTs, age, and sex into a ViT model. The new software algorithm affords accurate prognostication and demonstrates the ability to detect clinical changes over time.

Accurate estimation of intravoxel incoherent motion (IVIM) parameters from diffusion-weighted MRI remains challenging due to the ill-posed nature of the inverse problem and high sensitivity to noise, particularly in the perfusion compartment. In this work, we propose a probabilistic deep learning framework based on Deep Ensembles (DE) of Mixture Density Networks (MDNs), enabling estimation of total predictive uncertainty and decomposition into aleatoric (AU) and epistemic (EU) components. The method was benchmarked against non probabilistic neural networks, a Bayesian fitting approach and a probabilistic network with single Gaussian parametrization. Supervised training was performed on synthetic data, and evaluation was conducted on both simulated and two in vivo datasets. The reliability of the quantified uncertainties was assessed using calibration curves, output distribution sharpness, and the Continuous Ranked Probability Score (CRPS). MDNs produced more calibrated and sharper predictive distributions for the D and f parameters, although slight overconfidence was observed in D*. The Robust Coefficient of Variation (RCV) indicated smoother in vivo estimates for D* with MDNs compared to Gaussian model. Despite the training data covering the expected physiological range, elevated EU in vivo suggests a mismatch with real acquisition conditions, highlighting the importance of incorporating EU, which was allowed by DE. Overall, we present a comprehensive framework for IVIM fitting with uncertainty quantification, which enables the identification and interpretation of unreliable estimates. The proposed approach can also be adopted for fitting other physical models through appropriate architectural and simulation adjustments.

Magnetic Resonance Imaging (MRI) is widely utilized in medical imaging due to its high resolution and non-invasive nature. However, the prolonged acquisition time significantly limits its clinical applicability. Although traditional compressed sensing (CS) techniques can accelerate MRI acquisition, they often lead to degraded reconstruction quality under high undersampling rates. Deep learning-based methods, including CNN- and GAN-based approaches, have improved reconstruction performance, yet are limited by their local receptive fields, making it challenging to effectively capture long-range dependencies. Moreover, these models typically exhibit high computational complexity, which hinders their efficient deployment in practical scenarios. To address these challenges, we propose a lightweight Multi-scale Context-Aware Generative Adversarial Network (MCA-GAN), which enhances MRI reconstruction through dual-domain generators that collaboratively optimize both k-space and image-domain representations. MCA-GAN integrates several lightweight modules, including Depthwise Separable Local Attention (DWLA) for efficient local feature extraction, Adaptive Group Rearrangement Block (AGRB) for dynamic inter-group feature optimization, Multi-Scale Spatial Context Modulation Bridge (MSCMB) for multi-scale feature fusion in skip connections, and Channel-Spatial Multi-Scale Self-Attention (CSMS) for improved global context modeling. Extensive experiments conducted on the IXI, MICCAI 2013, and MRNet knee datasets demonstrate that MCA-GAN consistently outperforms existing methods in terms of PSNR and SSIM. Compared to SepGAN, the latest lightweight model, MCA-GAN achieves a 27.3% reduction in parameter size and a 19.6% reduction in computational complexity, while attaining the shortest reconstruction time among all compared methods. Furthermore, MCA-GAN exhibits robust performance across various undersampling masks and acceleration rates. Cross-dataset generalization experiments further confirm its ability to maintain competitive reconstruction quality, underscoring its strong generalization potential. Overall, MCA-GAN improves MRI reconstruction quality while significantly reducing computational cost through a lightweight architecture and multi-scale feature fusion, offering an efficient and accurate solution for accelerated MRI.

Brain tumors are a significant challenge to human health as they impair the proper functioning of the brain and the general quality of life, thus requiring clinical intervention through early and accurate diagnosis. Although current state-of-the-art deep learning methods have achieved remarkable progress, there is still a gap in the representation learning of tumor-specific spatial characteristics and the robustness of the classification model on heterogeneous data. In this paper, we introduce a novel Pyramidal Attention-Based bi-partitioned T Network (PABT-Net) that combines the hierarchical pyramidal attention mechanism and T-block based bi-partitioned feature extraction, and a self-convolutional dilated neural classifier as the final task. Such an architecture increases the discriminability of the space and decreases the false forecasting by adaptively focusing on informative areas in brain MRI images. The model was thoroughly tested on three benchmark datasets, Figshare Brain Tumor Dataset, Sartaj Brain MRI Dataset, and Br35H Brain Tumor Dataset, containing 7023 images labeled in four tumor classes: glioma, meningioma, no tumor, and pituitary tumor. It attained an overall classification accuracy of 99.12%, a mean cross-validation accuracy of 98.77%, a Jaccard similarity index of 0.986, and a Cohen's Kappa value of 0.987, indicating superb generalization and clinical stability. The model's effectiveness is also confirmed by tumor-wise classification accuracies: 96.75%, 98.46%, and 99.57% in glioma, meningioma, and pituitary tumors, respectively. Comparative experiments with the state-of-the-art models, including VGG19, MobileNet, and NASNet, were carried out, and ablation studies proved the effectiveness of NASNet incorporation. To capture more prominent spatial-temporal patterns, we investigated hybrid networks, including NASNet with ANN, CNN, LSTM, and CNN-LSTM variants. The framework implements a strict nine-fold cross-validation procedure. It integrates a broad range of measures in its evaluation, including precision, recall, specificity, F1-score, AUC, confusion matrices, and the ROC analysis, consistent across distributions. In general, the PABT-Net model has high potential to be a clinically deployable, interpretable, state-of-the-art automated brain tumor classification model.

Medical imaging, particularly retinal fundus photography, plays a crucial role in early disease detection and treatment for various ocular disorders. However, the development of robust diagnostic systems using deep learning remains constrained by the scarcity of expertly annotated data, which is time-consuming and expensive. Self-Supervised Learning (SSL) has emerged as a promising solution, but existing models fail to effectively incorporate critical domain knowledge specific to retinal anatomy. This potentially limits their clinical relevance and diagnostic capability. We address this issue by introducing an anatomically aware SSL framework that strategically integrates domain expertise through specialized masking of vital retinal structures during pretraining. Our approach leverages vessel and optic disc segmentation maps to guide the SSL process, enabling the development of clinically relevant feature representations without extensive labeled data. The framework combines a Vision Transformer with dual-masking strategies and anatomically informed loss functions to preserve structural integrity during feature learning. Comprehensive evaluation across multiple datasets demonstrates our method's competitive performance in diverse retinal disease classification tasks, including diabetic retinopathy grading, glaucoma detection, age-related macular degeneration identification, and multi-disease classification. The evaluation results establish the effectiveness of anatomically-aware SSL in advancing automated retinal disease diagnosis while addressing the fundamental challenge of limited labeled medical data.

<i>"Just Accepted" papers have undergone full peer review and have been accepted for publication in <i>Radiology: Artificial Intelligence</i>. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content.</i> Purpose To develop and validate MRSegmentator, a retrospective cross-modality deep learning model for multiorgan segmentation of MRI scans. Materials and Methods This retrospective study trained MRSegmentator on 1,200 manually annotated UK Biobank Dixon MRI sequences (50 participants), 221 in-house abdominal MRI sequences (177 patients), and 1228 CT scans from the TotalSegmentator-CT dataset. A human-in-the-loop annotation workflow leveraged cross-modality transfer learning from an existing CT segmentation model to segment 40 anatomic structures. The model's performance was evaluated on 900 MRI sequences from 50 participants in the German National Cohort (NAKO), 60 MRI sequences from AMOS22 dataset, and 29 MRI sequences from TotalSegmentator-MRI. Reference standard manual annotations were used for comparison. Metrics to assess segmentation quality included Dice Similarity Coefficient (DSC). Statistical analyses included organ-and sequence-specific mean ± SD reporting and two-sided <i>t</i> tests for demographic effects. Results 139 participants were evaluated; demographic information was available for 70 (mean age 52.7 years ± 14.0 [SD], 36 female). Across all test datasets, MRSegmentator demonstrated high class wise DSC for well-defined organs (lungs: 0.81-0.96, heart: 0.81-0.94) and organs with anatomic variability (liver: 0.82-0.96, kidneys: 0.77-0.95). Smaller structures showed lower DSC (portal/splenic veins: 0.64-0.78, adrenal glands: 0.56-0.69). The average DSC on the external testing using NAKO data, ranged from 0.85 ± 0.08 for T2-HASTE to 0.91 ± 0.05 for in-phase sequences. The model generalized well to CT, achieving mean DSC of 0.84 ± 0.12 on AMOS CT data. Conclusion MRSegmentator accurately segmented 40 anatomic structures on MRI and generalized to CT; outperforming existing open-source tools. Published under a CC BY 4.0 license.

Reliable uncertainty quantification is crucial for trustworthy decision-making and the deployment of AI models in medical imaging. While prior work has explored the ability of neural networks to quantify predictive, epistemic, and aleatoric uncertainties using an information-theoretical approach in synthetic or well defined data settings like natural image classification, its applicability to real life medical diagnosis tasks remains underexplored. In this study, we provide an extensive uncertainty quantification benchmark for multi-label chest X-ray classification using the MIMIC-CXR-JPG dataset. We evaluate 13 uncertainty quantification methods for convolutional (ResNet) and transformer-based (Vision Transformer) architectures across a wide range of tasks. Additionally, we extend Evidential Deep Learning, HetClass NNs, and Deep Deterministic Uncertainty to the multi-label setting. Our analysis provides insights into uncertainty estimation effectiveness and the ability to disentangle epistemic and aleatoric uncertainties, revealing method- and architecture-specific strengths and limitations.