In recent years, lung function assessment has attracted increasing attention in the perioperative management of thoracic surgery. However, traditional pulmonary function testing methods remain limited in clinical practice due to high equipment requirements and complex procedures. With the rapid development of artificial intelligence (AI) technology, lung function assessment based on multimodal chest imaging (such as X-rays, CT, and MRI) has become a new research focus. Through deep learning algorithms, AI models can accurately extract imaging features of patients and have made significant progress in quantitative analysis of pulmonary ventilation, evaluation of diffusion capacity, measurement of lung volumes, and prediction of lung function decline. Previous studies have demonstrated that AI models perform well in predicting key indicators such as forced expiratory volume in one second (FEV1), diffusing capacity for carbon monoxide (DLCO), and total lung capacity (TLC). Despite these promising prospects, challenges remain in clinical translation, including insufficient data standardization, limited model interpretability, and the lack of prediction models for postoperative complications. In the future, greater emphasis should be placed on multicenter collaboration, the construction of high-quality databases, the promotion of multimodal data integration, and clinical validation to further enhance the application value of AI technology in precision decision-making for thoracic surgery.

The validation of multimodal deep learning models for medical image translation is limited by the lack of high-quality, paired datasets. We propose a novel framework that leverages computational phantoms to generate realistic CT and MRI images, enabling reliable ground-truth datasets for robust validation of artificial intelligence (AI) methods that generate synthetic CT (sCT) from MRI, specifically for radiotherapy applications. Two CycleGANs (cycle-consistent generative adversarial networks) were trained to transfer the imaging style of real patients onto CT and MRI phantoms, producing synthetic data with realistic textures and continuous intensity distributions. These data were evaluated through paired assessments with original phantoms, unpaired comparisons with patient scans, and dosimetric analysis using patient-specific radiotherapy treatment plans. Additional external validation was performed on public CT datasets to assess the generalizability to unseen data. The resulting, paired CT/MRI phantoms were used to validate a GAN-based model for sCT generation from abdominal MRI in particle therapy, available in the literature. Results showed strong anatomical consistency with original phantoms, high histogram correlation with patient images (HistCC = 0.998 ± 0.001 for MRI, HistCC = 0.97 ± 0.04 for CT), and dosimetric accuracy comparable to real data. The novelty of this work lies in using generated phantoms as validation data for deep learning-based cross-modality synthesis techniques.

Sudden cardiac death (SCD) from ventricular arrhythmias (VAs) remains a leading cause of mortality worldwide. Traditional risk stratification, primarily based on left ventricular ejection fraction (LVEF) and other coarse metrics, often fails to identify a large subset of patients at risk and frequently leads to unnecessary device implantations. Advances in artificial intelligence (AI) offer new strategies to improve both long-term SCD risk prediction and near-term VAs forecasting. In this review, we discuss how AI algorithms applied to the 12-lead electrocardiogram (ECG) can identify subtle risk markers in conditions such as hypertrophic cardiomyopathy (HCM), arrhythmogenic right ventricular cardiomyopathy (ARVC), and coronary artery disease (CAD), often outperforming conventional risk models. We also explore the integration of AI with cardiac imaging, such as scar quantification on cardiac magnetic resonance (CMR) and fibrosis mapping, to enhance the identification of the arrhythmogenic substrate. Furthermore, we investigate the application of data from implantable cardioverter-defibrillators (ICDs) and wearable devices to predict ventricular tachycardia (VT) or ventricular fibrillation (VF) events before they occur, thereby advancing care toward real-time prevention. Amid these innovations, we address the medicolegal and ethical implications of AI-driven automated alerts in arrhythmia care, highlighting when clinicians can trust AI predictions. Future directions include multimodal AI fusion to personalise SCD risk assessment, as well as AI-guided VT ablation planning through imaging-based digital heart models. This review provides a comprehensive overview for general medical readers, focusing on peer-reviewed advances globally in the emerging intersection of AI, VAs, and SCD prevention.

Interstitial lung disease (ILD) is a leading cause of morbidity and mortality in systemic sclerosis (SSc). Chest computed tomography (CT) is the primary imaging modality for diagnosing and monitoring lung complications in SSc patients. However, its role in disease progression and mortality prediction has not yet been fully clarified. This study introduces a novel, large-scale longitudinal chest CT analysis framework that utilizes radiomics and deep learning to predict mortality associated with lung complications of SSc. We collected and analyzed 2,125 CT scans from SSc patients enrolled in the Northwestern Scleroderma Registry, conducting mortality analyses at one, three, and five years using advanced imaging analysis techniques. Death labels were assigned based on recorded deaths over the one-, three-, and five-year intervals, confirmed by expert physicians. In our dataset, 181, 326, and 428 of the 2,125 CT scans were from patients who died within one, three, and five years, respectively. Using ResNet-18, DenseNet-121, and Swin Transformer we use pre-trained models, and fine-tuned on 2,125 images of SSc patients. Models achieved an AUC of 0.769, 0.801, 0.709 for predicting mortality within one-, three-, and five-years, respectively. Our findings highlight the potential of both radiomics and deep learning computational methods to improve early detection and risk assessment of SSc-related interstitial lung disease, marking a significant advancement in the literature.

Convolutional Neural Networks have become a cornerstone of medical image analysis due to their proficiency in learning hierarchical spatial features. However, this focus on a single domain is inefficient at capturing global, holistic patterns and fails to explicitly model an image's frequency-domain characteristics. To address these challenges, we propose the Spatial-Spectral Summarizer Fusion Network (S$^3$F-Net), a dual-branch framework that learns from both spatial and spectral representations simultaneously. The S$^3$F-Net performs a fusion of a deep spatial CNN with our proposed shallow spectral encoder, SpectraNet. SpectraNet features the proposed SpectralFilter layer, which leverages the Convolution Theorem by applying a bank of learnable filters directly to an image's full Fourier spectrum via a computation-efficient element-wise multiplication. This allows the SpectralFilter layer to attain a global receptive field instantaneously, with its output being distilled by a lightweight summarizer network. We evaluate S$^3$F-Net across four medical imaging datasets spanning different modalities to validate its efficacy and generalizability. Our framework consistently and significantly outperforms its strong spatial-only baseline in all cases, with accuracy improvements of up to 5.13%. With a powerful Bilinear Fusion, S$^3$F-Net achieves a SOTA competitive accuracy of 98.76% on the BRISC2025 dataset. Concatenation Fusion performs better on the texture-dominant Chest X-Ray Pneumonia dataset, achieving 93.11% accuracy, surpassing many top-performing, much deeper models. Our explainability analysis also reveals that the S$^3$F-Net learns to dynamically adjust its reliance on each branch based on the input pathology. These results verify that our dual-domain approach is a powerful and generalizable paradigm for medical image analysis.

Fracture detection plays a critical role in medical imaging analysis, traditional fracture diagnosis relies on visual assessment by experienced physicians, however the speed and accuracy of this approach are constrained by the expertise. With the rapid advancements in artificial intelligence, deep learning models based on the YOLO framework have been widely employed for fracture detection, demonstrating significant potential in improving diagnostic efficiency and accuracy. This study proposes an improved YOLO-based model, termed Fracture-YOLO, which integrates novel Critical-Region-Selector Attention (CRSelector) and Scale-Aware (ScA) heads to further enhance detection performance. Specifically, the CRSelector module utilizes global texture information to focus on critical features of fracture regions. Meanwhile, the ScA module dynamically adjusts the weights of features at different scales, enhancing the model's capacity to identify fracture targets at multiple scales. Experimental results demonstrate that, compared to the baseline model, Fracture-YOLO achieves a significant improvement in detection precision, with mAP50 and mAP50-95 increasing by 4 and 3, surpassing the baseline model and achieving state-of-the-art (SOTA) performance.

Non-contrast computed tomography (NCCT) is essential for rapid stroke diagnosis but is limited by low image contrast and signal to noise ratio. We address this challenge by leveraging DINOv3, a state-of-the-art self-supervised vision transformer, to generate powerful feature representations for a comprehensive set of stroke analysis tasks. Our evaluation encompasses infarct and hemorrhage segmentation, anomaly classification (normal vs. stroke and normal vs. infarct vs. hemorrhage), hemorrhage subtype classification (EDH, SDH, SAH, IPH, IVH), and dichotomized ASPECTS classification (<=6 vs. >6) on multiple public and private datasets. This study establishes strong benchmarks for these tasks and demonstrates the potential of advanced self-supervised models to improve automated stroke diagnosis from NCCT, providing a clear analysis of both the advantages and current constraints of the approach. The code is available at https://github.com/Zzz0251/DINOv3-stroke.

Accurate image registration is essential for downstream applications, yet current deep registration networks provide limited indications of whether and when their predictions are reliable. Existing uncertainty estimation strategies, such as Bayesian methods, ensembles, or MC dropout, require architectural changes or retraining, limiting their applicability to pretrained registration networks. Instead, we propose a test-time uncertainty estimation framework that is compatible with any pretrained networks. Our framework is grounded in the transformation equivariance property of registration, which states that the true mapping between two images should remain consistent under spatial perturbations of the input. By analyzing the variance of network predictions under such perturbations, we derive a theoretical decomposition of perturbation-based uncertainty in registration. This decomposition separates into two terms: (i) an intrinsic spread, reflecting epistemic noise, and (ii) a bias jitter, capturing how systematic error drifts under perturbations. Across four anatomical structures (brain, cardiac, abdominal, and lung) and multiple registration models (uniGradICON, SynthMorph), the uncertainty maps correlate consistently with registration errors and highlight regions requiring caution. Our framework turns any pretrained registration network into a risk-aware tool at test time, placing medical image registration one step closer to safe deployment in clinical and large-scale research settings.

Early and accurate diagnosis of Alzheimer Disease is critical for effective clinical intervention, particularly in distinguishing it from Mild Cognitive Impairment, a prodromal stage marked by subtle structural changes. In this study, we propose a hybrid deep learning ensemble framework for Alzheimer Disease classification using structural magnetic resonance imaging. Gray and white matter slices are used as inputs to three pretrained convolutional neural networks such as ResNet50, NASNet, and MobileNet, each fine tuned through an end to end process. To further enhance performance, we incorporate a stacked ensemble learning strategy with a meta learner and weighted averaging to optimally combine the base models. Evaluated on the Alzheimer Disease Neuroimaging Initiative dataset, the proposed method achieves state of the art accuracy of 99.21% for Alzheimer Disease vs. Mild Cognitive Impairment and 91.0% for Mild Cognitive Impairment vs. Normal Controls, outperforming conventional transfer learning and baseline ensemble methods. To improve interpretability in image based diagnostics, we integrate Explainable AI techniques by Gradient weighted Class Activation, which generates heatmaps and attribution maps that highlight critical regions in gray and white matter slices, revealing structural biomarkers that influence model decisions. These results highlight the frameworks potential for robust and scalable clinical decision support in neurodegenerative disease diagnostics.

BackgroundIncarceration is a leading driver of tuberculosis in Latin America. Active case-finding in prisons may reduce population-wide tuberculosis burden, but optimal strategies and cost-effectiveness remain uncertain. Methods and findingsUsing dynamic transmission models calibrated to Brazil, Colombia, and Peru, we simulated annual or biannual (twice-yearly) prison-wide screening, alone or combined with entry and exit screening from 2026-2035. We evaluated four algorithms: 1) symptom screening, 2) chest X-ray with computer-aided detection (CXR-CAD), 3) symptoms and CXR-CAD (follow-up testing if either is positive) and 4) GeneXpert Ultra with pooled sputum. Individuals screening positive then received individual Xpert. We projected impacts on within-prison and population-level tuberculosis incidence in 2035, along with discounted costs (2023 USD) and disability-adjusted life years (DALYs). Model projections showed that combined entry, exit, and biannual screening with CXR-CAD was highly impactful and cost-effective across countries, reducing tuberculosis incidence by 62-87% in prisons and 18-28% population-wide. Compared to only biannual CXR-CAD (the next best strategy), the incremental cost per DALY averted of adding entry and exit screening was $2984 (Brazil), $2925 (Colombia), and $645 (Peru). Adding symptom screening to CXR-CAD marginally increased benefit and was only cost-effective in Perus higher-incidence prisons. Biannual screening alone remained cost-effective at prison incidence levels well below national averages. In settings without CXR-CAD, pooled Xpert was an impactful, cost-effective alternative. ConclusionsThese modeling results support immediate national-level adoption of prison-wide tuberculosis screening twice-yearly and at entry and exit. Screening should begin with available methods while building capacity for CXR-CAD, the most cost-effective algorithm. AUTHOR SUMMARYO_ST_ABSWhy was this study done?C_ST_ABSO_LIIn Latin America, rising incarceration has fueled the tuberculosis epidemic, with extremely high infection rates among people deprived of liberty. These effects extend beyond prison walls, driving tuberculosis spread in outside communities. C_LIO_LIInterventions targeted to prisons may have an outsized impact on reducing tuberculosis in the broader population. C_LIO_LIThe World Health Organization strongly recommends systematic screening for tuberculosis in prisons, but there is little evidence on how often to screen, which methods to use, and whether these approaches are cost-effective across different country contexts. C_LI What did the researchers do and find?O_LIWe developed mathematical models using data from Brazil, Colombia, and Peru to simulate different prison-based tuberculosis screening strategies and project their health impacts and costs. C_LIO_LIWe compared prison-wide screening once or twice a year, screening at prison entry or exit, and combinations of these approaches. We also compared different screening methods using symptoms, chest X-ray with computer-aided detection (CXR-CAD), or pooled molecular testing (GeneXpert Ultra). C_LIO_LIThe models projected that combining entry, exit, and twice-yearly prison-wide screening with CXR-CAD would be highly impactful and cost-effective in all three countries. This strategy could substantially reduce tuberculosis in prisons and in the general population. C_LIO_LITwice-yearly prison-wide screening remained cost-effective even in prisons with much lower tuberculosis rates than national averages. C_LIO_LICXR-CAD was the optimal screening method, but pooled molecular testing was also impactful and cost-effective where CXR-CAD was not available. C_LI Implications of all the available evidenceO_LISystematic screening in prisons, twice-yearly and at entry and exit, is projected to be highly impactful and cost-effective across different settings in Latin America. C_LIO_LIThese findings support urgent adoption of intensive prison-based tuberculosis screening throughout the region, starting with the best available diagnostic tools while investing in CXR-CAD. C_LI