Foundation models have recently gained tremendous popularity in medical image analysis. State-of-the-art methods leverage either paired image-text data via vision-language pre-training or unpaired image data via self-supervised pre-training to learn foundation models with generalizable image features to boost downstream task performance. However, learning foundation models exclusively on either paired or unpaired image data limits their ability to learn richer and more comprehensive image features. In this paper, we investigate a novel task termed semi-supervised vision-language pre-training, aiming to fully harness the potential of both paired and unpaired image data for foundation model learning. To this end, we propose MaskedCLIP, a synergistic masked image modeling and contrastive language-image pre-training framework for semi-supervised vision-language pre-training. The key challenge in combining paired and unpaired image data for learning a foundation model lies in the incompatible feature spaces derived from these two types of data. To address this issue, we propose to connect the masked feature space with the CLIP feature space with a bridge transformer. In this way, the more semantic specific CLIP features can benefit from the more general masked features for semantic feature extraction. We further propose a masked knowledge distillation loss to distill semantic knowledge of original image features in CLIP feature space back to the predicted masked image features in masked feature space. With this mutually interactive design, our framework effectively leverages both paired and unpaired image data to learn more generalizable image features for downstream tasks. Extensive experiments on retinal image analysis demonstrate the effectiveness and data efficiency of our method.

In computed tomography (CT), achieving high image quality while minimizing radiation exposure remains a key clinical challenge. This paper presents CAPRI-CT, a novel causal-aware deep learning framework for Causal Analysis and Predictive Reasoning for Image Quality Optimization in CT imaging. CAPRI-CT integrates image data with acquisition metadata (such as tube voltage, tube current, and contrast agent types) to model the underlying causal relationships that influence image quality. An ensemble of Variational Autoencoders (VAEs) is employed to extract meaningful features and generate causal representations from observational data, including CT images and associated imaging parameters. These input features are fused to predict the Signal-to-Noise Ratio (SNR) and support counterfactual inference, enabling what-if simulations, such as changes in contrast agents (types and concentrations) or scan parameters. CAPRI-CT is trained and validated using an ensemble learning approach, achieving strong predictive performance. By facilitating both prediction and interpretability, CAPRI-CT provides actionable insights that could help radiologists and technicians design more efficient CT protocols without repeated physical scans. The source code and dataset are publicly available at https://github.com/SnehaGeorge22/capri-ct.

Unsupervised anomaly detection (UAD) plays a crucial role in neuroimaging for identifying deviations from healthy subject data and thus facilitating the diagnosis of neurological disorders. In this work, we focus on Bayesian flow networks (BFNs), a novel class of generative models, which have not yet been applied to medical imaging or anomaly detection. BFNs combine the strength of diffusion frameworks and Bayesian inference. We introduce AnoBFN, an extension of BFNs for UAD, designed to: i) perform conditional image generation under high levels of spatially correlated noise, and ii) preserve subject specificity by incorporating a recursive feedback from the input image throughout the generative process. We evaluate AnoBFN on the challenging task of Alzheimer's disease-related anomaly detection in FDG PET images. Our approach outperforms other state-of-the-art methods based on VAEs (beta-VAE), GANs (f-AnoGAN), and diffusion models (AnoDDPM), demonstrating its effectiveness at detecting anomalies while reducing false positive rates.

Automated X-ray inspection is crucial for efficient and unobtrusive security screening in various public settings. However, challenges such as object occlusion, variations in the physical properties of items, diversity in X-ray scanning devices, and limited training data hinder accurate and reliable detection of illicit items. Despite the large body of research in the field, reported experimental evaluations are often incomplete, with frequently conflicting outcomes. To shed light on the research landscape and facilitate further research, a systematic, detailed, and thorough comparative evaluation of recent Deep Learning (DL)-based methods for X-ray object detection is conducted. For this, a comprehensive evaluation framework is developed, composed of: a) Six recent, large-scale, and widely used public datasets for X-ray illicit item detection (OPIXray, CLCXray, SIXray, EDS, HiXray, and PIDray), b) Ten different state-of-the-art object detection schemes covering all main categories in the literature, including generic Convolutional Neural Network (CNN), custom CNN, generic transformer, and hybrid CNN-transformer architectures, and c) Various detection (mAP50 and mAP50:95) and time/computational-complexity (inference time (ms), parameter size (M), and computational load (GFLOPS)) metrics. A thorough analysis of the results leads to critical observations and insights, emphasizing key aspects such as: a) Overall behavior of the object detection schemes, b) Object-level detection performance, c) Dataset-specific observations, and d) Time efficiency and computational complexity analysis. To support reproducibility of the reported experimental results, the evaluation code and model weights are made publicly available at https://github.com/jgenc/xray-comparative-evaluation.

<b>BACKGROUND</b>. Coronary artery calcium (CAC) scoring is used to stratify acute coronary syndrome (ACS) risk. Nonetheless, patients with a CAC score of zero (CAC₀) remain at risk from noncalcified plaque components. <b>OBJECTIVE</b>. The purpose of this study was to explore CTA-derived coronary artery plaque characteristics in symptomatic patients with CAC₀ who subsequently have ACS through comparisons with patients with a CAC score greater than 0 (CAC_{> 0}) who subsequently have ACS as well as with patients with CAC₀ who do not subsequently have ACS. <b>METHODS</b>. This study entailed a secondary retrospective analysis of prior prospective registry data. The international multicenter CONFIRM (Coronary CT Angiography Evaluation for Clinical Outcomes: An International Multicenter) registry collected longitudinal observational data on symptomatic patients who underwent clinically indicated coronary CTA from January 2004 to May 2010. ICONIC (Incident Coronary Syndromes Identified by CT) was a nested cohort study conducted within CONFIRM that identified patients without known coronary artery disease (CAD) at the time of CTA who did and did not subsequently have ACS (i.e., the ACS and control groups, respectively) and who were propensity matched in a 1:1 ratio on the basis of CAD risk factors and CAD severity on CTA. The present ICONIC substudy selected matched patients in the ACS and control groups who both had documented CAC scores. CTA examinations were analyzed using artificial intelligence software for automated quantitative plaque assessment. In the ACS group, invasive angiography findings were used to identify culprit lesions. <b>RESULTS</b>. The present study included 216 patients (mean age, 55.6 years; 91 women and 125 men), with 108 patients in each of the ACS and control groups. In the ACS group, 23% (<i>n</i> = 25) of patients had CAC₀. In the ACS group, culprit lesions in the subsets of patients with CAC₀ and CAC_{> 0} showed no significant differences in fibrous, fibrofatty, or necrotic-core plaque volumes (<i>p</i> > .05). In the CAC₀ subset, patients with ACS, compared with control patients, had greater mean (± SD) fibrous plaque volume (29.4 ± 42.0 vs 5.5 ± 15.2 mm³, <i>p</i> < .001), fibrofatty plaque volume (27.3 ± 52.2 vs 1.3 ± 3.7 mm³, <i>p</i> < .001), and necrotic-core plaque volume (2.8 ± 6.4 vs 0.0 ± 0.1 mm³, <i>p</i> < .001). <b>CONCLUSION</b>. After propensity-score matching, 23% of patients with ACS had CAC₀. Patients with CAC₀ in the ACS and control groups showed significant differences in volumes of noncalcified plaque components. <b>CLINICAL IMPACT</b>. Methods that identify and quantify noncalcified plaque forms may help characterize ACS risk in symptomatic patients with CAC₀.

Breast cancer (BC) remains one of the leading causes of cancer-related mortality among women, despite recent advances in Computer-Aided Diagnosis (CAD) systems. Accurate and efficient interpretation of multi-view mammograms is essential for early detection, driving a surge of interest in Artificial Intelligence (AI)-powered CAD models. While state-of-the-art multi-view mammogram classification models are largely based on Transformer architectures, their computational complexity scales quadratically with the number of image patches, highlighting the need for more efficient alternatives. To address this challenge, we propose Mammo-Mamba, a novel framework that integrates Selective State-Space Models (SSMs), transformer-based attention, and expert-driven feature refinement into a unified architecture. Mammo-Mamba extends the MambaVision backbone by introducing the Sequential Mixture of Experts (SeqMoE) mechanism through its customized SecMamba block. The SecMamba is a modified MambaVision block that enhances representation learning in high-resolution mammographic images by enabling content-adaptive feature refinement. These blocks are integrated into the deeper stages of MambaVision, allowing the model to progressively adjust feature emphasis through dynamic expert gating, effectively mitigating the limitations of traditional Transformer models. Evaluated on the CBIS-DDSM benchmark dataset, Mammo-Mamba achieves superior classification performance across all key metrics while maintaining computational efficiency.

Recent advances in deep learning have led to robust automated tools for segmentation of abdominal computed tomography (CT). Meanwhile, segmentation of magnetic resonance imaging (MRI) is substantially more challenging due to the inherent signal variability and the increased effort required for annotating training datasets. Hence, existing approaches are trained on limited sets of MRI sequences, which might limit their generalizability. To characterize the landscape of MRI abdominal segmentation tools, we present here a comprehensive benchmarking of the three state-of-the-art and open-source models: MRSegmentator, MRISegmentator-Abdomen, and TotalSegmentator MRI. Since these models are trained using labor-intensive manual annotation cycles, we also introduce and evaluate ABDSynth, a SynthSeg-based model purely trained on widely available CT segmentations (no real images). More generally, we assess accuracy and generalizability by leveraging three public datasets (not seen by any of the evaluated methods during their training), which span all major manufacturers, five MRI sequences, as well as a variety of subject conditions, voxel resolutions, and fields-of-view. Our results reveal that MRSegmentator achieves the best performance and is most generalizable. In contrast, ABDSynth yields slightly less accurate results, but its relaxed requirements in training data make it an alternative when the annotation budget is limited. The evaluation code and datasets are given for future benchmarking at https://github.com/deepakri201/AbdoBench, along with inference code and weights for ABDSynth.

In recent years, advanced deep learning architectures have shown strong performance in medical imaging tasks. However, the traditional centralized learning paradigm poses serious privacy risks as all data is collected and trained on a single server. To mitigate this challenge, decentralized approaches such as federated learning and swarm learning have emerged, allowing model training on local nodes while sharing only model weights. While these methods enhance privacy, they struggle with heterogeneous and imbalanced data and suffer from inefficiencies due to frequent communication and the aggregation of weights. More critically, the dynamic and complex nature of clinical environments demands scalable AI systems capable of continuously learning from diverse modalities and multilabels. Yet, both centralized and decentralized models are prone to catastrophic forgetting during system expansion, often requiring full model retraining to incorporate new data. To address these limitations, we propose VGS-ATD, a novel distributed learning framework. To validate VGS-ATD, we evaluate it in experiments spanning 30 datasets and 80 independent labels across distributed nodes, VGS-ATD achieved an overall accuracy of 92.7%, outperforming centralized learning (84.9%) and swarm learning (72.99%), while federated learning failed under these conditions due to high requirements on computational resources. VGS-ATD also demonstrated strong scalability, with only a 1% drop in accuracy on existing nodes after expansion, compared to a 20% drop in centralized learning, highlighting its resilience to catastrophic forgetting. Additionally, it reduced computational costs by up to 50% relative to both centralized and swarm learning, confirming its superior efficiency and scalability.

In recent years, advanced deep learning architectures have shown strong performance in medical imaging tasks. However, the traditional centralized learning paradigm poses serious privacy risks as all data is collected and trained on a single server. To mitigate this challenge, decentralized approaches such as federated learning and swarm learning have emerged, allowing model training on local nodes while sharing only model weights. While these methods enhance privacy, they struggle with heterogeneous and imbalanced data and suffer from inefficiencies due to frequent communication and the aggregation of weights. More critically, the dynamic and complex nature of clinical environments demands scalable AI systems capable of continuously learning from diverse modalities and multilabels. Yet, both centralized and decentralized models are prone to catastrophic forgetting during system expansion, often requiring full model retraining to incorporate new data. To address these limitations, we propose VGS-ATD, a novel distributed learning framework. To validate VGS-ATD, we evaluate it in experiments spanning 30 datasets and 80 independent labels across distributed nodes, VGS-ATD achieved an overall accuracy of 92.7%, outperforming centralized learning (84.9%) and swarm learning (72.99%), while federated learning failed under these conditions due to high requirements on computational resources. VGS-ATD also demonstrated strong scalability, with only a 1% drop in accuracy on existing nodes after expansion, compared to a 20% drop in centralized learning, highlighting its resilience to catastrophic forgetting. Additionally, it reduced computational costs by up to 50% relative to both centralized and swarm learning, confirming its superior efficiency and scalability.

To investigate the risk factors associated with postoperative cement displacement following percutaneous kyphoplasty (PKP) in patients with osteoporotic vertebral compression fractures (OVCF) and to develop predictive models for clinical risk assessment. This retrospective study included 198 patients with OVCF who underwent PKP. Imaging and clinical variables were collected. Multiple machine learning models, including logistic regression, L1- and L2-regularized logistic regression, support vector machine (SVM), decision tree, gradient boosting, and random forest, were developed to predict cement displacement. L1- and L2-regularized logistic regression models identified four key risk factors: kissing spine (L1: 1.11; L2: 0.91), incomplete anterior cortex (L1: -1.60; L2: -1.62), low vertebral body CT value (L1: -2.38; L2: -1.71), and large Cobb change (L1: 0.89; L2: 0.87). The support vector machine (SVM) model achieved the best performance (accuracy: 0.983, precision: 0.875, recall: 1.000, F1-score: 0.933, specificity: 0.981, AUC: 0.997). Other models, including logistic regression, decision tree, gradient boosting, and random forest, also showed high performance but were slightly inferior to SVM. Key predictors of cement displacement were identified, and machine learning models were developed for risk assessment. These findings can assist clinicians in identifying high-risk patients, optimizing treatment strategies, and improving patient outcomes.