Ulas Bagci

Hongyi Pan, Gorkem Durak, Halil Ertugrul Aktas et al.

Publicly available full-field digital mammography (FFDM) datasets remain limited in size, clinical labels, and vendor diversity, which hinders the training of robust models. We present LUMINA, a curated, multi-vendor FFDM dataset that explicitly encodes acquisition energy and vendor metadata to expose clinically relevant appearance shifts that current benchmarks overlook. This innovative resource comprises 1824 images from 468 patients (960 benign, 864 malignant) with pathology-confirmed outcomes, BI-RADS assessments, and breast-density annotations. LUMINA spans six acquisition systems and both high- and low-energy styles, exposing vendor- and energy-driven appearance shifts. To reduce cross-vendor/energy drift while preserving lesion morphology, we introduce a foreground-only, pixel-space alignment (''energy harmonization'') that aligns each image to a low-energy reference style, leaving the zero-valued background unchanged. By benchmarking modern CNN and transformer baselines on three clinically meaningful tasks -- diagnosis (benign vs. malignant), BI-RADS risk grouping, and density -- we unify single-vs-two-view evaluation and show that two-view models consistently outperform single-view; in our benchmark, EfficientNet-B0 attains AUC 93.54% for diagnosis, and Swin-T yields the best macro-AUC 89.43% for density. Harmonization improves AUC/ACC across backbones and yields more focal Grad-CAM localization around suspicious regions. Being a richly annotated resource, LUMINA thus provides (a) a vendor-diverse, energy-labeled benchmark and (b) a model-agnostic harmonization protocol that together catalyze reliable, deployable mammography AI.

Yen-Linh Vu, Dinh-Thang Duong, Truong-Binh Duong et al.

Recent progress has been made in region-aware vision-language modeling, particularly with the emergence of the Describe Anything Model (DAM). DAM is capable of generating detailed descriptions of any specific image areas or objects without the need for additional localized image-text alignment supervision. We hypothesize that such region-level descriptive capability is beneficial for the task of Visual Question Answering (VQA), especially in challenging scenarios involving images with dense text. In such settings, the fine-grained extraction of textual information is crucial to producing correct answers. Motivated by this, we introduce DAM-QA, a framework with a tailored evaluation protocol, developed to investigate and harness the region-aware capabilities from DAM for the text-rich VQA problem that requires reasoning over text-based information within images. DAM-QA incorporates a mechanism that aggregates answers from multiple regional views of image content, enabling more effective identification of evidence that may be tied to text-related elements. Experiments on six VQA benchmarks show that our approach consistently outperforms the baseline DAM, with a notable 7+ point gain on DocVQA. DAM-QA also achieves the best overall performance among region-aware models with fewer parameters, significantly narrowing the gap with strong generalist VLMs. These results highlight the potential of DAM-like models for text-rich and broader VQA tasks when paired with efficient usage and integration strategies. Our code is publicly available at https://github.com/Linvyl/DAM-QA.git.

Ha-Hieu Pham, Nguyen Lan Vi Vu, Thanh-Huy Nguyen et al.

Accurate gland segmentation in histopathology images is essential for cancer diagnosis and prognosis. However, significant variability in Hematoxylin and Eosin (H&E) staining and tissue morphology, combined with limited annotated data, poses major challenges for automated segmentation. To address this, we propose Color-Structure Dual-Student (CSDS), a novel semi-supervised segmentation framework designed to learn disentangled representations of stain appearance and tissue structure. CSDS comprises two specialized student networks: one trained on stain-augmented inputs to model chromatic variation, and the other on structure-augmented inputs to capture morphological cues. A shared teacher network, updated via Exponential Moving Average (EMA), supervises both students through pseudo-labels. To further improve label reliability, we introduce stain-aware and structure-aware uncertainty estimation modules that adaptively modulate the contribution of each student during training. Experiments on the GlaS and CRAG datasets show that CSDS achieves state-of-the-art performance in low-label settings, with Dice score improvements of up to 1.2% on GlaS and 0.7% on CRAG at 5% labeled data, and 0.7% and 1.4% at 10%. Our code and pre-trained models are available at https://github.com/hieuphamha19/CSDS.

Jinkui Hao, Gorkem Durak, Halil Ertugrul Aktas et al.

Coronary artery disease, the leading cause of cardiovascular mortality worldwide, can be assessed non-invasively by coronary computed tomography angiography (CCTA). Despite progress in automated CCTA analysis using deep learning, clinical translation is constrained by the scarcity of expert-annotated datasets. Furthermore, widely adopted label-free pretraining strategies, such as masked image modeling, are intrinsically biased toward global anatomical statistics, frequently failing to capture the spatially localized pathological features of coronary plaques. Here, we introduce CORA, a 3D vision foundation model for comprehensive cardiovascular risk assessment. CORA learns directly from volumetric CCTA via a pathology-centric, synthesis-driven self-supervised framework. By utilizing an anatomy-guided lesion synthesis engine, the model is explicitly trained to detect simulated vascular abnormalities, biasing representation learning toward clinically relevant disease features rather than dominant background anatomy. We trained CORA on a large-scale cohort of 12,801 unlabeled CCTA volumes and comprehensively evaluated the model across multi-center datasets from nine independent hospitals. Across diagnostic and anatomical tasks, including plaque characterization, stenosis detection, and coronary artery segmentation, CORA consistently outperformed the state-of-the-art 3D vision foundation models, achieving up to a 29\% performance gain. Crucially, by coupling the imaging encoder with a large language model, we extended CORA into a multimodal framework that significantly improved 30-day major adverse cardiac event (MACE) risk stratification. Our results establish CORA as a scalable and extensible foundation for unified anatomical assessment and cardiovascular risk prediction.

Xinran Gong, Gorkem Durak, Halil Ertugrul Aktas et al.

Coronary artery calcium (CAC) scoring from chest CT is a well-established tool to stratify and refine clinical cardiovascular disease risk estimation. CAC quantification relies on the accurate delineation of calcified lesions, but is oftentimes affected by artifacts introduced by cardiac and respiratory motion. ECG-gated cardiac CTs substantially reduce motion artifacts, but their use in population screening and routine imaging remains limited due to gating requirements and lack of insurance coverage. Although identification of incidental CAC from non-gated chest CT is increasingly considered for it offers an accessible and widely available alternative, this modality is limited by more severe motion artifacts. We present ProDM (Property-aware Progressive Correction Diffusion Model), a generative diffusion framework that restores motion-free calcified lesions from non-gated CTs. ProDM introduces three key components: (1) a CAC motion simulation data engine that synthesizes realistic non-gated acquisitions with diverse motion trajectories directly from cardiac-gated CTs, enabling supervised training without paired data; (2) a property-aware learning strategy incorporating calcium-specific priors through a differentiable calcium consistency loss to preserve lesion integrity; and (3) a progressive correction scheme that reduces artifacts gradually across diffusion steps to enhance stability and calcium fidelity. Experiments on real patient datasets show that ProDM significantly improves CAC scoring accuracy, spatial lesion fidelity, and risk stratification performance compared with several baselines. A reader study on real non-gated scans further confirms that ProDM suppresses motion artifacts and improves clinical usability. These findings highlight the potential of progressive, property-aware frameworks for reliable CAC quantification from routine chest CT imaging.

Abhijit Das, Debesh Jha, Jasmer Sanjotra et al.

Foundational models (FMs) have tremendous potential to revolutionize medical imaging. However, their deployment in real-world clinical settings demands extensive ethical considerations. This paper aims to highlight the ethical concerns related to FMs and propose a framework to guide their responsible development and implementation within medicine. We meticulously examine ethical issues such as privacy of patient data, bias mitigation, algorithmic transparency, explainability and accountability. The proposed framework is designed to prioritize patient welfare, mitigate potential risks, and foster trust in AI-assisted healthcare.

Ngoc Bui Lam Quang, Nam Le Nguyen Binh, Thanh-Huy Nguyen et al.

Multiple Instance Learning (MIL) is the leading approach for whole slide image (WSI) classification, enabling efficient analysis of gigapixel pathology slides. Recent work has introduced vision-language models (VLMs) into MIL pipelines to incorporate medical knowledge through text-based class descriptions rather than simple class names. However, when these methods rely on large language models (LLMs) to generate clinical descriptions or use fixed-length prompts to represent complex pathology concepts, the limited token capacity of VLMs often constrains the expressiveness and richness of the encoded class information. Additionally, descriptions generated solely by LLMs may lack domain grounding and fine-grained medical specificity, leading to suboptimal alignment with visual features. To address these challenges, we propose a vision-language MIL framework with two key contributions: (1) A grounded multi-agent description generation system that leverages curated pathology textbooks and agent specialization (e.g., morphology, spatial context) to produce accurate and diverse clinical descriptions; (2) A text encoding strategy using a list of descriptions rather than a single prompt, capturing fine-grained and complementary clinical signals for better alignment with visual features. Integrated into a VLM-MIL pipeline, our approach shows improved performance over single-prompt class baselines and achieves results comparable to state-of-the-art models, as demonstrated on renal and lung cancer datasets.

Necip Enes Gengec, Ergin Tari, Ulas Bagci

This study presents an innovative approach for automatic road detection with deep learning, by employing fusion strategies for utilizing both lower-resolution satellite imagery and GPS trajectory data, a concept never explored before. We rigorously investigate both early and late fusion strategies, and assess deep learning based road detection performance using different fusion settings. Our extensive ablation studies assess the efficacy of our framework under diverse model architectures, loss functions, and geographic domains (Istanbul and Montreal). For an unbiased and complete evaluation of road detection results, we use both region-based and boundary-based evaluation metrics for road segmentation. The outcomes reveal that the ResUnet model outperforms U-Net and D-Linknet in road extraction tasks, achieving superior results over the benchmark study using low-resolution Sentinel-2 data. This research not only contributes to the field of automatic road detection but also offers novel insights into the utilization of data fusion methods in diverse applications.