Medical visual agents can use tools to inspect images and retrieve external knowledge, but indiscriminate tool use may introduce noisy or misleading evidence. Reliable diagnosis therefore requires not
While vision-language models dominate medical representation learning, unstructured text lacks the dense, quantitative diagnostic phenotypes inherent in structured clinical tables. However, existing m
Reliable medical image understanding requires models to connect clinical language and visual reasoning with pixel-level grounding. Yet medical vision-language models often lack precise localization, w
Surgical instrument segmentation is a fundamental task for computer-assisted interventions, yet most existing methods rely on pixel-level annotations or manual spatial prompts, which limit scalability
Despite significant advances in Medical Report Generation (MRG), the reliability remains constrained by the prevalence of factual errors. While Direct Preference Optimization (DPO) has emerged as a pr
Parameter-Efficient Fine-Tuning (PEFT) has become the de facto standard for adapting Vision Transformers (ViTs) to downstream tasks. While parameter count has been the dominant efficiency metric in PE
Cross-modal alignment of visual and textual representations is fundamental to multimodal medical image understanding, yet remains hindered by uncertainty in both modalities under real-world clinical c
Medical visual grounding connects free-form clinical queries to spatial evidence in medical images and is an important component of interpretable medical artificial intelligence. However, general-purp
Attention-based multiple instance learning (ABMIL) is the predominant approach for slide-level prediction in computational pathology, yet its attention maps provide only local explanations: they indic
Vision-language models (VLMs), including medical specialists, are increasingly proposed for medical imaging, yet their stated confidence is rarely evaluated separately from correctness. We use brain M
Recent vision-language models for chest X-ray understanding are largely built on image-report alignment and therefore rely heavily on MIMIC-CXR as the dominant pretraining source. While effective at s
Pulmonary nodule malignancy prediction typically depends on image-trained specialist deep learning (DL) models that require substantial annotated imaging data and task-specific training. We investigat
Automated radiology report generation is advancing rapidly in response to the shortage of radiologists, yet unlike a perception model, existing generation models offer no control over the sensitivity-
Public chest X-ray repositories are widely used to train medical AI systems, yet their labels are typically extracted from radiology reports rather than verified directly on images. As a result, repos
Vision-language models offer a promising path toward automating radiology report generation, but applying them to full 3D CT volumes poses substantial computational challenges. Modern foundation visio
Text-conditioned chest X-ray generation aims to synthesize realistic radiographs that faithfully depict specified findings. Existing work has primarily improved quality by updating image generators, i
Radiology reports describe clinical observations but do not specify executable segmentation targets. They may contain present, negated, prior,uncertain, or irrelevant findings, while multiple valid ab
Radiology reporting is time-consuming and subject to inter-rater variability, making automated report generation an attractive clinical application for Vision-Language Models (VLMs). We benchmark stat
Computed tomography (CT) is widely used for clinical diagnosis and longitudinal follow-up, yet automatically generating accurate and complete radiology reports from three-dimensional (3D) CT remains c
Vision-Language Models (VLMs) for radiology report generation are typically trained on retrospective clinical reports, which suffer from omission noise: clinically present findings are left unreported
A clinically useful chest X-ray system must go beyond fluent report generation: it should classify findings with tunable decision thresholds, localize them spatially, and derive the anatomical measure
Automatic radiology report generation (RRG) aims to simulate the workflow of radiologists, assisting them in clinical diagnosis. However, existing methods often fall short in utilizing all information
In previous work, we integrated large language models (LLMs) into the lesion segmentation model based on the ULS23 DeepLesion dataset, using short-form findings from the reports. In this study, we dev