Medical Visual Question Answering
Also known as VQA
Overview
Medical visual question answering (MedVQA) asks models to interpret images such as X-rays, scans, pathology slides, and surgical videos in response to clinical questions, supporting tasks from finding specific abnormalities to integrating evidence across views or time. Common approaches adapt vision-language models with medical image-question datasets, while newer methods add region grounding, clinical knowledge, stepwise reasoning, or tools for measurements and image navigation. Benchmarks increasingly test spatial, temporal, multilingual, and multi-image reasoning, as well as whether answers actually depend on the visual evidence. A central challenge remains that high answer accuracy can coexist with shortcut use, hallucinations, poor calibration, or weak generalization across modalities and clinical settings.
Latest papers
183 papers8 papers in the last four weeks, down 58% on the four weeks before. 0.1% of all new papers.
Option-Aware Retrieval and Task-Specific VLM Adaptation for Medical VQA
STSG-VQA: Evidence-Grounded Temporal Question Answering from Surgical Spatio-Temporal Scene Graphs
A visual large language foundational model for medical image recognition using clinician-contributed online resources
Separating Capability from Confidence: Grounded Dual-State Calibration for GRPO-Trained Medical Vision-Language Models
MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering
MedQA-MM: Shortcuts Behind Medical Visual Reasoning
Candidate-Expanding Routing with Permutation-Stabilized Experts for Mixed-Format Medical VQA
SlideBank: A Persistent Hierarchical Evidence Bank for Consistent Whole-Slide Reasoning
Source-Dependent Deference in Medical Imaging Agents Under Falsified Findings: A Pilot Audit
PROVE: Proof-guided Regime-aware Operator Verification for Hallucination Detection in Medical Visual Question Answering
From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and Segmentation
[SEG] tokens within the MLLM's hidden states. Furthermore, a Reasoning-to-Visual (R2V) fusion mechanism is proposed to effectively inject these reasoning-aware features into a segmentation pipeline for accurate mask decoding. To facilitate this paradigm, we construct MedRAVS-13K, a comprehensive dataset comprising 13,824 expertly validated samples across four diverse imaging modalities. Extensive experiments demonstrate that MedREAL significantly outperforms state-of-the-arts, achieving 68.49% gIoU and 70.47% cIoU on benchmark evaluations. By generating evidence masks that are strictly consistent with textual diagnoses, MedREAL provides a robust, interpretable framework for reasoning-driven medical image analysis.