DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?
This work addresses the need for clinically trustworthy AI in medical imaging by providing a benchmark to evaluate reasoning, but it is incremental as it builds on existing VLM evaluation methods.
The authors tackled the problem of evaluating whether vision-language models reason like human doctors in medical image diagnosis, and found that performance drops sharply as reasoning complexity increases, with models often relying on shortcut correlations rather than grounded visual understanding.
Vision-language models (VLMs) exhibit strong zero-shot generalization on natural images and show early promise in interpretable medical image analysis. However, existing benchmarks do not systematically evaluate whether these models truly reason like human clinicians or merely imitate superficial patterns. To address this gap, we propose DrVD-Bench, the first multimodal benchmark for clinical visual reasoning. DrVD-Bench consists of three modules: Visual Evidence Comprehension, Reasoning Trajectory Assessment, and Report Generation Evaluation, comprising a total of 7,789 image-question pairs. Our benchmark covers 20 task types, 17 diagnostic categories, and five imaging modalities-CT, MRI, ultrasound, radiography, and pathology. DrVD-Bench is explicitly structured to reflect the clinical reasoning workflow from modality recognition to lesion identification and diagnosis. We benchmark 19 VLMs, including general-purpose and medical-specific, open-source and proprietary models, and observe that performance drops sharply as reasoning complexity increases. While some models begin to exhibit traces of human-like reasoning, they often still rely on shortcut correlations rather than grounded visual understanding. DrVD-Bench offers a rigorous and structured evaluation framework to guide the development of clinically trustworthy VLMs.