OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM

TL;DR

OmniMedVQA introduces a large-scale, diverse medical VQA benchmark from 73 datasets to evaluate and improve LVLMs in real-world medical scenarios, revealing current models' limitations.

Contribution

This paper presents OmniMedVQA, the first comprehensive medical VQA benchmark covering multiple modalities and anatomical regions, sourced from authentic medical data.

Findings

Existing LVLMs perform poorly on medical VQA tasks.

Medical-specialized LVLMs underperform compared to general models.

The dataset highlights the need for more versatile LVLMs in medicine.

Abstract

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in various multimodal tasks. However, their potential in the medical domain remains largely unexplored. A significant challenge arises from the scarcity of diverse medical images spanning various modalities and anatomical regions, which is essential in real-world medical applications. To solve this problem, in this paper, we introduce OmniMedVQA, a novel comprehensive medical Visual Question Answering (VQA) benchmark. This benchmark is collected from 73 different medical datasets, including 12 different modalities and covering more than 20 distinct anatomical regions. Importantly, all images in this benchmark are sourced from authentic medical scenarios, ensuring alignment with the requirements of the medical field and suitability for evaluating LVLMs. Through our extensive experiments, we have found that existing LVLMs struggle to address these medical VQA problems effectively. Moreover, what surprises us is that medical-specialized LVLMs even exhibit inferior performance to those general-domain models, calling for a more versatile and robust LVLM in the biomedical field. The evaluation results not only reveal the current limitations of LVLM in understanding real medical images but also highlight our dataset's significance. Our code with dataset are available at https://github.com/OpenGVLab/Multi-Modality-Arena.