Interpretable medical image Visual Question Answering via multi-modal relationship graph learning

Xinyue Hu, Lin Gu, Kazuma Kobayashi, Liangchen Liu, Mengliang Zhang, Tatsuya Harada, Ronald M. Summers, Yingying Zhu

Abstract: Highlights•Construct a large medical dataset focusing on chest X-ray image analysis.•Use Large Language Models to extract the dataset.•Embed multi-relationship graphs to create visual question answering model.