CoMT: Chain-of-Medical-Thought Reduces Hallucination in Medical Report Generation

TL;DR

This paper introduces CoMT, a chain-of-medical-thought approach that mimics human diagnostic reasoning to reduce hallucinations and improve accuracy in automatic medical report generation.

Contribution

It proposes a novel structured reasoning method that decomposes diagnostic processes into medical thought chains, addressing hallucinations caused by data imbalance and limited medical data.

Findings

Reduces hallucinations in medical report generation.

Improves diagnostic accuracy of medical visual language models.

Enhances inferential reasoning in medical report synthesis.

Abstract

Automatic medical report generation (MRG), which possesses significant research value as it can aid radiologists in clinical diagnosis and report composition, has garnered increasing attention. Despite recent progress, generating accurate reports remains arduous due to the requirement for precise clinical comprehension and disease diagnosis inference. Furthermore, owing to the limited accessibility of medical data and the imbalanced distribution of diseases, the underrepresentation of rare diseases in training data makes large-scale medical visual language models (LVLMs) prone to hallucinations, such as omissions or fabrications, severely undermining diagnostic performance and further intensifying the challenges for MRG in practice. In this study, to effectively mitigate hallucinations in medical report generation, we propose a chain-of-medical-thought approach (CoMT), which intends to imitate the cognitive process of human doctors by decomposing diagnostic procedures. The radiological features with different importance are structured into fine-grained medical thought chains to enhance the inferential ability during diagnosis, thereby alleviating hallucination problems and enhancing the diagnostic accuracy of MRG. The code and dataset have been released at https://github.com/FRENKIE-CHIANG/CoMT.