MRGAgents: A Multi-Agent Framework for Improved Medical Report Generation with Med-LVLMs

TL;DR

This paper introduces MRGAgents, a multi-agent framework that fine-tunes specialized models for different diseases, significantly improving the accuracy and comprehensiveness of medical reports generated from chest X-ray images.

Contribution

The paper presents a novel multi-agent approach with disease-specific agents to enhance medical report generation, addressing biases and improving diagnostic detail.

Findings

Outperforms state-of-the-art models in report quality.

Produces more comprehensive and diagnostically useful reports.

Effectively balances normal and abnormal findings.

Abstract

Medical Large Vision-Language Models (Med-LVLMs) have been widely adopted for medical report generation. Despite Med-LVLMs producing state-of-the-art performance, they exhibit a bias toward predicting all findings as normal, leading to reports that overlook critical abnormalities. Furthermore, these models often fail to provide comprehensive descriptions of radiologically relevant regions necessary for accurate diagnosis. To address these challenges, we proposeMedical Report Generation Agents (MRGAgents), a novel multi-agent framework that fine-tunes specialized agents for different disease categories. By curating subsets of the IU X-ray and MIMIC-CXR datasets to train disease-specific agents, MRGAgents generates reports that more effectively balance normal and abnormal findings while ensuring a comprehensive description of clinically relevant regions. Our experiments demonstrate that MRGAgents outperformed the state-of-the-art, improving both report comprehensiveness and diagnostic utility.