Enhancing LLMs for Impression Generation in Radiology Reports through a Multi-Agent System
This addresses the need for more accurate and consistent radiology report generation for healthcare professionals, though it is incremental as it builds on existing multi-agent and LLM methods.
This study tackled the problem of generating impressions in radiology reports from findings by introducing RadCouncil, a multi-agent LLM framework, and showed improvements over single-agent approaches in diagnostic accuracy, stylistic concordance, and clarity using chest X-ray data.
This study introduces "RadCouncil," a multi-agent Large Language Model (LLM) framework designed to enhance the generation of impressions in radiology reports from the finding section. RadCouncil comprises three specialized agents: 1) a "Retrieval" Agent that identifies and retrieves similar reports from a vector database, 2) a "Radiologist" Agent that generates impressions based on the finding section of the given report plus the exemplar reports retrieved by the Retrieval Agent, and 3) a "Reviewer" Agent that evaluates the generated impressions and provides feedback. The performance of RadCouncil was evaluated using both quantitative metrics (BLEU, ROUGE, BERTScore) and qualitative criteria assessed by GPT-4, using chest X-ray as a case study. Experiment results show improvements in RadCouncil over the single-agent approach across multiple dimensions, including diagnostic accuracy, stylistic concordance, and clarity. This study highlights the potential of utilizing multiple interacting LLM agents, each with a dedicated task, to enhance performance in specialized medical tasks and the development of more robust and adaptable healthcare AI solutions.