Enhancing LLMs for Impression Generation in Radiology Reports through a Multi-Agent System

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zeng, Fang, Lyu, Zhiliang, Li, Quanzheng, Li, Xiang
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912149851340800
author Zeng, Fang
Lyu, Zhiliang
Li, Quanzheng
Li, Xiang
author_facet Zeng, Fang
Lyu, Zhiliang
Li, Quanzheng
Li, Xiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06828
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing LLMs for Impression Generation in Radiology Reports through a Multi-Agent System
Zeng, Fang
Lyu, Zhiliang
Li, Quanzheng
Li, Xiang
Computation and Language
Artificial Intelligence
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.
title Enhancing LLMs for Impression Generation in Radiology Reports through a Multi-Agent System
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2412.06828