Benchmarking Radiology Report Generation From Noisy Free-Texts

doi:10.1109/JBHI.2025.3569428

	Benchmarking Radiology Report Generation From Noisy Free-Texts
	Yuan, Yujian 1; Zheng, Yanting 2; Qu, Liangqiong 3
	2025-10-01
发表期刊	IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
ISSN	2168-2194
卷号	29 期号:10 页码:7549-7558
摘要	Automatic radiology report generation can enhance diagnostic efficiency and accuracy. However, clean open-source imaging scan-report pairs are limited in scale and variety. Moreover, the vast amount of radiological texts available online is often too noisy to be directly employed. To address this challenge, we introduce a novel task called Noisy Report Refinement (NRR), which generates radiology reports from noisy free-texts. To achieve this, we propose a report refinement pipeline that leverages large language models (LLMs) enhanced with guided self-critique and report selection strategies. To address the inability of existing radiology report generation metrics in measuring cleanliness, radiological usefulness, and factual correctness across various modalities of reports in NRR task, we introduce a new benchmark, NRRBench, for NRR evaluation. This benchmark includes two online-sourced datasets and four clinically explainable LLM-based metrics: two metrics evaluate the matching rate of radiology entities and modality-specific template attributes respectively, one metric assesses report cleanliness, and a combined metric evaluates overall NRR performance. Experiments demonstrate that guided self-critique and report selection strategies significantly improve the quality of refined reports. Additionally, our proposed metrics show a much higher correlation with noisy rate and error count of reports than radiology report generation metrics in evaluating NRR.
关键词	Noise measurement Radiology Measurement Benchmark testing Pipelines Large language models Biomedical imaging Training Bioinformatics Text processing Benchmark large language model (LLM) natural language processing radiology report generation
DOI	10.1109/JBHI.2025.3569428
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62306253] ; Guangdong Natural Science Fund-General Programme[2024A1515010233] ; Guangzhou Municipal Science and Technology Project[2023A04J1860]
WOS研究方向	Computer Science ; Mathematical & Computational Biology ; Medical Informatics
WOS类目	Computer Science, Information Systems ; Computer Science, Interdisciplinary Applications ; Mathematical & Computational Biology ; Medical Informatics
WOS记录号	WOS:001590940200009
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/41659
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Qu, Liangqiong
作者单位	1.Univ Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Guangzhou Univ Chinese Med, Affiliated Hosp 1, Guangzhou 510405, Peoples R China 3.Univ Hong Kong, Hong Kong 999077, Peoples R China
推荐引用方式 GB/T 7714	Yuan, Yujian,Zheng, Yanting,Qu, Liangqiong. Benchmarking Radiology Report Generation From Noisy Free-Texts[J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS,2025,29(10):7549-7558.
APA	Yuan, Yujian,Zheng, Yanting,&Qu, Liangqiong.(2025).Benchmarking Radiology Report Generation From Noisy Free-Texts.IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS,29(10),7549-7558.
MLA	Yuan, Yujian,et al."Benchmarking Radiology Report Generation From Noisy Free-Texts".IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 29.10(2025):7549-7558.