中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Benchmarking Radiology Report Generation From Noisy Free-Texts

文献类型：期刊论文

作者Yuan, Yujian3; Zheng, Yanting1; Qu, Liangqiong2
刊名IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
出版日期2025-10-01
卷号29期号:10页码:7549-7558
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
ISSN号2168-2194
DOI10.1109/JBHI.2025.3569428
英文摘要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.
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
语种英语
WOS记录号WOS:001590940200009
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/41658]  
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.Guangzhou Univ Chinese Med, Affiliated Hosp 1, Guangzhou 510405, Peoples R China
2.Univ Hong Kong, Hong Kong 999077, Peoples R China
3.Univ Chinese Acad Sci, Inst Comp Technol, Beijing 100190, 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.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。