Evaluating diagnostic content of AI-generated radiology reports of chest X-rays

计算机科学 标准化 任务(项目管理) 隐藏字幕 人工智能 词汇 质量(理念) 自然语言处理 深度学习 放射科 情报检索 医学物理学 机器学习 医学 图像(数学) 语言学 哲学 经济 管理 操作系统 认识论
作者
Zaheer Ud Din Babar,Twan van Laarhoven,Fabio Massimo Zanzotto,Elena Marchiori
出处
期刊:Artificial Intelligence in Medicine [Elsevier BV]
卷期号:116: 102075-102075 被引量:16
标识
DOI:10.1016/j.artmed.2021.102075
摘要

Radiology reports are of core importance for the communication between the radiologist and clinician. A computer-aided radiology report system can assist radiologists in this task and reduce variation between reports thus facilitating communication with the medical doctor or clinician. Producing a well structured, clear, and clinically well-focused radiology report is essential for high-quality patient diagnosis and care. Despite recent advances in deep learning for image caption generation, this task remains highly challenging in a medical setting. Research has mainly focused on the design of tailored machine learning methods for this task, while little attention has been devoted to the development of evaluation metrics to assess the quality of AI-generated documents. Conventional quality metrics for natural language processing methods like the popular BLEU score, provide little information about the quality of the diagnostic content of AI-generated radiology reports. In particular, because radiology reports often use standardized sentences, BLEU scores of generated reports can be high while they lack diagnostically important information. We investigate this problem and propose a new measure that quantifies the diagnostic content of AI-generated radiology reports. In addition, we exploit the standardization of reports by generating a sequence of sentences. That is, instead of using a dictionary of words, as current image captioning methods do, we use a dictionary of sentences. The assumption underlying this choice is that radiologists use a well-focused vocabulary of ‘standard’ sentences, which should suffice for composing most reports. As a by-product, a significant training speed-up is achieved compared to models trained on a dictionary of words. Overall, results of our investigation indicate that standard validation metrics for AI-generated documents are weakly correlated with the diagnostic content of the reports. Therefore, these measures should be not used as only validation metrics, and measures evaluating diagnostic content should be preferred in such a medical context.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Owen应助hhh采纳,获得10
刚刚
无花果应助阿费采纳,获得10
刚刚
1秒前
1秒前
欣慰的小甜瓜关注了科研通微信公众号
1秒前
Ran完成签到,获得积分20
2秒前
zxxzxx发布了新的文献求助10
2秒前
研友_VZG7GZ应助Kiosta采纳,获得10
2秒前
3秒前
东方不败完成签到 ,获得积分10
3秒前
3秒前
专注凝蝶发布了新的文献求助10
3秒前
3秒前
cyy完成签到 ,获得积分10
4秒前
kk发布了新的文献求助10
4秒前
虚幻谷波完成签到,获得积分10
4秒前
淳于穆发布了新的文献求助10
4秒前
4秒前
5秒前
yeyeming完成签到,获得积分10
5秒前
6秒前
玉米小胚发布了新的文献求助10
6秒前
6秒前
三横一竖完成签到,获得积分10
6秒前
悦耳怜珊发布了新的文献求助10
6秒前
才识姐姐完成签到,获得积分10
7秒前
7秒前
HKJ发布了新的文献求助10
8秒前
8秒前
YiyueChan完成签到,获得积分10
9秒前
9秒前
大个应助不太入门的脑筋采纳,获得10
9秒前
9秒前
SRQ完成签到,获得积分10
10秒前
孙茜完成签到 ,获得积分10
10秒前
ltc完成签到,获得积分10
10秒前
华仔应助最终幻想采纳,获得10
10秒前
10秒前
11秒前
11秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3969383
求助须知:如何正确求助?哪些是违规求助? 3514211
关于积分的说明 11172730
捐赠科研通 3249476
什么是DOI,文献DOI怎么找? 1794909
邀请新用户注册赠送积分活动 875441
科研通“疑难数据库(出版商)”最低求助积分说明 804827