Exploring Multimodal Large Language Models for Radiology Report Error-checking

作者
Jinge Wu,Yunsoo Kim,Eva C. Keller,Jamie Chow,Adam P. Levine,Nikolas Pontikos,Zina M. Ibrahim,Paul M. Taylor,Michelle Claire Williams,Honghan Wu
出处
期刊:Cornell University - arXiv [Cornell University]
被引量:10
标识
DOI:10.48550/arxiv.2312.13103
摘要

This paper proposes one of the first clinical applications of multimodal large language models (LLMs) as an assistant for radiologists to check errors in their reports. We created an evaluation dataset from real-world radiology datasets (including X-rays and CT scans). A subset of original reports was modified to contain synthetic errors by introducing three types of mistakes: "insert", "remove", and "substitute". The evaluation contained two difficulty levels: SIMPLE for binary error-checking and COMPLEX for identifying error types. At the SIMPLE level, our fine-tuned model significantly enhanced performance by 47.4% and 25.4% on MIMIC-CXR and IU X-ray data, respectively. This performance boost is also observed in unseen modality, CT scans, as the model performed 19.46% better than the baseline model. The model also surpassed the domain expert's accuracy in the MIMIC-CXR dataset by 1.67%. Notably, among the subsets (N=21) of the test set where a clinician did not achieve the correct conclusion, the LLaVA ensemble mode correctly identified 71.4% of these cases. However, all models performed poorly in identifying mistake types, underscoring the difficulty of the COMPLEX level. This study marks a promising step toward utilizing multimodal LLMs to enhance diagnostic accuracy in radiology. The ensemble model demonstrated comparable performance to clinicians, even capturing errors overlooked by humans.

科研通智能强力驱动
Strongly Powered by AbleSci AI
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
归途完成签到,获得积分10
1秒前
NexusExplorer的应助被zhangxinyi采纳,获得10
1秒前
周周发布了新的文献求助10
1秒前
科研通AI65的应助被ad采纳,获得10
1秒前
3秒前
Mickey完成签到 ,获得积分10
3秒前
abcd_1067完成签到,获得积分10
3秒前
不安的恶天完成签到,获得积分10
3秒前
顾矜的应助被小y同学采纳,获得10
3秒前
3秒前
minmin完成签到 ,获得积分10
4秒前
在水一方的应助被Eana采纳,获得10
5秒前
5秒前
5秒前
妮妮完成签到,获得积分10
5秒前
6秒前
大个的应助被科研通管家采纳,获得10
6秒前
Cr的应助被科研通管家采纳,获得10
6秒前
科研通AI2S的应助被临平吴彦祖采纳,获得10
6秒前
CipherSage的应助被科研通管家采纳,获得10
6秒前
sendou的应助被科研通管家采纳,获得30
6秒前
Jasper的应助被科研通管家采纳,获得10
6秒前
7秒前
yn107发布了新的文献求助10
7秒前
顾矜的应助被科研通管家采纳,获得10
7秒前
科研菜菜的应助被科研通管家采纳,获得30
7秒前
Eric完成签到,获得积分10
7秒前
7秒前
wanci的应助被科研通管家采纳,获得10
7秒前
英俊的铭的应助被科研通管家采纳,获得10
7秒前
上官若男的应助被科研通管家采纳,获得10
7秒前
脑洞疼的应助被科研通管家采纳,获得10
8秒前
Akim的应助被科研通管家采纳,获得10
8秒前
所所的应助被科研通管家采纳,获得10
8秒前
8秒前
Jasper的应助被科研通管家采纳,获得10
8秒前
Cr的应助被科研通管家采纳,获得10
8秒前
思源的应助被科研通管家采纳,获得10
8秒前
Orange的应助被xyt采纳,获得10
8秒前
Cr的应助被科研通管家采纳,获得10
8秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183508
求助须知:如何正确求助?哪些是违规求助? 9572862
关于积分的说明 21827639
捐赠科研通 7780681
什么是DOI,文献DOI怎么找? 3434016
关于科研通互助平台的介绍 2558189
邀请新用户注册赠送积分活动 2480405