从半结构冠状动脉CT血管学报告中提取CAD-RADS 2.0的大型语言模型:多机构研究
Dabin Min1,2, Kwang Nam Jin3,4, SangHeum Bang3
1Interdisciplinary Program in Bioengineering, Seoul National University Graduate School, Seoul, Republic of Korea.
Korean journal of radiology
|August 28, 2025
概括
大型语言模型 (LLM) 准确地从冠状动脉CT血管学 (CCTA) 报告中提取冠状动脉疾病报告和数据系统 (CAD-RADS) 的组件. 在CAD-RADS 2.0数据提取过程中提升了LLM的准确性.
科学领域:
- 医疗信息学
- 放射学中的人工智能
- 心血管成像
背景情况:
- 冠状动脉扫描 (CCTA) 报告包含诊断冠状动脉疾病 (CAD) 的关键数据.
- 冠状动脉疾病报告和数据系统 (CAD-RADS) 标准化了CCTA发现的报告.
- 自动提取CAD-RADS组件可以简化工作流程并提高数据的一致性.
研究的目的:
- 评估各种大型语言模型 (LLM) 从CCTA报告中提取CAD-RADS 2.0组件的准确性.
- 评估各种促使策略,包括思维链 (CoT),对LLM绩效的影响.
- 在多机构数据集上比较多个LLM的性能.
主要方法:
- 一个由319个综合性,半结构化的CCTA报告组成的多机构数据集.
- 对CAD-RADS 2.0组件 (狭窄症严重程度,斑块负担,修饰剂) 的参考标准由经过认证的放射科医生制定.
- 使用零射击,少数射击和Cot提示策略评估了六种LLM.
- 使用McNemar的测试进行统计比较.
主要成果:
- 在提取所有CAD- RADS 2.0组件时,LLM表现出高精度,峰值狭窄度的精度高达0. 980 (内部) 和0. 946 (外部).
- 斑块负荷提取实现了近乎完美的精度 (外部最高为0. 993), 修饰剂检测率始终高 (≥0. 990).
- 连锁思维 (CoT) 促使几个模型的精度显著提高,特别是GPT-4,在狭窄严重程度上提高了0.192.
结论:
- 大型语言模型显示出从CCTA报告中精确自动提取CAD-RADS 2.0组件的巨大潜力.
- 使用思维链提示是提高LLM在此任务中的关键策略.
- 这些发现支持将LLM整合到放射学工作流程中,以提高效率和数据标准化.
更多相关视频
06:59Improved Registration of 3D CT Angiography with X-ray Fluoroscopy for Image Fusion During Transcatheter Aortic Valve Implantation
Published on: June 3, 2018
10.7K
09:57Development and Evaluation of 3D-Printed Cardiovascular Phantoms for Interventional Planning and Training
Published on: January 18, 2021
4.2K
相关概念视频
Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
119
Calcium-Scoring CT ScanA calcium-scoring CT scan, also known as coronary artery calcium (CAC) scan, detects calcium deposits in the coronary arteries. This test assesses the risk of coronary artery disease (CAD), which can lead to cardiovascular events such as angina, heart failure, and sudden cardiac arrest.A calcium-scoring CT scan is generally recommended for individuals at intermediate risk of CAD without symptoms. It includes:Men aged 40-75 and women aged 50-75: Especially those with a...
119
Imaging Studies for Cardiovascular System V: CT
66
Cardiac computed tomography (CT) scanning is an advanced cardiac imaging technique that utilizes CT technology, with or without intravenous (IV) contrast, to produce accurate cross-sectional virtual slices of specific areas of the heart, coronary circulation, and major blood vessels such as the aorta, pulmonary veins, and arteries. The computer processes these slices to generate three-dimensional images. Multidetector CT (MDCT) is a rapid form of CT scanning that captures multiple slices...
66
