Lee June-Goo, Jun Tae Joon, Jeong Gyujun, Oh Hongmin, Kim Sijoon, Kang Heejun, Lee Jung Bok, Koo Hyun Jung, Lee Jong Eun, Kang Joon-Won, Ahn Yura, Lee Sang Min, Seo Joon Beom, Park Seong Ho, Cho Min Soo, Ahn Jung-Min, Park Duk-Woo, Kim Joon Bum, Kim Cherry, Suh Young Joo, Cho Iksung, van Assen Marly, De Cecco Carlo N, Chun Eun Ju, Kim Young-Hak, Yang Dong Hyun
Biomedical Engineering Research Center, Asan Institute for Life Sciences, Asan Medical Center, Seoul, South Korea.
Big Data Research Center, Asan Institute for Life Sciences, Asan Medical Center, Seoul, South Korea; (c)Department of Clinical Epidemiology and Biostatistics, Asan Medical Center, Seoul, South Korea.
JACC Adv. 2025 May;4(5):101687. doi: 10.1016/j.jacadv.2025.101687. Epub 2025 Apr 25.
The analysis of cardiovascular borders (CVBs) in chest x-rays (CXRs) traditionally relied on subjective assessment and does not have established normal ranges.
The authors aimed to develop a deep learning-based method for quantifying CVBs on CXRs and to explore its clinical utility.
This study used a prevalidated deep learning to analyze CVBs. A total of 96,129 normal CXRs from 4 sites were used to establish age- and sex-specific normal ranges of CVBs. The quantified CVBs were standardized into z-scores for newly inputted CXRs. The clinical utility of the z-score analysis was tested using 44,567 diseased CXRs from 3 sites (9,964 valve disease; 32,900 coronary artery disease; 1,299 congenital heart disease; 294 aortic aneurysm; 110 mediastinal mass).
For distinguishing valve disease from normal controls, the area under the receiver operating characteristic curve for the cardiothoracic ratio was 0.80 (95% CI: 0.80-0.80), while the combination of right atrium and left ventricle borders had an area under the receiver operating characteristic curve of 0.83 (95% CI: 0.83-0.83). Between mitral and aortic stenosis, z-scores of CVBs were significantly different in the left atrial appendage (1.54 vs 0.33, P < 0.001), carinal angle (1.10 vs 0.67, P < 0.001), and ascending aorta (0.63 vs 1.02, P < 0.001), reflecting disease pathophysiology. Cardiothoracic ratio was independently associated with a 5-year risk of death or myocardial infarction in the coronary artery disease (z-score ≥2, adjusted HR: 3.73 [95% CI: 2.09-6.64], reference z-score <-1).
Deep learning-derived z-score analysis of CXR showed potential in classifying and stratifying the risk of cardiovascular abnormalities.
传统上，胸部X光片（CXR）中心血管边界（CVB）的分析依赖主观评估，且尚无既定的正常范围。
作者旨在开发一种基于深度学习的方法来量化CXR上的CVB，并探索其临床效用。
本研究使用经过预验证的深度学习来分析CVB。来自4个地点的总共96,129张正常CXR用于建立CVB的年龄和性别特异性正常范围。将量化的CVB标准化为新输入CXR的z分数。使用来自3个地点的44,567张患病CXR（9,964例瓣膜病；32,900例冠状动脉疾病；1,299例先天性心脏病；294例主动脉瘤；110例纵隔肿块）测试z分数分析的临床效用。
为了区分瓣膜病与正常对照，心胸比率的受试者工作特征曲线下面积为0.80（95%CI：0.80-0.80），而右心房和左心室边界的组合在受试者工作特征曲线下面积为0.83（95%CI：0.83-0.83）。在二尖瓣狭窄和主动脉瓣狭窄之间，CVB的z分数在左心耳（1.54对0.33，P<0.001）、气管隆凸角（1.10对0.67，P<0.001）和升主动脉（0.63对1.02，P<0.001）上有显著差异，反映了疾病的病理生理学。在冠状动脉疾病中，心胸比率与5年死亡或心肌梗死风险独立相关（z分数≥2，调整后HR：3.73[95%CI：2.09-6.64]，参考z分数<-1）。
基于深度学习的CXR的z分数分析在心血管异常的分类和风险分层方面显示出潜力。
