Avram Robert, Olgin Jeffrey E, Ahmed Zeeshan, Verreault-Julien Louis, Wan Alvin, Barrios Joshua, Abreau Sean, Wan Derek, Gonzalez Joseph E, Tardif Jean-Claude, So Derek Y, Soni Krishan, Tison Geoffrey H
Division of Cardiology, Department of Medicine, University of California, San Francisco, Cardiology, 505 Parnassus Avenue, San Francisco, CA, 94143, USA.
Division of Cardiology, Department of Medicine, Montreal Heart Institute - Université de Montréal, 5000 Rue Belanger, Montreal, QC, H1T 1C8, Canada.
NPJ Digit Med. 2023 Aug 11;6(1):142. doi: 10.1038/s41746-023-00880-1.
Coronary angiography is the primary procedure for diagnosis and management decisions in coronary artery disease (CAD), but ad-hoc visual assessment of angiograms has high variability. Here we report a fully automated approach to interpret angiographic coronary artery stenosis from standard coronary angiograms. Using 13,843 angiographic studies from 11,972 adult patients at University of California, San Francisco (UCSF), between April 1, 2008 and December 31, 2019, we train neural networks to accomplish four sequential necessary tasks for automatic coronary artery stenosis localization and estimation. Algorithms are internally validated against criterion-standard labels for each task in hold-out test datasets. Algorithms are then externally validated in real-world angiograms from the University of Ottawa Heart Institute (UOHI) and also retrained using quantitative coronary angiography (QCA) data from the Montreal Heart Institute (MHI) core lab. The CathAI system achieves state-of-the-art performance across all tasks on unselected, real-world angiograms. Positive predictive value, sensitivity and F1 score are all ≥90% to identify projection angle and ≥93% for left/right coronary artery angiogram detection. To predict obstructive CAD stenosis (≥70%), CathAI exhibits an AUC of 0.862 (95% CI: 0.843-0.880). In UOHI external validation, CathAI achieves AUC 0.869 (95% CI: 0.830-0.907) to predict obstructive CAD. In the MHI QCA dataset, CathAI achieves an AUC of 0.775 (95%. CI: 0.594-0.955) after retraining. In conclusion, multiple purpose-built neural networks can function in sequence to accomplish automated analysis of real-world angiograms, which could increase standardization and reproducibility in angiographic coronary stenosis assessment.
冠状动脉造影是冠心病（CAD）诊断和管理决策的主要手段，但造影血管造影的临时视觉评估具有高度变异性。在此，我们报告一种从标准冠状动脉造影解读冠状动脉狭窄的全自动方法。我们使用了2008年4月1日至2019年12月31日期间加利福尼亚大学旧金山分校（UCSF）11972名成年患者的13843项血管造影研究，训练神经网络完成自动冠状动脉狭窄定位和估计的四个连续必要任务。算法在保留测试数据集中针对每个任务的标准标准标签进行内部验证。然后，算法在渥太华大学心脏研究所（UOHI）的实际血管造影中进行外部验证，并使用蒙特利尔心脏研究所（MHI）核心实验室的定量冠状动脉造影（QCA）数据进行重新训练。CathAI系统在未选择的实际血管造影的所有任务中均实现了最先进的性能。阳性预测值、敏感性和F1分数在识别投影角度时均≥90%，在检测左/右冠状动脉造影时均≥93%。为了预测阻塞性CAD狭窄（≥70%），CathAI的曲线下面积（AUC）为0.862（95%置信区间：0.843-0.880）。在UOHI外部验证中，CathAI预测阻塞性CAD的AUC为0.869（95%置信区间：0.830-0.907）。在MHI QCA数据集中，重新训练后CathAI的AUC为0.775（95%置信区间：0.594-0.955）。总之，多个专用神经网络可以按顺序运行，以完成对实际血管造影的自动分析，这可以提高冠状动脉狭窄造影评估的标准化和可重复性。
