CathAI: fully automated coronary angiography interpretation and stenosis estimation.

CathAI: fully automated coronary angiography interpretation and stenosis estimation.
复制标题

DOI:
10.1038/s41746-023-00880-1
复制
发表时间:
2023-08-11
影响因子:
15.2
通讯作者:
--
中科院分区:
医学1区
文献类型:
--
作者:

文献摘要

参考文献

相似文献

冠状动脉造影是冠状动脉疾病(CAD)诊断和管理决策的主要程序,但血管造影的临时视觉评估具有很高的可变性。在这里,我们报告了一种完全自动化的方法来解释标准冠状动脉血管造影中的冠状动脉狭窄。利用2008年4月1日至2019年12月31日期间来自加州大学旧金山分校(UCSF) 11,972名成年患者的13,843项血管造影研究,我们训练神经网络来完成自动冠状动脉狭窄定位和估计的四个顺序的必要任务。算法在内部针对hold out测试数据集中的每个任务的标准标签进行验证。然后,算法在渥太华大学心脏研究所(UOHI)的真实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)数据进行再训练。CathAI系统在非选择的真实血管造影中实现了最先进的性能。识别投影角度的阳性预测值、敏感性和F1评分均≥90%,左/右冠状动脉造影检测的阳性预测值、敏感性和F1评分均≥93%。用于预测阻塞性CAD狭窄(≥70%),CathAI的AUC为0.862 (95% CI: 0.843-0.880)。在UOHI外部验证中,CathAI预测阻塞性CAD的AUC达到0.869 (95% CI: 0.830-0.907)。在MHI QCA数据集中,CathAI实现了0.775(95%)的AUC。CI: 0.594-0.955)。综上所述,多个目的构建的神经网络可以依次完成真实血管造影的自动分析,可以提高血管造影冠状动脉狭窄评估的标准化和可重复性。
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.
DOI: 10.1016/j.cmpb.2020.105819
发表时间: 2021-01-01
影响因子: 6.1
作者:
Moon, Jong Hak;Lee, Da Young;Choi, Jin Ho
通讯作者: Choi, Jin Ho
DOI: 10.1016/j.jacc.2019.10.060
发表时间: 2020-02-04
影响因子: 24
作者:
Parikh, Rushi V.;Liu, Grace;Fearon, William F.
通讯作者: Fearon, William F.
DOI: 10.1016/s0895-4356(03)00177-x
发表时间: 2003-11-01
影响因子: 7.2
作者:
Glas, AS;Lijmer, JG;Bossuyt, PMM
通讯作者: Bossuyt, PMM
DOI: 10.1111/j.1540-8183.2009.00491.x
发表时间: 2009-12-01
影响因子: 2.1
作者:
Garrone, Paolo;Biondi-Zoccai, Giuseppe;Agostoni, Pierfrancesco
通讯作者: Agostoni, Pierfrancesco
DOI: 10.1038/s41598-021-97355-8
发表时间: 2021-09-10
期刊: Scientific reports
影响因子: 4.6
作者:
Iyer K;Najarian CP;Fattah AA;Arthurs CJ;Soroushmehr SMR;Subban V;Sankardas MA;Nadakuditi RR;Nallamothu BK;Figueroa CA
通讯作者: Figueroa CA