Deep learning-enabled coronary CT angiography for plaque and stenosis quantification and cardiac risk prediction: an international multicentre study.
Deep learning-enabled coronary CT angiography for plaque and stenosis quantification and cardiac risk prediction: an international multicentre study.
复制标题
基于深度学习的冠状动脉CT血管造影用于斑块和狭窄量化和心脏风险预测：一项国际多中心研究。
DOI：
10.1016/s2589-7500(22)00022-x
复制
发表时间：
2022-04
影响因子：
30.8
通讯作者：
Dey, Damini
中科院分区：
文献类型：
--
作者：
Lin, Andrew;Manral, Nipun;McElhinney, Priscilla;Killekar, Aditya;Matsumoto, Hidenari;Kwiecinski, Jacek;Pieszko, Konrad;Razipour, Aryabod;Grodecki, Kajetan;Park, Caroline;Otaki, Yuka;Doris, Mhairi;Kwan, Alan C.;Han, Donghee;Kuronuma, Keiichiro;Tomasino, Guadalupe Flores;Tzolos, Evangelos;Shanbhag, Aakash;Goeller, Markus;Marwan, Mohamed;Gransar, Heidi;Tamarappoo, Balaji K.;Cadet, Sebastien;Achenbach, Stephan;Nicholls, Stephen J.;Wong, Dennis T.;Berman, Daniel S.;Dweck, Marc;Newby, David E.;Williams, Michelle C.;Slomka, Piotr J.;Dey, Damini
冠状动脉 CT 血管造影 (CCTA) 的动脉粥样硬化斑块定量能够准确评估冠状动脉疾病负担和预后。我们寻求开发和验证深度学习系统，用于基于 CCTA 的斑块体积和狭窄严重程度测量。这项国际多中心研究包括在 11 个地点接受 CCTA 的 9 组患者，这些患者被分配到训练组和测试组。回顾性收集了 2010 年 11 月 18 日至 2019 年 1 月 25 日期间接受 CCTA 的各种冠状动脉疾病临床表现的患者的数据。训练了一种新型深度学习卷积神经网络来分割 921 名患者（5045 个病变）的冠状动脉斑块。然后将深度学习网络应用于一个独立的测试集，其中包括由 175 名患者（1081 个病灶）组成的外部验证队列和 50 名患者（84 个病灶）在 CCTA 1 个月内通过血管内超声评估的情况。我们评估了前瞻性 SCOT-HEART 试验中 1611 名患者基于深度学习的斑块测量对致命性或非致命性心肌梗死（我们的主要结果）的预后价值，使用多变量 Cox 回归分析作为二分变量进行评估，并调整 ASSIGN 临床风险评分。在整个测试集中，深度学习和专家读者测量的总斑块体积（组内相关系数 [ICC] 0·964）和直径狭窄百分比（ICC 0·879；均 p<0·0001）之间分别具有极好的或良好的一致性。与血管内超声相比，深度学习斑块总体积 (ICC 0·949) 和最小管腔面积 (ICC 0·904) 具有良好的一致性。每个患者的平均深度学习斑块分析时间为 5·65 秒 (SD 1·87)，而专家则为 25·66 分钟 (6·79)。在中位随访 4·7 年 (IQR 4·0–5·7) 中，SCOT-HEART 试验的 1611 名患者中有 41 名 (2·5%) 发生心肌梗死。在调整基于深度学习的阻塞性狭窄（HR 2·49、1·07–5·50；p=0·0089）和 ASSIGN 后，基于深度学习的总斑块体积为 238·5 mm3 或更高与心肌梗死风险增加相关（风险比 [HR] 5·36，95% CI 1·70–16·86；p=0·0042）临床风险评分（HR 1·01、0·99–1·04；p=0·35）。我们新颖的、经过外部验证的深度学习系统可通过 CCTA 快速测量斑块体积和狭窄严重程度，与专家读者和血管内超声密切一致，并且可能对未来心肌梗死具有预后价值。
Atherosclerotic plaque quantification from coronary CT angiography (CCTA) enables accurate assessment of coronary artery disease burden and prognosis. We sought to develop and validate a deep learning system for CCTA-derived measures of plaque volume and stenosis severity. This international, multicentre study included nine cohorts of patients undergoing CCTA at 11 sites, who were assigned into training and test sets. Data were retrospectively collected on patients with a wide range of clinical presentations of coronary artery disease who underwent CCTA between Nov 18, 2010, and Jan 25, 2019. A novel deep learning convolutional neural network was trained to segment coronary plaque in 921 patients (5045 lesions). The deep learning network was then applied to an independent test set, which included an external validation cohort of 175 patients (1081 lesions) and 50 patients (84 lesions) assessed by intravascular ultrasound within 1 month of CCTA. We evaluated the prognostic value of deep learning-based plaque measurements for fatal or non-fatal myocardial infarction (our primary outcome) in 1611 patients from the prospective SCOT-HEART trial, assessed as dichotomous variables using multivariable Cox regression analysis, with adjustment for the ASSIGN clinical risk score. In the overall test set, there was excellent or good agreement, respectively, between deep learning and expert reader measurements of total plaque volume (intraclass correlation coefficient [ICC] 0·964) and percent diameter stenosis (ICC 0·879; both p<0·0001). When compared with intravascular ultrasound, there was excellent agreement for deep learning total plaque volume (ICC 0·949) and minimal luminal area (ICC 0·904). The mean per-patient deep learning plaque analysis time was 5·65 s (SD 1·87) versus 25·66 min (6·79) taken by experts. Over a median follow-up of 4·7 years (IQR 4·0–5·7), myocardial infarction occurred in 41 (2·5%) of 1611 patients from the SCOT-HEART trial. A deep learning-based total plaque volume of 238·5 mm3 or higher was associated with an increased risk of myocardial infarction (hazard ratio [HR] 5·36, 95% CI 1·70–16·86; p=0·0042) after adjustment for the presence of deep learning-based obstructive stenosis (HR 2·49, 1·07–5·50; p=0·0089) and the ASSIGN clinical risk score (HR 1·01, 0·99–1·04; p=0·35). Our novel, externally validated deep learning system provides rapid measurements of plaque volume and stenosis severity from CCTA that agree closely with expert readers and intravascular ultrasound, and could have prognostic value for future myocardial infarction.