British Heart Foundation Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, UK.
Departments of Medicine (Division of Artificial Intelligence), Imaging and Biomedical Sciences Cedars-Sinai Medical Center, 6500 Wilshire Blvd, Floor 4, Los Angeles 90048 CA, USA.
Eur Heart J Cardiovasc Imaging. 2024 Jun 28;25(7):976-985. doi: 10.1093/ehjci/jeae045.
Vessel-specific coronary artery calcification (CAC) is additive to global CAC for prognostic assessment. We assessed accuracy and prognostic implications of vessel-specific automated deep learning (DL) CAC analysis on electrocardiogram (ECG) gated and attenuation correction (AC) computed tomography (CT) in a large multi-centre registry.
Vessel-specific CAC was assessed in the left main/left anterior descending (LM/LAD), left circumflex (LCX), and right coronary artery (RCA) using a DL model trained on 3000 gated CT and tested on 2094 gated CT and 5969 non-gated AC CT. Vessel-specific agreement was assessed with linear weighted Cohen's Kappa for CAC zero, 1-100, 101-400, and >400 Agatston units (AU). Risk of major adverse cardiovascular events (MACE) was assessed during 2.4 ± 1.4 years follow-up, with hazard ratios (HR) and 95% confidence intervals (CI). There was strong to excellent agreement between DL and expert ground truth for CAC in LM/LAD, LCX and RCA on gated CT [0.90 (95% CI 0.89 to 0.92); 0.70 (0.68 to 0.73); 0.79 (0.77 to 0.81)] and AC CT [0.78 (0.77 to 0.80); 0.60 (0.58 to 0.62); 0.70 (0.68 to 0.71)]. MACE occurred in 242 (12%) undergoing gated CT and 841(14%) of undergoing AC CT. LM/LAD CAC >400 AU was associated with the highest risk of MACE on gated (HR 12.0, 95% CI 7.96, 18.0, P < 0.001) and AC CT (HR 4.21, 95% CI 3.48, 5.08, P < 0.001).
Vessel-specific CAC assessment with DL can be performed accurately and rapidly on gated CT and AC CT and provides important prognostic information.
血管特异性冠状动脉钙化（CAC）对预后评估具有附加价值。我们评估了在大型多中心注册研究中，基于心电图（ECG）门控和衰减校正（AC）计算机断层扫描（CT）的深度学习（DL）自动血管特异性 CAC 分析的准确性和预后意义。
使用在 3000 次门控 CT 上训练并在 2094 次门控 CT 和 5969 次非门控 AC CT 上测试的 DL 模型评估左主干/左前降支（LM/LAD）、左回旋支（LCX）和右冠状动脉（RCA）的血管特异性 CAC。使用线性加权 Cohen's Kappa 评估 CAC 零、1-100、101-400 和 >400 单位（AU）的血管特异性一致性。在 2.4±1.4 年的随访期间评估主要不良心血管事件（MACE）的风险，使用风险比（HR）和 95%置信区间（CI）。DL 与专家地面真实之间在门控 CT 上的 LM/LAD、LCX 和 RCA 的 CAC 之间具有很强到极好的一致性[0.90（95%CI 0.89 至 0.92）；0.70（0.68 至 0.73）；0.79（0.77 至 0.81）]和 AC CT[0.78（0.77 至 0.80）；0.60（0.58 至 0.62）；0.70（0.68 至 0.71）]。在接受门控 CT 的 242 例（12%）和接受 AC CT 的 841 例（14%）中发生了 MACE。LM/LAD CAC >400 AU 与门控 CT（HR 12.0，95%CI 7.96，18.0，P <0.001）和 AC CT（HR 4.21，95%CI 3.48，5.08，P <0.001）的最高 MACE 风险相关。
基于 DL 的血管特异性 CAC 评估可以在门控 CT 和 AC CT 上准确快速地进行，并提供重要的预后信息。
