Department of Radiology and Research Institute of Radiology, Cardiac Imaging Centre, Asan Medical Centre, University of Ulsan College of Medicine, 05505 Olympic-Ro 388-1 Seoul, South Korea.
Division of Cardiology, Internal Medicine, Asan Medical Centre, University of Ulsan College of Medicine, 05505 Olympic-Ro, 388-1 Seoul, South Korea.
Eur Heart J Cardiovasc Imaging. 2021 Aug 14;22(9):998-1006. doi: 10.1093/ehjci/jeab062.
To evaluate the impact of coronary artery calcium (CAC) score, minimal lumen area (MLA), and length of coronary artery stenosis on the diagnostic performance of the machine-learning-based computed tomography-derived fractional flow reserve (ML-FFR).
In 471 patients with coronary artery disease, computed tomography angiography (CTA) and invasive coronary angiography were performed with fractional flow reserve (FFR) in 557 lesions at a single centre. Diagnostic performances of ML-FFR, computational fluid dynamics-based CT-FFR (CFD-FFR), MLA, quantitative coronary angiography (QCA), and visual stenosis grading were evaluated using invasive FFR as a reference standard. Diagnostic performances were analysed according to lesion characteristics including the MLA, length of stenosis, CAC score, and stenosis degree. ML-FFR was obtained by automated feature selection and model building from quantitative CTA. A total of 272 lesions showed significant ischaemia, defined by invasive FFR ≤0.80. There was a significant correlation between CFD-FFR and ML-FFR (r = 0.99, P < 0.001). ML-FFR showed moderate sensitivity and specificity in the per-patient analysis. Diagnostic performances of CFD-FFR and ML-FFR did not decline in patients with high CAC scores (CAC > 400). Sensitivities of CFD-FFR and ML-FFR showed a downward trend along with the increase in lesion length and decrease in MLA. The area under the curve (AUC) of ML-FFR (0.73) was higher than those of QCA and visual grading (AUC = 0.65 for both, P < 0.001) and comparable to those of MLA (AUC = 0.71, P = 0.21) and CFD-FFR (AUC = 0.73, P = 0.86).
ML-FFR showed comparable results to MLA and CFD-FFR for the prediction of lesion-specific ischaemia. Specificities and accuracies of CFD-FFR and ML-FFR decreased with smaller MLA and long lesion length.
评估冠状动脉钙化（CAC）评分、最小管腔面积（MLA）和冠状动脉狭窄长度对基于机器学习的计算机断层扫描衍生的分数流量储备（ML-FFR）的诊断性能的影响。
在 471 例冠心病患者中，在一个中心对 557 处病变进行了计算机断层血管造影（CTA）和有创冠状动脉造影，同时进行了分数流量储备（FFR）检测。使用有创 FFR 作为参考标准，评估 ML-FFR、基于计算流体动力学的 CT-FFR（CFD-FFR）、MLA、定量冠状动脉造影（QCA）和视觉狭窄分级的诊断性能。根据病变特征（包括 MLA、狭窄长度、CAC 评分和狭窄程度）分析诊断性能。ML-FFR 通过从定量 CTA 中自动选择特征和建立模型获得。共有 272 处病变存在显著缺血，由有创 FFR ≤0.80 定义。CFD-FFR 和 ML-FFR 之间存在显著相关性（r=0.99，P<0.001）。在每位患者的分析中，ML-FFR 显示出中等的敏感性和特异性。在 CAC 评分较高（CAC>400）的患者中，CFD-FFR 和 ML-FFR 的诊断性能并未下降。随着病变长度的增加和 MLA 的减少，CFD-FFR 和 ML-FFR 的敏感性呈下降趋势。ML-FFR 的曲线下面积（AUC）（0.73）高于 QCA 和视觉分级（两者 AUC 均为 0.65，P<0.001），与 MLA（AUC=0.71，P=0.21）和 CFD-FFR（AUC=0.73，P=0.86）相当。
ML-FFR 在预测病变特异性缺血方面与 MLA 和 CFD-FFR 具有可比的结果。CFD-FFR 和 ML-FFR 的特异性和准确性随着较小的 MLA 和较长的病变长度而降低。
Zotero 插件