Diagnostic accuracy of a deep learning approach to calculate FFR from coronary CT angiography

作     者：Zhi-Qiang WANG Yu-Jie ZHOU Ying-Xin ZHAO Dong-Mei SHI Yu-Yang LIU Wei LIU Xiao-Li LIU Yue-Ping LI 

作者机构：Department of Cardiology Beijing Anzhen Hospital Capital Medical University Beijing Institute of Heart Lung and Blood Vessel Disease Beijing Key Laboratory of Precision Medicine of Coronary Atherosclerotic Disease Clinical Center for Coronary Heart Disease Capital Medical University 

出 版 物：《Journal of Geriatric Cardiology》 (老年心脏病学杂志（英文版）)

年 卷 期：2019年第16卷第1期

页      面：42-48页

核心收录：

学科分类：10[医学] 

主　　题：Computed tomography angiography Coronary artery Deep learning Fractional flow reserve 

摘      要：Background The computational fluid dynamics(CFD)approach has been frequently applied to compute the fractional flow reserve(FFR)using computed tomography angiography(CTA).This technique is *** developed the DEEPVESSEL-FFR platform using the emerging deep learning technique to calculate the FFR value out of CTA images in five *** study is to evaluate the DEEPVESSEL-FFR platform using the emerging deep learning technique to calculate the FFR value from CTA images as an efficient *** A single-center,prospective study was conducted and 63 patients were enrolled for the evaluation of the diagnostic performance of *** quantification method for the three-dimensional coronary arterial geometry and the deep learning based prediction of FFR were developed to assess the ischemic risk of the stenotic coronary *** performance of the DEEPVESSEL-FFR was assessed by using wire-based FFR as reference *** primary evaluation factor was defined by using the area under receiver-operation characteristics curve(AUC)*** For per-patient level,taking the cut-off value0.8 referring to the FFR measurement,DEEPVESSEL-FFR presented higher diagnostic performance in determining ischemia-related lesions with area under the curve of 0.928 compare to CTA stenotic severity ***-FFR correlated with FFR(R=0.686,P0.001),with a mean di&ference of-0.006士0.0091(P=0.619).The secondary evaluation factors,indicating per vessel accuracy,sensitivity,specificity,positive predictive value,and negative predictive value were 87.3%,97.14%,75%,82.93%,and 95.45%,*** DEEPVESSEL-FFR is a novel method that allows efficient assessment of the functional significance of coronary stenosis.