基于机器学习的FFR_(CT)对冠状动脉功能性狭窄的诊断准确性研究  

Diagnostic performance of machine learning based FFR_(CT) in coronary artery stenosis

作　　者：余蒙蒙 李跃华[1] 李文彬[1] 陆志刚[2] 魏盟[2] 沈成兴 闫静 张佳胤[1] YU Mengmeng;LI Yuehua;LI Wenbin;LU Zhigang;WEI Meng;SHEN Chengxing;YAN Jing;ZHANG Jiayin(Department of Radiology;Department of Cardiology, Shanghai Jiao Tong University Affiliated Sixth People, s Hospital;Siemens Healthcare Ltd)

机构地区：[1]上海交通大学附属第六人民医院放射科,上海200233 [2]上海交通大学附属第六人民医院心内科,上海200233 [3]西门子医疗系统有限公司

出　　处：《国际医学放射学杂志》2018年第3期282-286,共5页International Journal of Medical Radiology

基　　金：上海市重中之重医学影像重点学科项目(2017ZZ02005)

摘　　要：目的以有创性冠状动脉血流储备分数(FFR)为金标准,探讨不同区间内基于机器深度学习的CT冠状动脉血流储备分数(FFR_(CT))对冠状动脉功能性狭窄的诊断准确性。方法回顾性收集先后行冠状动脉CT血管成像(CCTA)及FFR检查的病人125例(162处病变),年龄42.0~88.0岁,平均(61.0±8.2)岁,男79例,女46例。两项检查时间间隔≤2周。在CCTA影像上获得病变直径狭窄程度,采用西门子c FFR原型软件(cFFR,version3.0.0)计算FFR_(CT)数值。以FFR≤0.8为具有血流动力学意义的狭窄,绘制FFR_(CT)及CCTA的受试者操作特征曲线,获得曲线下面积(AUC)。并计算两种方法的敏感度、特异度、阳性预测值、阴性预测值及准确度。结果 FFR_(CT)及CCTA对于诊断功能性狭窄的AUC分别为0.85、0.76(P<0.05)。基于病人水平分析,CCTA和FFR_(CT)的诊断敏感度、特异度、准确度分别为77.6%、69.7%、76.8%和85.7%、78.9%和86.1%。当FFR_(CT)数值≤0.69、0.7~0.8、0.81~0.89、≥0.9时,FFR_(CT)诊断功能性狭窄的准确度分别为86.4%、61.2%、88.6%、98.2%。结论以FFR为金标准,FFR_(CT)数值在0.7~0.8之外的病变结果具有良好的诊断准确性,而数值在0.7~0.8区域内的病变诊断准确性欠佳。Objective To investigate the diagnostic performance of machine learning based FFRCTacross the different intervals of FFRCTvalue for identifying functionally significant stenosis, with reference to invasive FFR. Methods We retrospectively reviewed the data of one hundred and twenty-five patients [mean age： 61.0±8.2（range, 42.0-88.0） years;79 males and 46 females] with 162 lesions, who underwent both coronary computed tomography angiography（CCTA） and invasive coronary angiography（ICA） within 2 weeks interval. Diameter stenosis derived from CCTA were recorded and FFRCT were performed on routine CCTA datasets using Siemens prototype software（c FFR, version 3.0.0）. Lesions with FFR ≤0.8 were considered to be hemodynamically functional significant stenosis, receiver operating characteristic curve analysis was performed to calculate the area under the receiver operating characteristic curve（AUC）. Sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were recorded. Results The AUC values were 0.85 and 0.76 for FFRCTand CCTA, respectively（P0.05）, for diagnosing functionally significant stenosis. Per-patient sensitivity, specificity,and diagnostic accuracy to identify a significant functionally stenosis were 85.7%, 78.9%, 86.1%, respectively, for FFRCT;and 77.6%, 69.7%,76.8%, respectively, for CCTA. For lesions with FFRCTvalues below 0.69, 0.70 to 0.80, 0.81 to 0.89, and above 0.90, the diagnostic accuracies of FFRCTwere 86.4%, 61.2%, 88.6%, 98.2%, respectively. Conclusion Using FFR calculated from ICA as the garden standard, it can achieve a high diagnostic accuracy when the FFRCTvalue is less than 0.7 or more than 0.8, otherwise efficient diagnostic performance is not guaranteed.

关 键 词：冠心病 体层摄影术 X线计算机 有创性冠状动脉造影 血流储备分数 

分 类 号：R445.3[医药卫生—影像医学与核医学] R541.4[医药卫生—诊断学]