基于人工智能技术的FFR_(CT)评估左冠状动脉前降支纵深型心肌桥血流动力学变化  

The role of Artificial intelligent-based FFR_(CT) in assessing the hemodynamic relevance of deep myocardial bridge of the left anterior descending coronary artery

作　　者：成水华 倪炯[1] 刘君[1] 黄芳[1] 王培军[1] Cheng Shuihua;Ni Jiong;Liu Jun;Huang Fang;Wang Peijun(Department of Radiology,Tongji Hospital,Tongji University School of Medicine,Shanghai 200065,China)

机构地区：[1]同济大学附属同济医院放射科,上海200065

出　　处：《中华医学杂志》2021年第7期464-469,共6页National Medical Journal of China

基　　金：国家重点研发计划(2017YFC0112800)。

摘　　要：目的探讨基于人工智能技术的冠状动脉CT血流储备分数(FFR_(CT))对左冠状动脉前降支纵深型心肌桥患者血流动力学改变的评估价值。方法回顾性分析2017年1月至2019年12月同济大学附属同济医院放射科行冠状动脉CT血管造影(CCTA)检查诊断为左冠状动脉前降支纵深型心肌桥的113例患者资料。测量心肌桥的位置、长度、深度以及收缩期管腔狭窄率。利用基于人工智能技术的冠状动脉FFR_(CT)软件计算左冠状动脉前降支纵深型心肌桥的FFR_(CT)值。以0.80为界,将所有患者分为FFR_(CT)正常组(FFR_(CT)>0.80)及FFR_(CT)异常组(FFR_(CT)≤0.80),分析FFR_(CT)异常与左前降支纵深型心肌桥位置、长度、深度、收缩期狭窄率之间的关系。通过受试者工作特征(ROC)曲线分析心肌桥长度、深度及收缩期狭窄率预测FFR_(CT)异常的效能。结果FFR_(CT)正常组(n=79)和FFR_(CT)异常组(n=34)两组患者间年龄、性别及高危因素差异均无统计学意义(均P>0.05)。在临床症状中,FFR_(CT)正常组患者不稳定性心绞痛、无症状性心肌缺血、稳定性心绞痛占比分别约15.2%、41.8%、32.9%,FFR_(CT)异常组患者以上临床症状占比分别约32.4%、23.5%、35.3%,两组患者不稳定性心绞痛差异有统计学意义(χ^(2)=4.32,P=0.038),无症状性心肌缺血、稳定性心绞痛差异无统计学意义(χ^(2)=3.42、0.06,均P>0.05)。FFR_(CT)正常组及FFR_(CT)异常组患者纵深型心肌桥长度分别约(36±5)mm、(44±5)mm,两者差异具有统计学意义(t=-7.703,P<0.001)。ROC曲线显示纵深型心肌桥长度的最佳截断值为39.7 mm,曲线下面积为0.88(95%CI:0.81~0.95,P<0.001),其诊断FFR_(CT)≤0.80的准确率为82.3%。结论FFR_(CT)值在评估左冠状动脉前降支纵深型心肌桥患者的血流动力学方面有重要价值,且纵深型心肌桥的长度是影响FFR_(CT)值的重要因素。Objective To investigate the role of artificial intelligence-based coronary CT blood flow reserve score(FFR_(CT))in assessing hemodynamic relevance in patients with deep myocardial bridge(MB)of the left anterior descending coronary artery.Methods A total of 113 patients diagnosed with deep MB of the left anterior descending coronary artery by coronary CT angiography(CCTA)at the Department of Radiology of Tongji Hospital Affiliated to Tongji University from January 2017 to December 2019 were retrospectively analyzed.The location,length,depth,and degree of systolic compression of the MB were measured.The artificial intelligence-based coronary FFR_(CT) software was employed to calculate the FFR_(CT) value of the deep MB of the left anterior descending coronary artery.With the boundary of 0.80,all patients were divided into FFR_(CT) normal group(FFR_(CT)>0.80)and FFR_(CT) abnormal group(FFR_(CT)≤0.80),and the relationship between FFR_(CT) abnormality and the location,length,depth,and degree of systolic stenosis of the deep MB of the left anterior descending branch was analyzed.The effectiveness of the receiver operating characteristic(ROC)curve in predicting FFR_(CT) abnormalities was measured by using ROC curve to analyze the length,depth,and degree of systolic stenosis of MB.Results There were no significant differences in age,gender and high-risk factors between FFR_(CT) normal group(n=79)and FFR_(CT) abnormal group(n=34)(P>0.05).In terms of clinical symptoms,unstable angina,asymptomatic myocardial ischemia,stable angina in the FFR_(CT) normal group were 15.2%,41.8%,32.9%,respectively,while 32.4%,23.5%,35.3% in the FFR_(CT) abnormal group,respectively.Except for unstable angina(χ^(2)=4.32,P=0.038),there were no significant differences in asymptomatic myocardial ischemia and stable angina between the two groups(χ^(2)=3.42,0.06,P>0.05).The length of deep MB was about(36±5)mm in the FFR_(CT) normal group and(44±5)mm in the FFR_(CT) abnormal group,respectively.The difference between the two groups was statistica

关 键 词：心肌桥 人工智能 血流储备分数 冠状动脉CT血管成像 

分 类 号：R541.4[医药卫生—心血管疾病] TP18[医药卫生—内科学]