Deep Learning Analysis of Upright-Supine High-Efficiency SPECT Myocardial Perfusion Imaging for Prediction of Obstructive Coronary Artery Disease: A Multicenter Study
Deep Learning Analysis of Upright-Supine High-Efficiency SPECT Myocardial Perfusion Imaging for Prediction of Obstructive Coronary Artery Disease: A Multicenter Study
复制标题
DOI：
10.2967/jnumed.118.213538
复制
发表时间：
2019-05-01
影响因子：
9.3
通讯作者：
Slomka, Piotr J.
中科院分区：
文献类型：
--
作者：
Betancur, Julian;Hu, Lien-Hsin;Slomka, Piotr J.
常规使用固态摄像机对2种体位（半直立、仰卧）的患者进行SPECT心肌灌注成像（MPI）的组合分析，以减轻衰减伪影。我们评估了通过深度学习（DL）半直立和仰卧应力MPI的组合分析与标准组合总灌注不足（TPD）相比对阻塞性疾病的预测。方法：研究了1,160例无已知冠状动脉疾病的患者（64%为男性）。患者在4个不同的中心使用新一代固态SPECT扫描仪接受了负荷Tc-99 m-sestamibi MPI。所有患者均在MPI的6个月内进行了现场临床读数和有创冠状动脉造影相关性。阻塞性疾病定义为3支主要冠状动脉狭窄至少70%，左主干狭窄至少50%。在Cedars-Sinai对图像进行定量。使用标准临床核心脏病学软件分割左心室心肌。轮廓放置由经验丰富的技术人员验证。使用性别和相机特异性正常限值计算联合应力TPD。DL使用标准化放射性示踪剂计数、低灌注缺陷和低灌注严重程度的极分布进行训练，并在一种等同于外部验证的新型留一中心交叉验证程序中评价其预测阻塞性疾病。在验证过程中，使用来自3个中心的数据训练4个DL模型，然后在1个中心进行评价。合并每个中心的预测值，以获得多中心性能的总体估计。结果：718例（62%）患者和3，480支动脉中的1，272支（37%）患有阻塞性疾病。DL预测每例患者和每支血管疾病的受试者工作特征曲线下面积高于联合TPD（每例患者，0.81 vs. 0.78;每支血管，0.77 vs. 0.73; P < 0.001）。将DL临界值设置为与联合TPD的标准临界值具有相同的特异性，每个患者的灵敏度从61.8%（TPD）提高到65.6%（DL）（P < 0.05），每个血管的灵敏度从54.6%（TPD）提高到59.1%（DL）（P < 0.01）。当阈值与正常临床读数的特异性（56.3%）相匹配时，DL的灵敏度为84.8%，而现场临床读数的灵敏度为82.6%（P = 0.3）。结论：与目前的定量方法相比，DL提高了MPI的自动解释。
Combined analysis of SPECT myocardial perfusion imaging (MPI) performed with a solid-state camera on patients in 2 positions (semiupright, supine) is routinely used to mitigate attenuation artifacts. We evaluated the prediction of obstructive disease from combined analysis of semiupright and supine stress MPI by deep learning (DL) as compared with standard combined total perfusion deficit (TPD). Methods: 1,160 patients without known coronary artery disease (64% male) were studied. Patients underwent stress Tc-99m-sestamibi MPI with new-generation solid-state SPECT scanners in 4 different centers. All patients had on-site clinical reads and invasive coronary angiography correlations within 6 mo of MPI. Obstructive disease was defined as at least 70% narrowing of the 3 major coronary arteries and at least 50% for the left main coronary artery. Images were quantified at Cedars-Sinai. The left ventricular myocardium was segmented using standard clinical nuclear cardiology software. The contour placement was verified by an experienced technologist. Combined stress TPD was computed using sex-and camera-specific normal limits. DL was trained using polar distributions of normalized radiotracer counts, hypoperfusion defects, and hypoperfusion severities and was evaluated for prediction of obstructive disease in a novel leave-one-center-out crossvalidation procedure equivalent to external validation. During the validation procedure, 4 DL models were trained using data from 3 centers and then evaluated on the 1 center left aside. Predictions for each center were merged to have an overall estimation of the multicenter performance. Results: 718 (62%) patients and 1,272 of 3,480 (37%) arteries had obstructive disease. The area under the receiver operating characteristics curve for prediction of disease on a per-patient and per-vessel basis by DL was higher than for combined TPD (per-patient, 0.81 vs. 0.78; per-vessel, 0.77 vs. 0.73; P < 0.001). With the DL cutoff set to exhibit the same specificity as the standard cutoff for combined TPD, per-patient sensitivity improved from 61.8% (TPD) to 65.6% (DL) (P < 0.05), and per-vessel sensitivity improved from 54.6% (TPD) to 59.1% (DL) (P < 0.01). With the threshold matched to the specificity of a normal clinical read (56.3%), DL had a sensitivity of 84.8%, versus 82.6% for an on-site clinical read (P = 0.3). Conclusion: DL improves automatic interpretation of MPI as compared with current quantitative methods.