Fully Automated Echocardiogram Interpretation in Clinical Practice.
Fully Automated Echocardiogram Interpretation in Clinical Practice.
复制标题
DOI：
10.1161/circulationaha.118.034338
复制
发表时间：
2018-10-16
期刊：
影响因子：
37.8
通讯作者：
Deo RC
中科院分区：
文献类型：
--
作者：
Zhang J;Gajjala S;Agrawal P;Tison GH;Hallock LA;Beussink-Nelson L;Lassen MH;Fan E;Aras MA;Jordan C;Fleischmann KE;Melisko M;Qasim A;Shah SJ;Bajcsy R;Deo RC
补充数字内容可在正文中找到。心脏图像自动解释具有以多种方式改变临床实践的潜力，包括使初级保健和农村环境中的非专家能够对心脏功能进行连续评估。我们假设，计算机视觉的进步可以为超声心动图的解释建立一个完全自动化的、可扩展的分析管道，包括(1)视图识别，(2)图像分割，(3)结构和功能的量化，以及(4)疾病检测。使用跨越10年的14个 035超声心动图，我们训练和评估了用于多任务的卷积神经网络模型，包括23个视点的自动识别和5个常见视点的心腔分割。分割输出被用来量化心腔体积和左心室质量，确定射血分数，并通过斑点跟踪促进纵向应变的自动确定。结果通过与手动分割和在常规临床工作流程中获得的8666个超声心动图的测量进行比较来评估。最后，我们开发了检测3种疾病的模型：肥厚型心肌病、心脏淀粉样蛋白和肺动脉高压。卷积神经网络能够准确识别视角(例如，胸骨旁长轴的识别率为96%)，包括标记部分遮挡的心腔，并能够分割单个心腔。由此得到的心脏结构测量值与研究报告值一致(例如，左心室质量、左心室舒张期容量和左心房容量观察值的中位数绝对偏差为15%至17%)。在功能方面，我们计算了自动射血分数和纵向应变测量(在2个队列内)，与商业软件得出的值一致(对于射血分数，中位绝对偏差=9.7%的观察值，N=6407项研究；对于应变，中位绝对偏差=7.5%，n=419，9.0%，n=110)，并证明了其适用于对乳腺癌患者曲妥珠单抗心脏毒性的连续监测。总体而言，我们发现自动化测量在11个内部一致性指标上与手动测量相当或更好(例如，左房和左心室容量的相关性)。最后，我们训练卷积神经网络来检测肥厚型心肌病、心脏淀粉样变性和肺动脉高压，C统计量分别为0.93、0.87和0.85。我们的流程为使用自动解释来支持连续患者跟踪和对医疗系统中归档的数百万超声心动图进行可扩展分析奠定了基础。
Supplemental Digital Content is available in the text. Automated cardiac image interpretation has the potential to transform clinical practice in multiple ways, including enabling serial assessment of cardiac function by nonexperts in primary care and rural settings. We hypothesized that advances in computer vision could enable building a fully automated, scalable analysis pipeline for echocardiogram interpretation, including (1) view identification, (2) image segmentation, (3) quantification of structure and function, and (4) disease detection. Using 14 035 echocardiograms spanning a 10-year period, we trained and evaluated convolutional neural network models for multiple tasks, including automated identification of 23 viewpoints and segmentation of cardiac chambers across 5 common views. The segmentation output was used to quantify chamber volumes and left ventricular mass, determine ejection fraction, and facilitate automated determination of longitudinal strain through speckle tracking. Results were evaluated through comparison to manual segmentation and measurements from 8666 echocardiograms obtained during the routine clinical workflow. Finally, we developed models to detect 3 diseases: hypertrophic cardiomyopathy, cardiac amyloid, and pulmonary arterial hypertension. Convolutional neural networks accurately identified views (eg, 96% for parasternal long axis), including flagging partially obscured cardiac chambers, and enabled the segmentation of individual cardiac chambers. The resulting cardiac structure measurements agreed with study report values (eg, median absolute deviations of 15% to 17% of observed values for left ventricular mass, left ventricular diastolic volume, and left atrial volume). In terms of function, we computed automated ejection fraction and longitudinal strain measurements (within 2 cohorts), which agreed with commercial software-derived values (for ejection fraction, median absolute deviation=9.7% of observed, N=6407 studies; for strain, median absolute deviation=7.5%, n=419, and 9.0%, n=110) and demonstrated applicability to serial monitoring of patients with breast cancer for trastuzumab cardiotoxicity. Overall, we found automated measurements to be comparable or superior to manual measurements across 11 internal consistency metrics (eg, the correlation of left atrial and ventricular volumes). Finally, we trained convolutional neural networks to detect hypertrophic cardiomyopathy, cardiac amyloidosis, and pulmonary arterial hypertension with C statistics of 0.93, 0.87, and 0.85, respectively. Our pipeline lays the groundwork for using automated interpretation to support serial patient tracking and scalable analysis of millions of echocardiograms archived within healthcare systems.