Graduate Institute of Clinical Medicine, College of Medicine, National Taiwan University, Taipei, Taiwan; Heart Center, Cheng-Hsin General Hospital, Taipei, Taiwan.
Department of Surgery, National Taiwan University Hospital, Taipei, Taiwan.
JACC Cardiovasc Imaging. 2021 Feb;14(2):335-345. doi: 10.1016/j.jcmg.2020.08.034. Epub 2020 Nov 18.
The aim of this study was to develop an artificial intelligence tool to assess echocardiographic image quality objectively.
Left ventricular global longitudinal strain (LVGLS) has recently been used to monitor cancer therapeutics-related cardiac dysfunction (CTRCD) but image quality limits its reliability.
A DenseNet-121 convolutional neural network was developed for view identification from an athlete's echocardiographic dataset. To prove the concept that classification confidence (CC) can serve as a quality marker, values of longitudinal strain derived from feature tracking of cardiac magnetic resonance (CMR) imaging and strain analysis of echocardiography were compared. The CC was then applied to patients with breast cancer free from CTRCD to investigate the effects of image quality on the reliability of strain analysis.
CC of the apical 4-chamber view (A4C) was significantly correlated with the endocardial border delineation index. CC of A4C >900 significantly predicted a <15% relative difference in longitudinal strain between CMR feature tracking and automated echocardiographic analysis. Echocardiographic studies (n =752) of 102 patients with breast cancer without CTRCD were investigated. The strain analysis showed higher parallel forms, inter-rater, and test-retest reliabilities in patients with CC of A4C >900. During sequential comparisons of automated LVGLS in individual patients, those with CC of A4C >900 had a lower false positive detection rate of CTRCD.
CC of A4C was associated with the reliability of automated LVGLS and could also potentially be used as a filter to select comparable images from sequential echocardiographic studies in individual patients and reduce the false positive detection rate of CTRCD.
本研究旨在开发一种人工智能工具，客观评估超声心动图图像质量。
左心室整体纵向应变（LVGLS）最近已用于监测癌症治疗相关心脏功能障碍（CTRCD），但图像质量限制了其可靠性。
开发了一种 DenseNet-121 卷积神经网络，用于从运动员的超声心动图数据集中识别视图。为了证明分类置信度（CC）可以作为质量标志物的概念，比较了来自心脏磁共振成像（CMR）特征追踪和超声心动图应变分析的纵向应变值。然后将 CC 应用于无 CTRCD 的乳腺癌患者，以研究图像质量对应变分析可靠性的影响。
心尖 4 腔视图（A4C）的 CC 与心内膜边界描绘指数显著相关。A4C 的 CC >900 显著预测了 CMR 特征追踪和自动超声心动图分析之间的纵向应变相对差异<15%。对 102 例无 CTRCD 的乳腺癌患者的 752 项超声心动图研究进行了调查。应变分析显示，A4C 的 CC >900 的患者的平行形式、观察者间和测试-再测试可靠性更高。在对个别患者的自动 LVGLS 进行顺序比较时，A4C 的 CC >900 的患者的 CTRCD 假阳性检出率较低。
A4C 的 CC 与自动 LVGLS 的可靠性相关，也可以用作过滤器，从个别患者的连续超声心动图研究中选择可比的图像，并降低 CTRCD 的假阳性检出率。
