Ono Shunzaburo, Komatsu Masaaki, Sakai Akira, Arima Hideki, Ochida Mie, Aoyama Rina, Yasutomi Suguru, Asada Ken, Kaneko Syuzo, Sasano Tetsuo, Hamamoto Ryuji
Department of Cardiovascular Medicine, Tokyo Medical and Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo 113-8510, Japan.
Division of Medical AI Research and Development, National Cancer Center Research Institute, 5-1-1 Tsukiji, Chuo-ku, Tokyo 104-0045, Japan.
Biomedicines. 2022 May 6;10(5):1082. doi: 10.3390/biomedicines10051082.
Endocardial border detection is a key step in assessing left ventricular systolic function in echocardiography. However, this process is still not sufficiently accurate, and manual retracing is often required, causing time-consuming and intra-/inter-observer variability in clinical practice. To address these clinical issues, more accurate and normalized automatic endocardial border detection would be valuable. Here, we develop a deep learning-based method for automated endocardial border detection and left ventricular functional assessment in two-dimensional echocardiographic videos. First, segmentation of the left ventricular cavity was performed in the six representative projections for a cardiac cycle. We employed four segmentation methods: U-Net, UNet++, UNet3+, and Deep Residual U-Net. UNet++ and UNet3+ showed a sufficiently high performance in the mean value of intersection over union and Dice coefficient. The accuracy of the four segmentation methods was then evaluated by calculating the mean value for the estimation error of the echocardiographic indexes. UNet++ was superior to the other segmentation methods, with the acceptable mean estimation error of the left ventricular ejection fraction of 10.8%, global longitudinal strain of 8.5%, and global circumferential strain of 5.8%, respectively. Our method using UNet++ demonstrated the best performance. This method may potentially support examiners and improve the workflow in echocardiography.
心内膜边界检测是超声心动图评估左心室收缩功能的关键步骤。然而，这一过程仍不够准确，临床实践中常常需要人工重新追踪，导致耗时且存在观察者内/间差异。为解决这些临床问题，更准确且标准化的自动心内膜边界检测将很有价值。在此，我们开发了一种基于深度学习的方法，用于二维超声心动图视频中的自动心内膜边界检测和左心室功能评估。首先，在心动周期的六个代表性投影中对左心室腔进行分割。我们采用了四种分割方法：U-Net、UNet++、UNet3+和深度残差U-Net。UNet++和UNet3+在交并比均值和Dice系数方面表现出足够高的性能。然后通过计算超声心动图指标估计误差的均值来评估这四种分割方法的准确性。UNet++优于其他分割方法，左心室射血分数、整体纵向应变和整体圆周应变的平均估计误差分别为可接受的10.8%、8.5%和5.8%。我们使用UNet++的方法表现出最佳性能。该方法可能会为检查人员提供支持并改善超声心动图的工作流程。
