Department of Circulation and Medical Imaging, Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology, Trondheim, Norway.
Department of Circulation and Medical Imaging, Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology, Trondheim, Norway.
Ultrasound Med Biol. 2024 Apr;50(4):540-548. doi: 10.1016/j.ultrasmedbio.2023.12.018. Epub 2024 Jan 29.
The right ventricle receives less attention than its left counterpart in echocardiography research, practice and development of automated solutions. In the work described here, we sought to determine that the deep learning methods for automated segmentation of the left ventricle in 2-D echocardiograms are also valid for the right ventricle. Additionally, here we describe and explore a keypoint detection approach to segmentation that guards against erratic behavior often displayed by segmentation models.
We used a data set of echo images focused on the right ventricle from 250 participants to train and evaluate several deep learning models for segmentation and keypoint detection. We propose a compact architecture (U-Net KP) employing the latter approach. The architecture is designed to balance high speed with accuracy and robustness.
All featured models achieved segmentation accuracy close to the inter-observer variability. When computing the metrics of right ventricular systolic function from contour predictions of U-Net KP, we obtained the bias and 95% limits of agreement of 0.8 ± 10.8% for the right ventricular fractional area change measurements, -0.04 ± 0.54 cm for the tricuspid annular plane systolic excursion measurements and 0.2 ± 6.6% for the right ventricular free wall strain measurements. These results were also comparable to the semi-automatically derived inter-observer discrepancies of 0.4 ± 11.8%, -0.37 ± 0.58 cm and -1.0 ± 7.7% for the aforementioned metrics, respectively.
Given the appropriate data, automated segmentation and quantification of the right ventricle in 2-D echocardiography are feasible with existing methods. However, keypoint detection architectures may offer higher robustness and information density for the same computational cost.
在超声心动图研究、实践和自动化解决方案的开发中，右心室受到的关注不如左心室多。在本文所述的工作中，我们试图确定用于自动分割二维超声心动图中左心室的深度学习方法也适用于右心室。此外，我们在这里描述并探索了一种关键点检测方法来分割，以防止分割模型经常出现的不稳定行为。
我们使用了一个来自 250 名参与者的专注于右心室的超声图像数据集来训练和评估几种用于分割和关键点检测的深度学习模型。我们提出了一种紧凑的架构（U-Net KP），采用了后一种方法。该架构旨在平衡速度、准确性和鲁棒性。
所有特征模型的分割准确性都接近观察者间的变异性。当从 U-Net KP 的轮廓预测计算右心室收缩功能的指标时，我们得到了右心室分数面积变化测量值的偏差和 95%一致性限为 0.8 ± 10.8%，三尖瓣环平面收缩期位移测量值为-0.04 ± 0.54 cm，右心室游离壁应变测量值为 0.2 ± 6.6%。这些结果也与半自动获得的观察者间差异 0.4 ± 11.8%、-0.37 ± 0.58 cm 和-1.0 ± 7.7%分别在上述指标上相当。
在有适当数据的情况下，现有的方法可以实现二维超声心动图中右心室的自动分割和定量。然而，关键点检测架构可能在相同的计算成本下提供更高的鲁棒性和信息密度。
