Division of Pediatric Cardiology, Department of Pediatrics, Stanford University School of Medicine, Palo Alto, California.
Division of Pediatric Cardiology, Department of Pediatrics, Stanford University School of Medicine, Palo Alto, California.
J Am Soc Echocardiogr. 2023 May;36(5):482-489. doi: 10.1016/j.echo.2023.01.015. Epub 2023 Feb 7.
Significant interobserver and interstudy variability occurs for left ventricular (LV) functional indices despite standardization of measurement techniques. Artificial intelligence models trained on adult echocardiograms are not likely to be applicable to a pediatric population. We present EchoNet-Peds, a video-based deep learning algorithm, which matches human expert performance of LV segmentation and ejection fraction (EF).
A large pediatric data set of 4,467 echocardiograms was used to develop EchoNet-Peds. EchoNet-Peds was trained on 80% of the data for segmentation of the left ventricle and estimation of LVEF. The remaining 20% was used to fine-tune and validate the algorithm.
In both apical 4-chamber and parasternal short-axis views, EchoNet-Peds segments the left ventricle with a Dice similarity coefficient of 0.89. EchoNet-Peds estimates EF with a mean absolute error of 3.66% and can routinely identify pediatric patients with systolic dysfunction (area under the curve of 0.95). EchoNet-Peds was trained on pediatric echocardiograms and performed significantly better to estimate EF (P < .001) than an adult model applied to the same data.
Accurate, rapid automation of EF assessment and recognition of systolic dysfunction in a pediatric population are feasible using EchoNet-Peds with the potential for far-reaching clinical impact. In addition, the first large pediatric data set of annotated echocardiograms is now publicly available for efforts to develop pediatric-specific artificial intelligence algorithms.
尽管测量技术已经标准化，但左心室（LV）功能指标的观察者间和研究间差异仍然很大。基于成人超声心动图训练的人工智能模型不太可能适用于儿科人群。我们提出了 EchoNet-Peds，这是一种基于视频的深度学习算法，可与 LV 分段和射血分数（EF）的人类专家表现相匹配。
使用大型儿科超声心动图数据集（4467 例）来开发 EchoNet-Peds。EchoNet-Peds 利用 80%的数据进行左心室分段和 LVEF 估计的训练。其余 20%用于调整和验证算法。
在 apical 4 腔和胸骨旁短轴视图中，EchoNet-Peds 对左心室进行分段的 Dice 相似系数为 0.89。EchoNet-Peds 估计 EF 的平均绝对误差为 3.66%，并且可以常规识别有收缩功能障碍的儿科患者（曲线下面积为 0.95）。EchoNet-Peds 是基于儿科超声心动图进行训练的，与应用于相同数据的成人模型相比，其 EF 估计效果明显更好（P<.001）。
使用 EchoNet-Peds 可以实现 EF 评估的快速、准确自动化，并识别儿科人群中的收缩功能障碍，具有广泛的临床影响。此外，现在可公开获取带有注释的大型儿科超声心动图数据集，以便努力开发儿科专用的人工智能算法。
