Fast and accurate view classification of echocardiograms using deep learning
Fast and accurate view classification of echocardiograms using deep learning
复制标题
DOI：
10.1038/s41746-017-0013-1
复制
发表时间：
2018-03-21
影响因子：
15.2
通讯作者：
Arnaout, Rima
中科院分区：
文献类型：
--
作者：
Madani, Ali;Arnaout, Ramy;Arnaout, Rima
超声心动图是心脏病学必不可少的。然而，对人类解释的需求限制了超声心动图在精确医学方面的全部潜力。深度学习是一种新兴的图像分析工具，但尚未广泛应用于超声心动图，部分原因是其复杂的多视图格式。全面的计算机辅助超声心动图解释的第一步是确定计算机是否可以学习识别这些视图。我们训练了一个卷积神经网络，根据来自267个经胸超声心动图的标记静态图像和视频，同时对15个标准视图（12个视频，3个静态）进行分类，这些图像和视频捕获了一系列真实世界的临床变化。我们的模型在12个视频视图中进行分类，总体测试准确率为97.8%，没有过度拟合。即使在单个低分辨率图像上，15个视图的准确性也为91.7%，而委员会认证的超声心动图技师的准确性为70.2-84.0%。数据可视化实验表明，该模型识别相关视图之间的相似性，并使用临床相关的图像特征进行分类。我们的研究结果为人工智能辅助超声心动图解释提供了基础。
Echocardiography is essential to cardiology. However, the need for human interpretation has limited echocardiography's full potential for precision medicine. Deep learning is an emerging tool for analyzing images but has not yet been widely applied to echocardiograms, partly due to their complex multi-view format. The essential first step toward comprehensive computer-assisted echocardiographic interpretation is determining whether computers can learn to recognize these views. We trained a convolutional neural network to simultaneously classify 15 standard views (12 video, 3 still), based on labeled still images and videos from 267 transthoracic echocardiograms that captured a range of real-world clinical variation. Our model classified among 12 video views with 97.8% overall test accuracy without overfitting. Even on single low-resolution images, accuracy among 15 views was 91.7% vs. 70.2-84.0% for board-certified echocardiographers. Data visualization experiments showed that the model recognizes similarities among related views and classifies using clinically relevant image features. Our results provide a foundation for artificial intelligence-assisted echocardiographic interpretation.