查看文章

Machine learning analysis of biomedical images has seen significant recent advances. In contrast, there has been much less work on medical videos, despite the fact that videos are routinely used in many clinical settings. A major bottleneck for this is the the lack of openly available and well annotated medical video data. Computer vision has benefited greatly from many open databases which allow for collaboration, comparison, and creation of medical task specific architectures. We present the EchoNet-Dynamic Dataset of 10,036 echocardiography videos, spanning the range of typical echocardiography lab imaging conditions, with corresponding labeled measurements including ejection fraction, left ventricular volume at end-systole and end-diastole, and human expert tracings of the left ventricle as an aid in studying automated approaches to evaluate cardiac function. We additionally present the performance of three 3D convolutional architectures for video classification used to assess ejection fraction to near-expert human performance and as a benchmark for further collaboration, comparison, and creation of task-specific architectures. To the best of our knowledge, this is the largest labeled medical video dataset made available publicly to researchers and medical professionals and first public report of video-based 3D convolutional architectures to assess cardiac function.