Deep learning for diagnosis of cardiac disease from a small dataset of echocardiogram videos

Abstract

The development of deep learning algorithms usually requires large labeled training datasets. However, some kind of medical data, such as the echocardiogram videos of cardiac sarcoidosis, is highly difficult to collect. The purpose of this study was to develop a deep learning model to detect cardiac sarcoidosis using a small dataset of 302 echocardiogram videos. We compared several different model architectures including 2D and 3D models, and also discussed the effect of pretraining on a large open dataset of echocardiogram videos. We found that 3D models outperforms 2D models, and the pretraining improved the performance of the model from an AUC of 0.761 (95% CI 0.610, 0.911) to 0.841 (95% CI 0.716, 0.968).