PT  - JOURNAL ARTICLE
AU  - Amirata Ghorbani
AU  - David Ouyang
AU  - Abubakar Abid
AU  - Bryan He
AU  - Jonathan H. Chen
AU  - Robert A. Harrington
AU  - David H. Liang
AU  - Euan A. Ashley
AU  - James Y. Zou
TI  - Deep Learning Interpretation of Echocardiograms
AID  - 10.1101/681676
DP  - 2019 Jan 01
TA  - bioRxiv
PG  - 681676
4099  - http://biorxiv.org/content/early/2019/06/24/681676.short
4100  - http://biorxiv.org/content/early/2019/06/24/681676.full
AB  - Echocardiography uses ultrasound technology to capture high temporal and spatial resolution images of the heart and surrounding structures and is the most common imaging modality in cardiovascular medicine. Using convolutional neural networks on a large new dataset, we show that deep learning applied to echocardiography can identify local cardiac structures, estimate cardiac function, and predict systemic phenotypes that modify cardiovascular risk but not readily identifiable to human interpretation. Our deep learning model, EchoNet, accurately identified the presence of pacemaker leads (AUC = 0.89), enlarged left atrium (AUC = 0.85), normal left ventricular wall thickness (AUC = 0.75), left ventricular end systolic and diastolic volumes(R2 = 0.73 and R2 = 0.68), and ejection fraction (R2 = 0.48) as well as predicted systemic phenotypes of age (R2 = 0.46), sex (AUC = 0.88), weight (R2 = 0.56), and height (R2 = 0.33). Interpretation analysis validates that EchoNet shows appropriate attention to key cardiac structures when performing human-explainable tasks and highlight hypothesis-generating regions of interest when predicting systemic phenotypes difficult for human interpretation. Machine learning on echocardiography images can streamline repetitive tasks in the clinical workflow, standardize interpretation in areas with insufficient qualified cardiologists, and more consistently produce echocardiographic measurements.