Meeting Banner
Abstract #4785

Real-World Clinical Performance of Deep Learning for Quantification and Segmentation of Biventricular Cardiac Size and Function

Tara Retson1, Evan Masutani2, Courtney Chen2, Jesse Lieman-Sifry3, Felix Lau3, Matthieu Le3, Sean Sall3, Daniel Golden3, and Albert Hsiao2

1Radiology, UC San Diego, San Diego, CA, United States, 2UC San Diego, San Diego, CA, United States, 3Arterys, Inc, San Francisco, CA, United States

In this study of routine clinical cardiac MRIs performed for a typical range of clinical indications, we examined the effectiveness of deep learning (DL) for real-world automated quantitative analysis of cardiac size and biventricular function. We find that automated measurements correlate well with skilled readers. While the variation between DL quantification and experts lie within the range seen between experts, there remain several observed failure modes which may benefit from expert supervision. The combination of DL automation with specialist oversight may reduce the time burden of manual segmentation, improve physician efficiency, and promote technique accessibility.

This abstract and the presentation materials are available to members only; a login is required.

Join Here