Video Representation Learning of Cardiac MRI for Genetic Discovery

Matt Sooknah, Sivaramakrishnan Sankarapandian, Ramprakash Srinivasan, Johannes Riegler, Jun Xu

Keywords: representation learning, medical imaging, target discovery, masked autoencoders, cardiac MRI

TL;DR: We apply self-supervised video representation learning to cardiac MRI scans and use the resulting embeddings to predict cardiac function, discover disease-enriched subpopulations and identify genetic targets.

Abstract: In recent years, many studies have utilized cardiac magnetic resonance imaging (cMRI) to define image-derived phenotypes (IDPs) relating to heart structure and function for genome-wide association studies (GWAS). These IDPs are traditionally defined manually from volume, strain, and geometric parameters. Here we introduce an unsupervised learning approach that extracts spatiotemporal representations from cMRI videos in a large human cohort of ~68,000 subjects from the UK BioBank. The resulting representations can be used to predict age and manually crafted IDPs accurately. We further use these representations to define IDPs to capture both known and potential novel genetic associations. Our work suggests that unsupervised learning can be used to extract rich, unbiased information from medical videos with applications to genetic discovery.

Submission Number: 49