Autoencoder-based phenotyping of ophthalmic images highlights genetic loci influencing retinal morphology and provides informative biomarkers

Abstract excerpt

MOTIVATION: Genome-wide association studies (GWAS) have been remarkably successful in identifying associations between genetic variants and imaging-derived phenotypes. To date, the main focus of these analyses has been on established, clinically-used imaging features. We sought to investigate if deep learning approaches can detect more nuanced patterns of image variability. RESULTS: We used an autoencoder to...

Topics

Share this publication in a Topic to start or enrich a Post.

• Share to Glaucoma and retinal disorders
• Share to Retinal Development and Disorders
• Share to Retinal Imaging and Analysis