Igwas: Image-Based Genome-Wide Association of Self-Supervised Deep Phenotyping of Retina Fundus Images

Authors

Ziqian Xie
Tao Zhang
Sangbae Kim
Jiaxiong Lu
Wanheng Zhang
Cheng-Hui Lin
Man-Ru Wu
Alexander Davis
Roomasa Channa
Luca Giancardo
Han Chen
Sui Wang
Rui Chen
Degui Zhi

Publication Date

5-1-2024

Journal

PLOS Genetics

Abstract

Existing imaging genetics studies have been mostly limited in scope by using imaging-derived phenotypes defined by human experts. Here, leveraging new breakthroughs in self-supervised deep representation learning, we propose a new approach, image-based genome-wide association study (iGWAS), for identifying genetic factors associated with phenotypes discovered from medical images using contrastive learning. Using retinal fundus photos, our model extracts a 128-dimensional vector representing features of the retina as phenotypes. After training the model on 40,000 images from the EyePACS dataset, we generated phenotypes from 130,329 images of 65,629 British White participants in the UK Biobank. We conducted GWAS on these phenotypes and identified 14 loci with genome-wide significance (p

Keywords

Humans, Genome-Wide Association Study, Phenotype, Retina, Fundus Oculi, Male, Polymorphism, Single Nucleotide, Female, Image Processing, Computer-Assisted

Comments

Supplementary Materials

PMID: 38728357