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

• Published in: Bioinformatics (Oxford, England) England), 2024-12, Vol.41 (1)
• Main Authors: Sergouniotis, Panagiotis I, Diakite, Adam, Gaurav, Kumar, Birney, Ewan, Fitzgerald, Tomas
• Format: Article
• Language: English
• Subjects: Biomarkers; Deep Learning; Genetic Loci; Genome-Wide Association Study - methods; Glaucoma - diagnostic imaging; Glaucoma - genetics; Humans; Original Paper; Phenotype; Polymorphism, Single Nucleotide; Retina - diagnostic imaging; Tomography, Optical Coherence - methods
• ISSN: 1367-4811; 1367-4803; 1367-4811
• DOI: 10.1093/bioinformatics/btae732

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. We used an autoencoder to represent retinal optical coherence tomography (OCT) images from 31 135 UK Biobank participants. For each subject, we obtained a 64-dimensional vector representing features of retinal structure. GWAS of these autoencoder-derived imaging parameters identified 118 statistically significant loci; 41 of these associations were also significant in a replication study. These loci encompassed variants previously linked with retinal thickness measurements, ophthalmic disorders, and/or neurodegenerative conditions. Notably, the generated retinal phenotypes were found to contribute to predictive models for glaucoma and cardiovascular disorders. Overall, we demonstrate that self-supervised phenotyping of OCT images enhances the discoverability of genetic factors influencing retinal morphology and provides epidemiologically informative biomarkers. Code and data links available at https://github.com/tf2/autoencoder-oct.