Multi-omic spatial effects on high-resolution AI-derived retinal thickness

Jackson, VE; Wu, Y; Bonelli, R; Owen, JP; Scott, LW; Farashi, S; Kihara, Y; Gantner, ML; Egan, C; Williams, KM; Ansell, BRE; Tufail, A; Lee, AY; Bahlo, M

Author(s): Jackson, VE; Wu, Y; Bonelli, R; Owen, JP; Scott, LW; Farashi, S; Kihara, Y; Gantner, ML; Egan, C; Williams, KM; Ansell, BRE; Tufail, A; Lee, AY; Bahlo, M;
Details: Publication Year 2025-02-04,Volume 16,Issue #1,Page 1317
Journal Title: Nature Communications
Abstract: Retinal thickness is a marker of retinal health and more broadly, is seen as a promising biomarker for many systemic diseases. Retinal thickness measurements are procured from optical coherence tomography (OCT) as part of routine clinical eyecare. We processed the UK Biobank OCT images using a convolutional neural network to produce fine-scale retinal thickness measurements across > 29,000 points in the macula, the part of the retina responsible for human central vision. The macula is disproportionately affected by high disease burden retinal disorders such as age-related macular degeneration and diabetic retinopathy, which both involve metabolic dysregulation. Analysis of common genomic variants, metabolomic, blood and immune biomarkers, disease PheCodes and genetic scores across a fine-scale macular thickness grid, reveals multiple novel genetic loci including four on the X chromosome; retinal thinning associated with many systemic disorders including multiple sclerosis; and multiple associations to correlated metabolites that cluster spatially in the retina. We highlight parafoveal thickness to be particularly susceptible to systemic insults. These results demonstrate the gains in discovery power and resolution achievable with AI-leveraged analysis. Results are accessible using a bespoke web interface that gives full control to pursue findings.
Publisher: Springer Nature
Keywords: Humans; *Retina/metabolism/diagnostic imaging; *Tomography, Optical Coherence/methods; Male; Female; Macular Degeneration/genetics/diagnostic imaging/pathology; Diabetic Retinopathy/genetics/diagnostic imaging/pathology; Neural Networks, Computer; Middle Aged; Biomarkers; Aged; United Kingdom; Artificial Intelligence; Multiomics
Research Division(s): Genetics and Gene Regulation
PubMed ID: 39904976
Publisher's Version: https://doi.org/10.1038/s41467-024-55635-7
Open Access at Publisher's Site: https://doi.org/10.1038/s41467-024-55635-7
Terms of Use/Rights Notice: Refer to copyright notice on published article.

Creation Date: 2025-02-07 03:05:02

Last Modified: 2025-02-07 03:12:59