Deep learning of fundus and optical coherence tomography images enables identification of diverse genetic and environmental factors associated with eye aging

A, Le Goallec; Diai, S; Collin, S; Thouvenot, Vincent; Cj, Patel

doi:10.1101/2021.06.24.21259471

Cited by 5 publications

(2 citation statements)

References 117 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…45 Notably, an independent group separately identified our top GWAS candidate locus as the most significant locus. 46 This combined with previous studies showing ALK to be important for lifespan extension in flies 23 and our own experimental validation confirming improved ocular health in a fly homolog, Alk , is compelling evidence of a true biological signal in the GWAS.…”

Section: Discussionsupporting

confidence: 75%

Longitudinal fundus imaging and its genome-wide association analysis provide evidence for a human retinal aging clock

Ahadi

Wilson

Babenko

et al. 2022

Preprint

View full text Add to dashboard Cite

Biological age, distinct from an individual's chronological age, has been studied extensively through predictive aging clocks. However, these clocks have limited accuracy in short time-scales. Deep learning approaches on imaging datasets of the eye have proven powerful for a variety of quantitative phenotype inference tasks and provide an opportunity to explore organismal aging and tissue health. Here we trained deep learning models on fundus images from the EyePACS dataset to predict individuals' chronological age. These predictions led to the concept of a retinal aging clock, eyeAge, which we employed for a series of downstream longitudinal analyses. eyeAge was used to predict chronological age on timescales under a year using longitudinal fundus imaging data from a subset of patients. To further validate the model, it was applied to a separate cohort from the UK Biobank. The difference between individuals' eyeAge and their chronological age, hereafter eyeAgeAccel, was computed and used for genome-wide association analysis (GWAS). EyeAge predicted chronological age more accurately than other aging clocks (mean absolute error of 2.86 and 3.30 years on quality-filtered data from EyePACS and UKBiobank, respectively). Additionally, eyeAgeAccel was highly independent of blood marker-based measures of biological age (e.g. phenotypic age), maintaining an all-cause mortality hazard ratio of 1.026 even in the presence of phenotypic age. Longitudinal studies showed that the resulting models were able to predict individuals' aging, in time-scales less than a year, with 71% accuracy. The individual-specific component to this prediction was confirmed with the identification of multiple GWAS hits in the independent UK Biobank cohort. The knockdown of the fly homolog to the top hit, ALKAL2, which was previously shown to extend lifespan in flies, also slowed age-related decline in vision in flies. In conclusion, predicted age from retinal images can be used as a biomarker of biological aging that is independent from assessment based on blood markers. This study demonstrates the potential utility of a retinal aging clock for studying aging and age-related diseases and quantitatively measuring aging on very short time-scales, opening avenues for quick and actionable evaluation of gero-protective therapeutics.

show abstract

Section: Discussionsupporting

confidence: 75%

Longitudinal fundus imaging and its genome-wide association analysis provide evidence for a human retinal aging clock

Ahadi

Wilson

Babenko

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep learning approaches have been shown to be able to detect imaging patterns that are not amenable to human identification and which can assist with prediction tasks (Radhakrishnan 2023). For example, neural networks can predict sex and age with good accuracy from retinal OCT images (Chueh 2022; Le Goallec 2022) whereas human experts find these tasks impossible. Here, we investigated if autoencoders can identify OCT parameters that can be used to predict health outcomes (glaucoma and cardiovascular disease).…”

Section: Discussionmentioning

confidence: 99%

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

Sergouniotis

Diakité

Gaurav

et al. 2023

Preprint

View full text Add to dashboard Cite

Genome-wide association studies (GWAS) have been remarkably successful in identifying associations between genetic variation and imaging-derived phenotypes. To date, the main focus of these analyses has been established, clinically-used imaging features. Here, we sought to investigate if deep learning approaches can help detect more nuanced patterns of image variability. To this end, we used an autoencoder to represent retinal optical coherence tomography (OCT) images from 31,135 UK Biobank participants. For each study subject, we obtained a 64-dimensional vector representing features of retinal structure. GWAS of these autoencoder-derived imaging parameters identified 113 genome-wide-significant loci. These encompassed variants previously linked with retinal thickness measurements, ophthalmic disorders and/or neurodegenerative conditions (including dementia). 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.

show abstract

Using deep learning to predict abdominal age from liver and pancreas magnetic resonance images

Diai

Collin

et al. 2022

Nat Commun

Self Cite

View full text Add to dashboard Cite

With age, the prevalence of diseases such as fatty liver disease, cirrhosis, and type two diabetes increases. Approaches to both predict abdominal age and identify risk factors for accelerated abdominal age may ultimately lead to advances that will delay the onset of these diseases. We build an abdominal age predictor by training convolutional neural networks to predict abdominal age (or “AbdAge”) from 45,552 liver magnetic resonance images [MRIs] and 36,784 pancreas MRIs (R-Squared = 73.3 ± 0.6; mean absolute error = 2.94 ± 0.03 years). Attention maps show that the prediction is driven by both liver and pancreas anatomical features, and surrounding organs and tissue. Abdominal aging is a complex trait, partially heritable (h_g2 = 26.3 ± 1.9%), and associated with 16 genetic loci (e.g. in PLEKHA1 and EFEMP1), biomarkers (e.g body impedance), clinical phenotypes (e.g, chest pain), diseases (e.g. hypertension), environmental (e.g smoking), and socioeconomic (e.g education, income) factors.

show abstract

Deep learning of fundus and optical coherence tomography images enables identification of diverse genetic and environmental factors associated with eye aging

Cited by 5 publications

References 117 publications

Longitudinal fundus imaging and its genome-wide association analysis provide evidence for a human retinal aging clock

Longitudinal fundus imaging and its genome-wide association analysis provide evidence for a human retinal aging clock

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

Using deep learning to predict abdominal age from liver and pancreas magnetic resonance images

Contact Info

Product

Resources

About