Exploring Healthy Retinal Aging with Deep Learning
Purpose: To study the individual course of retinal changes caused by healthy aging using deep learning. Design: Retrospective analysis of a large data set of retinal OCT images. Participants: A total of 85 709 adults between the age of 40 and 75 years of whom OCT images were acquired in the scope of...
Main Authors: | , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-09-01
|
Series: | Ophthalmology Science |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S266691452300026X |
_version_ | 1797671429253103616 |
---|---|
author | Martin J. Menten, PhD Robbie Holland, MSc Oliver Leingang, PhD Hrvoje Bogunović, PhD Ahmed M. Hagag, MD Rebecca Kaye, MD Sophie Riedl, MD Ghislaine L. Traber, MD Osama N. Hassan, MSc Nick Pawlowski, PhD Ben Glocker, PhD Lars G. Fritsche, PhD Hendrik P.N. Scholl, MD Sobha Sivaprasad, MD Ursula Schmidt-Erfurth, MD Daniel Rueckert, PhD Andrew J. Lotery, MD |
author_facet | Martin J. Menten, PhD Robbie Holland, MSc Oliver Leingang, PhD Hrvoje Bogunović, PhD Ahmed M. Hagag, MD Rebecca Kaye, MD Sophie Riedl, MD Ghislaine L. Traber, MD Osama N. Hassan, MSc Nick Pawlowski, PhD Ben Glocker, PhD Lars G. Fritsche, PhD Hendrik P.N. Scholl, MD Sobha Sivaprasad, MD Ursula Schmidt-Erfurth, MD Daniel Rueckert, PhD Andrew J. Lotery, MD |
author_sort | Martin J. Menten, PhD |
collection | DOAJ |
description | Purpose: To study the individual course of retinal changes caused by healthy aging using deep learning. Design: Retrospective analysis of a large data set of retinal OCT images. Participants: A total of 85 709 adults between the age of 40 and 75 years of whom OCT images were acquired in the scope of the UK Biobank population study. Methods: We created a counterfactual generative adversarial network (GAN), a type of neural network that learns from cross-sectional, retrospective data. It then synthesizes high-resolution counterfactual OCT images and longitudinal time series. These counterfactuals allow visualization and analysis of hypothetical scenarios in which certain characteristics of the imaged subject, such as age or sex, are altered, whereas other attributes, crucially the subject’s identity and image acquisition settings, remain fixed. Main Outcome Measures: Using our counterfactual GAN, we investigated subject-specific changes in the retinal layer structure as a function of age and sex. In particular, we measured changes in the retinal nerve fiber layer (RNFL), combined ganglion cell layer plus inner plexiform layer (GCIPL), inner nuclear layer to the inner boundary of the retinal pigment epithelium (INL-RPE), and retinal pigment epithelium (RPE). Results: Our counterfactual GAN is able to smoothly visualize the individual course of retinal aging. Across all counterfactual images, the RNFL, GCIPL, INL-RPE, and RPE changed by −0.1 μm ± 0.1 μm, −0.5 μm ± 0.2 μm, −0.2 μm ± 0.1 μm, and 0.1 μm ± 0.1 μm, respectively, per decade of age. These results agree well with previous studies based on the same cohort from the UK Biobank population study. Beyond population-wide average measures, our counterfactual GAN allows us to explore whether the retinal layers of a given eye will increase in thickness, decrease in thickness, or stagnate as a subject ages. Conclusion: This study demonstrates how counterfactual GANs can aid research into retinal aging by generating high-resolution, high-fidelity OCT images, and longitudinal time series. Ultimately, we envision that they will enable clinical experts to derive and explore hypotheses for potential imaging biomarkers for healthy and pathologic aging that can be refined and tested in prospective clinical trials. Financial Disclosure(s): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article. |
first_indexed | 2024-03-11T21:15:24Z |
format | Article |
id | doaj.art-e0eb53ffa5f04287a5154c4856cf8732 |
institution | Directory Open Access Journal |
issn | 2666-9145 |
language | English |
last_indexed | 2024-03-11T21:15:24Z |
publishDate | 2023-09-01 |
publisher | Elsevier |
record_format | Article |
series | Ophthalmology Science |
spelling | doaj.art-e0eb53ffa5f04287a5154c4856cf87322023-09-29T04:45:19ZengElsevierOphthalmology Science2666-91452023-09-0133100294Exploring Healthy Retinal Aging with Deep LearningMartin J. Menten, PhD0Robbie Holland, MSc1Oliver Leingang, PhD2Hrvoje Bogunović, PhD3Ahmed M. Hagag, MD4Rebecca Kaye, MD5Sophie Riedl, MD6Ghislaine L. Traber, MD7Osama N. Hassan, MSc8Nick Pawlowski, PhD9Ben Glocker, PhD10Lars G. Fritsche, PhD11Hendrik P.N. Scholl, MD12Sobha Sivaprasad, MD13Ursula Schmidt-Erfurth, MD14Daniel Rueckert, PhD15Andrew J. Lotery, MD16BioMedIA, Imperial College London, London, United Kingdom; Institute for AI and Informatics in Medicine, Technical University of Munich, Munich, Germany; Correspondence: Martin J. Menten, Imperial College London, South Kensington Campus, SW7 2AZ, London, United Kingdom.BioMedIA, Imperial College London, London, United KingdomLaboratory for Ophthalmic Image Analysis, Medical University of Vienna, Vienna, AustriaLaboratory for Ophthalmic Image Analysis, Medical University of Vienna, Vienna, Austria; Christian Doppler Laboratory for Artificial Intelligence in Retina, Christian Doppler Forschungsgesellschaft, Vienna, AustriaInstitute of Ophthalmology, University College London, London, United Kingdom; Moorfields Eye Unit, National Institute for Health Research, London, United KingdomClinical and Experimental Sciences, Faculty of Medicine, University of Southampton, Southampton, United KingdomLaboratory for Ophthalmic Image Analysis, Medical University of Vienna, Vienna, AustriaInstitute of Molecular and Clinical Ophthalmology Basel, Basel, Switzerland; Department of Ophthalmology, University of Basel, Basel, SwitzerlandBioMedIA, Imperial College London, London, United KingdomBioMedIA, Imperial College London, London, United Kingdom; Microsoft Research, Cambridge, United KingdomBioMedIA, Imperial College London, London, United KingdomDepartment of Biostatistics, University of Michigan, Ann Arbor, MichiganInstitute of Molecular and Clinical Ophthalmology Basel, Basel, Switzerland; Department of Ophthalmology, University of Basel, Basel, SwitzerlandInstitute of Ophthalmology, University College London, London, United Kingdom; Moorfields Eye Unit, National Institute for Health Research, London, United KingdomLaboratory for Ophthalmic Image Analysis, Medical University of Vienna, Vienna, AustriaBioMedIA, Imperial College London, London, United Kingdom; Institute for AI and Informatics in Medicine, Technical University of Munich, Munich, GermanyClinical and Experimental Sciences, Faculty of Medicine, University of Southampton, Southampton, United KingdomPurpose: To study the individual course of retinal changes caused by healthy aging using deep learning. Design: Retrospective analysis of a large data set of retinal OCT images. Participants: A total of 85 709 adults between the age of 40 and 75 years of whom OCT images were acquired in the scope of the UK Biobank population study. Methods: We created a counterfactual generative adversarial network (GAN), a type of neural network that learns from cross-sectional, retrospective data. It then synthesizes high-resolution counterfactual OCT images and longitudinal time series. These counterfactuals allow visualization and analysis of hypothetical scenarios in which certain characteristics of the imaged subject, such as age or sex, are altered, whereas other attributes, crucially the subject’s identity and image acquisition settings, remain fixed. Main Outcome Measures: Using our counterfactual GAN, we investigated subject-specific changes in the retinal layer structure as a function of age and sex. In particular, we measured changes in the retinal nerve fiber layer (RNFL), combined ganglion cell layer plus inner plexiform layer (GCIPL), inner nuclear layer to the inner boundary of the retinal pigment epithelium (INL-RPE), and retinal pigment epithelium (RPE). Results: Our counterfactual GAN is able to smoothly visualize the individual course of retinal aging. Across all counterfactual images, the RNFL, GCIPL, INL-RPE, and RPE changed by −0.1 μm ± 0.1 μm, −0.5 μm ± 0.2 μm, −0.2 μm ± 0.1 μm, and 0.1 μm ± 0.1 μm, respectively, per decade of age. These results agree well with previous studies based on the same cohort from the UK Biobank population study. Beyond population-wide average measures, our counterfactual GAN allows us to explore whether the retinal layers of a given eye will increase in thickness, decrease in thickness, or stagnate as a subject ages. Conclusion: This study demonstrates how counterfactual GANs can aid research into retinal aging by generating high-resolution, high-fidelity OCT images, and longitudinal time series. Ultimately, we envision that they will enable clinical experts to derive and explore hypotheses for potential imaging biomarkers for healthy and pathologic aging that can be refined and tested in prospective clinical trials. Financial Disclosure(s): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.http://www.sciencedirect.com/science/article/pii/S266691452300026XAgingBiomarker discoveryDeep learningMachine learningRetina |
spellingShingle | Martin J. Menten, PhD Robbie Holland, MSc Oliver Leingang, PhD Hrvoje Bogunović, PhD Ahmed M. Hagag, MD Rebecca Kaye, MD Sophie Riedl, MD Ghislaine L. Traber, MD Osama N. Hassan, MSc Nick Pawlowski, PhD Ben Glocker, PhD Lars G. Fritsche, PhD Hendrik P.N. Scholl, MD Sobha Sivaprasad, MD Ursula Schmidt-Erfurth, MD Daniel Rueckert, PhD Andrew J. Lotery, MD Exploring Healthy Retinal Aging with Deep Learning Ophthalmology Science Aging Biomarker discovery Deep learning Machine learning Retina |
title | Exploring Healthy Retinal Aging with Deep Learning |
title_full | Exploring Healthy Retinal Aging with Deep Learning |
title_fullStr | Exploring Healthy Retinal Aging with Deep Learning |
title_full_unstemmed | Exploring Healthy Retinal Aging with Deep Learning |
title_short | Exploring Healthy Retinal Aging with Deep Learning |
title_sort | exploring healthy retinal aging with deep learning |
topic | Aging Biomarker discovery Deep learning Machine learning Retina |
url | http://www.sciencedirect.com/science/article/pii/S266691452300026X |
work_keys_str_mv | AT martinjmentenphd exploringhealthyretinalagingwithdeeplearning AT robbiehollandmsc exploringhealthyretinalagingwithdeeplearning AT oliverleingangphd exploringhealthyretinalagingwithdeeplearning AT hrvojebogunovicphd exploringhealthyretinalagingwithdeeplearning AT ahmedmhagagmd exploringhealthyretinalagingwithdeeplearning AT rebeccakayemd exploringhealthyretinalagingwithdeeplearning AT sophieriedlmd exploringhealthyretinalagingwithdeeplearning AT ghislaineltrabermd exploringhealthyretinalagingwithdeeplearning AT osamanhassanmsc exploringhealthyretinalagingwithdeeplearning AT nickpawlowskiphd exploringhealthyretinalagingwithdeeplearning AT benglockerphd exploringhealthyretinalagingwithdeeplearning AT larsgfritschephd exploringhealthyretinalagingwithdeeplearning AT hendrikpnschollmd exploringhealthyretinalagingwithdeeplearning AT sobhasivaprasadmd exploringhealthyretinalagingwithdeeplearning AT ursulaschmidterfurthmd exploringhealthyretinalagingwithdeeplearning AT danielrueckertphd exploringhealthyretinalagingwithdeeplearning AT andrewjloterymd exploringhealthyretinalagingwithdeeplearning |