Want to take quizzes and track your credits?
Can deep learning be used to synthesize fundus images of age-related macular degeneration (AMD) that appear realistic to retinal specialists?
In this study of fundus images from 4613 study participants from the Age-Related Eye Disease Study and 133 821 fundus images, the ability of 2 retinal specialists to distinguish real from synthetic fundus images of varying stages of AMD was close to chance, and their diagnostic accuracy similar for real and synthetic images. Machines trained with only synthetic images showed performance nearing that resulting from training on real images.
These findings suggest that deep-learning–synthesized fundus images of AMD are realistic and could be used for education of humans across various levels of expertise and for machine training.
Deep learning (DL) used for discriminative tasks in ophthalmology, such as diagnosing diabetic retinopathy or age-related macular degeneration (AMD), requires large image data sets graded by human experts to train deep convolutional neural networks (DCNNs). In contrast, generative DL techniques could synthesize large new data sets of artificial retina images with different stages of AMD. Such images could enhance existing data sets of common and rare ophthalmic diseases without concern for personally identifying information to assist medical education of students, residents, and retinal specialists, as well as for training new DL diagnostic models for which extensive data sets from large clinical trials of expertly graded images may not exist.
To develop DL techniques for synthesizing high-resolution realistic fundus images serving as proxy data sets for use by retinal specialists and DL machines.
Design, Setting, and Participants
Generative adversarial networks were trained on 133 821 color fundus images from 4613 study participants from the Age-Related Eye Disease Study (AREDS), generating synthetic fundus images with and without AMD. We compared retinal specialists’ ability to diagnose AMD on both real and synthetic images, asking them to assess image gradability and testing their ability to discern real from synthetic images. The performance of AMD diagnostic DCNNs (referable vs not referable AMD) trained on either all-real vs all-synthetic data sets was compared.
Main Outcomes and Measures
Accuracy of 2 retinal specialists (T.Y.A.L. and K.D.P.) for diagnosing and distinguishing AMD on real vs synthetic images and diagnostic performance (area under the curve) of DL algorithms trained on synthetic vs real images.
The diagnostic accuracy of 2 retinal specialists on real vs synthetic images was similar. The accuracy of diagnosis as referable vs nonreferable AMD compared with certified human graders for retinal specialist 1 was 84.54% (error margin, 4.06%) on real images vs 84.12% (error margin, 4.16%) on synthetic images and for retinal specialist 2 was 89.47% (error margin, 3.45%) on real images vs 89.19% (error margin, 3.54%) on synthetic images. Retinal specialists could not distinguish real from synthetic images, with an accuracy of 59.50% (error margin, 3.93%) for retinal specialist 1 and 53.67% (error margin, 3.99%) for retinal specialist 2. The DCNNs trained on real data showed an area under the curve of 0.9706 (error margin, 0.0029), and those trained on synthetic data showed an area under the curve of 0.9235 (error margin, 0.0045).
Conclusions and Relevance
Deep learning–synthesized images appeared to be realistic to retinal specialists, and DCNNs achieved diagnostic performance on synthetic data close to that for real images, suggesting that DL generative techniques hold promise for training humans and machines.
Sign in to take quiz and track your certificates
JN Learning™ is the home for CME and MOC from the JAMA Network. Search by specialty or US state and earn AMA PRA Category 1 CME Credit™ from articles, audio, Clinical Challenges and more. Learn more about CME/MOC
Accepted for Publication: October 23, 2018.
Published Online: January 10, 2019. doi:10.1001/jamaophthalmol.2018.6156
Correction: This article was corrected on February 14, 2019, to fix errors in the text, Table 2, and the supplement.
Corresponding Author: Neil M. Bressler, MD, Wilmer Eye Institute, Johns Hopkins University, 600 N Wolfe St, Maumenee 752, Baltimore, MD 21287-9227 (firstname.lastname@example.org).
Author Contributions: Dr Burlina and Mr Joshi had full access to all the data in the study and take full responsibility for the integrity of the data and the accuracy of the data analysis.
Concept and design: Burlina, Joshi.
Study concept and design: Bressler.
Acquisition, analysis, or interpretation of data: All authors.
Drafting of the manuscript: Burlina, Joshi, Pacheco, Liu.
Critical revision of the manuscript for important intellectual content: Burlina, Liu, Bressler.
Statistical analysis: Burlina, Joshi.
Obtained funding: Burlina, Bressler.
Administrative, technical, or material support: Burlina, Joshi, Bressler.
Conflict of Interest: Dr Burlina reported a patent to a system and method for detecting and classifying severity of retinal disease issued and a patent to a system and method for automated detection of age-related macular degeneration issued. Dr Bressler reported grants from Bayer, Genentech/Roche, Novartis, the National Institutes of Health, and Samsung Bioepis outside the submitted work and a patent for automated detection of retinal diseases issued. No other disclosures were reported.
Funding/Support: This work was supported in part by award R21EY024310 from the National Eye Institute (Drs Burlina and Bressler), the Johns Hopkins Applied Physics Laboratory, the James P. Gills Professorship, and unrestricted research funds to the Johns Hopkins University School of Medicine Retina Division for Macular Degeneration and Related Diseases Research.
Role of the Funder/Sponsor: The National Eye Institute and Johns Hopkins University had no role in the design and conduct of the study; collection, management, analysis, and interpretation of the data; preparation, review, or approval of the manuscript; and decision to submit the manuscript for publication.
Disclaimer: Dr Bressler is the editor of JAMA Ophthalmology, but he was not involved in the review process or the acceptance of the manuscript.
Additional Information: Answer to the Figure: The real images with referable age-related macular degeneration (AMD) (ie, with the intermediate or advanced stage of AMD as defined in the Age-Related Eye Disease Study) are A, C, and F. The synthetic images with referable AMD are B, D, and E.
You currently have no searches saved.