ARTIFICIAL INTELLIGENCE IN RETINA: Edited by Judy E. Kim and Ehsan RahimyGenerative adversarial networks in ophthalmology: what are these and how can they be used?Wang, Zhaorana,∗; Lim, Gilberta,b,∗; Ng, Wei Yana,b; Keane, Pearse A.c; Campbell, J. Peterd; Tan, Gavin Siew Weia,b; Schmetterer, Leopolda,b,e,f,g,h,i; Wong, Tien Yina,b; Liu, Yongc; Ting, Daniel Shu Weia,b Author Information aDuke-NUS Medical School, National University of Singapore bSingapore Eye Research Institute, Singapore, Singapore National Eye Centre, Singapore cInstitute of High Performance Computing, Agency for Science, Technology and Research (A∗STAR), Singapore dDepartment of Ophthalmology, Casey Eye Institute, Oregon Health & Science University, Portland, Oregon, USA eSERI-NTU Advanced Ocular Engineering (STANCE) fSchool of Chemical and Biomedical Engineering, Nanyang Technological University, Singapore gInstitute of Molecular and Clinical Ophthalmology Basel, Basel, Switzerland hDepartment of Clinical Pharmacology iCenter for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria Correspondence to Daniel Shu Wei Ting, MD, PhD, Consultant, Surgical Retina Department, Singapore National Eye Centre, Singapore, Assistant Professor, Duke-National University of Singapore Medical School, Singapore, 11 Third Hospital Avenue, Singapore 168751, Singapore. Tel: +65 6227 7255; e-mail: [email protected] Current Opinion in Ophthalmology 32(5):p 459-467, September 2021. | DOI: 10.1097/ICU.0000000000000794 Buy Metrics Abstract Purpose of review The development of deep learning (DL) systems requires a large amount of data, which may be limited by costs, protection of patient information and low prevalence of some conditions. Recent developments in artificial intelligence techniques have provided an innovative alternative to this challenge via the synthesis of biomedical images within a DL framework known as generative adversarial networks (GANs). This paper aims to introduce how GANs can be deployed for image synthesis in ophthalmology and to discuss the potential applications of GANs-produced images. Recent findings Image synthesis is the most relevant function of GANs to the medical field, and it has been widely used for generating ‘new’ medical images of various modalities. In ophthalmology, GANs have mainly been utilized for augmenting classification and predictive tasks, by synthesizing fundus images and optical coherence tomography images with and without pathologies such as age-related macular degeneration and diabetic retinopathy. Despite their ability to generate high-resolution images, the development of GANs remains data intensive, and there is a lack of consensus on how best to evaluate the outputs produced by GANs. Summary Although the problem of artificial biomedical data generation is of great interest, image synthesis by GANs represents an innovation with yet unclear relevance for ophthalmology. Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.