Generative Adversarial Networks (GANs) for Retinal Fundus Image Synthesis

The lack of access to large annotated datasets and legal concerns regarding patient privacyare limiting factorsfor many applications of deep learning in the retinalimage analysis domain. Therefore the idea of generating synthetic retinalimages, indiscerniblefrom real data, has gained more interest. Generative adversarial networks (GANs) have proven to be a valuable framework for producing synthetic databases of anatomically consistent retinalfundus images. In Ophthalmology, GANs in particular have shown increased interest. We discuss here the potential advantages and limitations that need to be addressed before GANs can be widely adopted for retinalimaging.