Generative Adversarial Networks Synthesize Realistic OCT Images of the Retina

TL;DR

This paper demonstrates the first successful use of Generative Adversarial Networks to synthesize realistic retinal OCT images, including pathological features, with potential applications in medical training, diagnosis, and drug development.

Contribution

It introduces the first end-to-end GAN-based method for generating realistic OCT images of the retina, including various pathologies.

Findings

GANs can synthesize realistic retinal OCT images with recognizable pathology

Generated images include macular holes, choroidal neovascular membranes, and other conditions

Potential for use in surgical simulation and disease treatment planning

Abstract

We report, to our knowledge, the first end-to-end application of Generative Adversarial Networks (GANs) towards the synthesis of Optical Coherence Tomography (OCT) images of the retina. Generative models have gained recent attention for the increasingly realistic images they can synthesize, given a sampling of a data type. In this paper, we apply GANs to a sampling distribution of OCTs of the retina. We observe the synthesis of realistic OCT images depicting recognizable pathology such as macular holes, choroidal neovascular membranes, myopic degeneration, cystoid macular edema, and central serous retinopathy amongst others. This represents the first such report of its kind. Potential applications of this new technology include for surgical simulation, for treatment planning, for disease prognostication, and for accelerating the development of new drugs and surgical procedures to treat retinal disease.