Synthetic Medical Images from Dual Generative Adversarial Networks

TL;DR

This paper introduces a dual-GAN pipeline for generating realistic synthetic medical images, aiming to address data scarcity and privacy issues in medical imaging research, exemplified on retinal fundi images.

Contribution

The paper presents a novel hierarchical two-stage GAN approach for synthetic medical image generation, facilitating public access to private data and advancing imaging research.

Findings

Successful generation of realistic retinal fundi images

Development of SynthMed, an online repository for synthetic images

Potential to enhance medical imaging research with synthetic data

Abstract

Currently there is strong interest in data-driven approaches to medical image classification. However, medical imaging data is scarce, expensive, and fraught with legal concerns regarding patient privacy. Typical consent forms only allow for patient data to be used in medical journals or education, meaning the majority of medical data is inaccessible for general public research. We propose a novel, two-stage pipeline for generating synthetic medical images from a pair of generative adversarial networks, tested in practice on retinal fundi images. We develop a hierarchical generation process to divide the complex image generation task into two parts: geometry and photorealism. We hope researchers will use our pipeline to bring private medical data into the public domain, sparking growth in imaging tasks that have previously relied on the hand-tuning of models. We have begun this initiative through the development of SynthMed, an online repository for synthetic medical images.