Synthetic Medical Images from Dual Generative Adversarial Networks

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.

First two authors contributed equally. Accepted to NIPS 2017 Workshops on Medical Imaging and Machine Learning for Health

Cited by in corpus (13)

• Free-form tumor synthesis in computed tomography images via richer generative adversarial network
• Generative adversarial networks in time series: A survey and taxonomy
• Unsupervised Medical Image Segmentation with Adversarial Networks: From Edge Diagrams to Segmentation Maps
• Synthesizing brain tumor images and annotations by combining progressive growing GAN and SPADE
• Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesis
• Ebola Optimization Search Algorithm (EOSA): A new metaheuristic algorithm based on the propagation model of Ebola virus disease
• TricycleGAN: Unsupervised Image Synthesis and Segmentation Based on Shape Priors
• Ensembles of GANs for synthetic training data generation
• G2R Bound: A Generalization Bound for Supervised Learning from GAN-Synthetic Data
• Semi-supervised mp-MRI Data Synthesis with StitchLayer and Auxiliary Distance Maximization
• Synthesizing New Retinal Symptom Images by Multiple Generative Models
• Multimodal Medical Volume Colorization from 2D Style
• Downhole Track Detection via Multiscale Conditional Generative Adversarial Nets