GANs for Medical Image Synthesis: An Empirical Study

TL;DR

This study evaluates various GAN architectures for medical image synthesis, revealing that while some generate realistic images, none fully replicate the complexity of real medical datasets, impacting their utility for downstream tasks.

Contribution

It provides a comprehensive empirical comparison of multiple GANs across different medical imaging modalities, highlighting their strengths and limitations.

Findings

Some GANs produce images that can fool experts in visual tests.

GANs vary significantly in image quality and usefulness for medical tasks.

No GAN fully captures the complexity of real medical datasets.

Abstract

Generative Adversarial Networks (GANs) have become increasingly powerful, generating mind-blowing photorealistic images that mimic the content of datasets they were trained to replicate. One recurrent theme in medical imaging is whether GANs can also be effective at generating workable medical data as they are for generating realistic RGB images. In this paper, we perform a multi-GAN and multi-application study to gauge the benefits of GANs in medical imaging. We tested various GAN architectures from basic DCGAN to more sophisticated style-based GANs on three medical imaging modalities and organs namely : cardiac cine-MRI, liver CT and RGB retina images. GANs were trained on well-known and widely utilized datasets from which their FID score were computed to measure the visual acuity of their generated images. We further tested their usefulness by measuring the segmentation accuracy of a U-Net trained on these generated images. Results reveal that GANs are far from being equal as some are ill-suited for medical imaging applications while others are much better off. The top-performing GANs are capable of generating realistic-looking medical images by FID standards that can fool trained experts in a visual Turing test and comply to some metrics. However, segmentation results suggests that no GAN is capable of reproducing the full richness of a medical datasets.