Generating Highly Realistic Images of Skin Lesions with GANs

TL;DR

This paper demonstrates the use of progressive growing GANs to generate high-resolution, realistic skin lesion images, addressing data scarcity and class imbalance in medical image analysis.

Contribution

It introduces a high-resolution skin lesion image synthesis method using progressive growing GANs, outperforming other architectures like DCGAN and LAPGAN.

Findings

Generated images are highly realistic and difficult for experts to distinguish from real images.

Progressive growing GANs outperform other architectures in quality of synthesized images.

Synthesized images can potentially augment training datasets for skin lesion analysis.

Abstract

As many other machine learning driven medical image analysis tasks, skin image analysis suffers from a chronic lack of labeled data and skewed class distributions, which poses problems for the training of robust and well-generalizing models. The ability to synthesize realistic looking images of skin lesions could act as a reliever for the aforementioned problems. Generative Adversarial Networks (GANs) have been successfully used to synthesize realistically looking medical images, however limited to low resolution, whereas machine learning models for challenging tasks such as skin lesion segmentation or classification benefit from much higher resolution data. In this work, we successfully synthesize realistically looking images of skin lesions with GANs at such high resolution. Therefore, we utilize the concept of progressive growing, which we both quantitatively and qualitatively compare to other GAN architectures such as the DCGAN and the LAPGAN. Our results show that with the help of progressive growing, we can synthesize highly realistic dermoscopic images of skin lesions that even expert dermatologists find hard to distinguish from real ones.