Application of DatasetGAN in medical imaging: preliminary studies

TL;DR

This paper explores the potential of DatasetGAN, a GAN-based framework, for generating annotated medical images with segmentation, through preliminary studies including visual evaluation and segmentation performance analysis.

Contribution

The study introduces three modifications to DatasetGAN tailored for medical images and evaluates its effectiveness for medical imaging applications.

Findings

Synthesized images were visually convincing.

Segmentation performance improved with DatasetGAN-generated data.

Potential for reducing annotation effort in medical imaging.

Abstract

Generative adversarial networks (GANs) have been widely investigated for many potential applications in medical imaging. DatasetGAN is a recently proposed framework based on modern GANs that can synthesize high-quality segmented images while requiring only a small set of annotated training images. The synthesized annotated images could be potentially employed for many medical imaging applications, where images with segmentation information are required. However, to the best of our knowledge, there are no published studies focusing on its applications to medical imaging. In this work, preliminary studies were conducted to investigate the utility of DatasetGAN in medical imaging. Three improvements were proposed to the original DatasetGAN framework, considering the unique characteristics of medical images. The synthesized segmented images by DatasetGAN were visually evaluated. The trained DatasetGAN was further analyzed by evaluating the performance of a pre-defined image segmentation technique, which was trained by the use of the synthesized datasets. The effectiveness, concerns, and potential usage of DatasetGAN were discussed.