Generative adversarial networks and adversarial methods in biomedical image analysis

TL;DR

This paper reviews the application of generative adversarial networks and adversarial methods in biomedical image analysis, discussing their benefits, limitations, and future research directions.

Contribution

It provides an overview of how GANs and adversarial techniques are used in biomedical imaging, highlighting their strengths and potential future developments.

Findings

GANs have been extensively used for synthesizing biomedical images

Adversarial methods have improved analysis tasks in biomedical imaging

The paper discusses limitations and future directions of adversarial methods

Abstract

Generative adversarial networks (GANs) and other adversarial methods are based on a game-theoretical perspective on joint optimization of two neural networks as players in a game. Adversarial techniques have been extensively used to synthesize and analyze biomedical images. We provide an introduction to GANs and adversarial methods, with an overview of biomedical image analysis tasks that have benefited from such methods. We conclude with a discussion of strengths and limitations of adversarial methods in biomedical image analysis, and propose potential future research directions.