Generative Adversarial Networks in Medical Image Processing

Author(s): Meiqin Gong, Siyu Chen, Qingyuan Chen, Yuanqi Zeng, Yongqing Zhang*

Journal Name: Current Pharmaceutical Design

Volume 27 , Issue 15 , 2021

Become EABM
Become Reviewer
Call for Editor


Background: The emergence of generative adversarial networks (GANs) has provided new technology and framework for the application of medical images. Specifically, a GAN requires little to no labeled data to obtain high-quality data that can be generated through competition between the generator and discriminator networks. Therefore, GANs are rapidly proving to be a state-of-the-art foundation, achieving enhanced performances in various medical applications.

Methods: In this article, we introduce the principles of GANs and their various variants, deep convolutional GAN, conditional GAN, Wasserstein GAN, Info-GAN, boundary equilibrium GAN, and cycle-GAN.

Results: All various GANs have found success in medical imaging tasks, including medical image enhancement, segmentation, classification, reconstruction, and synthesis. Furthermore, we summarize the data processing methods and evaluation indicators. Finally, we note the limitations of existing methods and the existing challenges that need to be addressed in this field.

Conclusion: Although GANs are in the initial stage of development in medical image processing, it will have a great prospect in the future.

Keywords: Generative adversarial networks, medical image processing, deep learning, segmentation, reconstruction, synthesis.

Rights & PermissionsPrintExport Cite as

Article Details

Year: 2021
Published on: 31 May, 2021
Page: [1856 - 1868]
Pages: 13
DOI: 10.2174/1381612826666201125110710
Price: $65

Article Metrics

PDF: 150