Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2020 May 12:8:164.
doi: 10.3389/fpubh.2020.00164. eCollection 2020.

Generative Adversarial Networks and Its Applications in Biomedical Informatics

Lan Lan  1 , Lei You  2 , Zeyang Zhang  3 , Zhiwei Fan  4 , Weiling Zhao  2 , Nianyin Zeng  5 , Yidong Chen  6 , Xiaobo Zhou  2
Affiliations
Review

Generative Adversarial Networks and Its Applications in Biomedical Informatics

Lan Lan et al. Front Public Health. .

Abstract

The basic Generative Adversarial Networks (GAN) model is composed of the input vector, generator, and discriminator. Among them, the generator and discriminator are implicit function expressions, usually implemented by deep neural networks. GAN can learn the generative model of any data distribution through adversarial methods with excellent performance. It has been widely applied to different areas since it was proposed in 2014. In this review, we introduced the origin, specific working principle, and development history of GAN, various applications of GAN in digital image processing, Cycle-GAN, and its application in medical imaging analysis, as well as the latest applications of GAN in medical informatics and bioinformatics.

Keywords: Generative Adversarial Networks (GAN); biomedical applications; data augmentation; discriminator; generator; image conversion.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Digital image diagram of GAN.
Figure 2
Figure 2
The architecture of Cycle-GAN.
Figure 3
Figure 3
The experiment results from Cycle-GAN, where real B is the real MRI image, fake A is the generated CT image based on the real MRI image, and rec B is the reconstructed MRI image based on the generated CT image of heart for a patient.
Figure 4
Figure 4
The architecture of LSTM-based GAN in medical informatics.
Figure 5
Figure 5
Bioinformatics diagram of GAN.
See this image and copyright information in PMC

References

    1. Goodfellow IJ, Pouget-Abadie J, Mirza M, Bing X, Warde-Farley D, Ozair S, et al. Generative Adversarial Nets. In: International Conference on Neural Information Processing Systems Montréal, QC: (2014).
    1. Lin Y, Dai X, Li L, Wang X, Wang F. The new Frontier of AI research: generative adversarial networks. Acta Autom Sin. (2018) 44:775–92. 10.16383/j.aas.2018.y000002 - DOI
    1. Zhang Z, Zhou X, Zhao S, Zhang X. Semantic prior guided face inpainting. In: Zhang Z, Zhou X, Zhao S, Zhang X, editors. MMAsia '19. New York, NY: (2019).
    1. Hiasa Y, Otake Y, Takao M, Matsuoka T, Sato Y. Cross-modality image synthesis from unpaired data using CycleGAN: effects of gradient consistency loss and training data size. In: Goksel O, Oguz I, Gooya A, Burgos N, editors. Simulation and Synthesis in Medical Imaging - Third International Workshop, SASHIMI 2018, Held in Conjunction with MICCAI 2018, Proceedings. Granada: Springer verlag; (2018).
    1. Zhu JY, Park T, Isola P, Efros AA. Unpaired image-to-image translation using cycle-consistent adversarial networks. In: IEEE International Conference on Computer Vision. Venice: (2017).

MeSH terms

LinkOut - more resources