Generative Adversarial Networks in Medical Imaging: Applications, Challenges, and Emerging Trends (2020–2025)

DOI

10.2991/978-94-6239-648-7_86How to use a DOI?

Keywords

Generative Adversarial Networks; Medical Imaging; Image Synthesis

Abstract

Generative Adversarial Networks (GANs) have developed into an important class of generative models in medical imaging, providing distinct properties for problems that are difficult because of limited data and costly annotation. In 2020–2025, GANs have also shifted from basic augmentation to more advanced tasks such as, image generation, cross-domain translations, super-resolution reconstructions, as well as data generation within domain-specific applications of medical imaging, for example, ophthalmology and neuroimaging. Although there has been ongoing progress in GAN implementations, challenges remain that are inherent to GANs, such as training instabilities, and mode collapse in training, and clinically meaningful evaluation measures have not yet evolved. Additionally, diffusion models have become increasingly popular in the generative modeling landscape and have led to some studies that highlight the benefits and limitations of GANs. This review aims to summarize the development and application of GANs in medical imaging, highlighting relevant technical and practice problems and trends including, hybrid GAN-diffusion architectures, clinical empirically-based proof methods, ethics, and explainability. Our analysis concludes that there will continue to be ongoing GAN development alongside novel generative models; however, GANs will remain a relevant and practical approach in the bounded environment of medical imaging computing.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Taoyu Chen
PY  - 2026
DA  - 2026/04/24
TI  - Generative Adversarial Networks in Medical Imaging: Applications, Challenges, and Emerging Trends (2020–2025)
BT  - Proceedings of the International Workshop on Advances in Deep Learning for Image Analysis and Computer Vision (IWADIC 2025)
PB  - Atlantis Press
SP  - 795
EP  - 804
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6239-648-7_86
DO  - 10.2991/978-94-6239-648-7_86
ID  - Chen2026
ER  -