Deep learning: Generative adversarial networks and adversarial methods

Jelmer M. Wolterink, Konstantinos Kamnitsas, Christian Ledig, Ivana Išgum

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

5 Citations (Scopus)

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. This chapter provides 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.

Original languageEnglish
Title of host publicationHandbook of Medical Image Computing and Computer Assisted Intervention
Place of PublicationLondon
PublisherElsevier
Pages547-574
Number of pages28
ISBN (Print)978-0-12-816176-0
DOIs
Publication statusPublished - 1 Jan 2019
Externally publishedYes

Publication series

NameThe Elsevier and MICCAI Society book series
PublisherElsevier

Keywords

  • Adversarial methods
  • Deep learning
  • Generative adversarial networks

Fingerprint

Dive into the research topics of 'Deep learning: Generative adversarial networks and adversarial methods'. Together they form a unique fingerprint.

Cite this