Deep learning: Generative adversarial networks and adversarial methods

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

doi:10.1016/B978-0-12-816176-0.00028-4

Deep learning: Generative adversarial networks and adversarial methods

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

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic › peer-review

7 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 language	English
Title of host publication	Handbook of Medical Image Computing and Computer Assisted Intervention
Place of Publication	London
Publisher	Elsevier
Pages	547-574
Number of pages	28
ISBN (Print)	978-0-12-816176-0
DOIs	https://doi.org/10.1016/B978-0-12-816176-0.00028-4
Publication status	Published - 1 Jan 2019
Externally published	Yes

Publication series

Name	The Elsevier and MICCAI Society book series
Publisher	Elsevier

Keywords

Adversarial methods
Deep learning
Generative adversarial networks

Access to Document

10.1016/B978-0-12-816176-0.00028-4

Cite this

@inbook{d6de8bbddbb14886b01a345750ea82e6,

title = "Deep learning: Generative adversarial networks and 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. 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.",

keywords = "Adversarial methods, Deep learning, Generative adversarial networks",

author = "Wolterink, {Jelmer M.} and Konstantinos Kamnitsas and Christian Ledig and Ivana I{\v s}gum",

year = "2019",

month = jan,

day = "1",

doi = "10.1016/B978-0-12-816176-0.00028-4",

language = "English",

isbn = "978-0-12-816176-0",

series = "The Elsevier and MICCAI Society book series",

publisher = "Elsevier",

pages = "547--574",

booktitle = "Handbook of Medical Image Computing and Computer Assisted Intervention",

address = "Netherlands",

}

Deep learning : Generative adversarial networks and adversarial methods. / Wolterink, Jelmer M.; Kamnitsas, Konstantinos; Ledig, Christian et al.

Handbook of Medical Image Computing and Computer Assisted Intervention. London : Elsevier, 2019. p. 547-574 (The Elsevier and MICCAI Society book series).

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic › peer-review

TY - CHAP

T1 - Deep learning

T2 - Generative adversarial networks and adversarial methods

AU - Wolterink, Jelmer M.

AU - Kamnitsas, Konstantinos

AU - Ledig, Christian

AU - Išgum, Ivana

PY - 2019/1/1

Y1 - 2019/1/1

N2 - 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.

AB - 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.

KW - Adversarial methods

KW - Deep learning

KW - Generative adversarial networks

UR - http://www.scopus.com/inward/record.url?scp=85082621182&partnerID=8YFLogxK

U2 - 10.1016/B978-0-12-816176-0.00028-4

DO - 10.1016/B978-0-12-816176-0.00028-4

M3 - Chapter

AN - SCOPUS:85082621182

SN - 978-0-12-816176-0

T3 - The Elsevier and MICCAI Society book series

SP - 547

EP - 574

BT - Handbook of Medical Image Computing and Computer Assisted Intervention

PB - Elsevier

CY - London

ER -

Deep learning: Generative adversarial networks and adversarial methods

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

Cite this