Unsupervised learning for cross-domain medical image synthesis using deformation invariant cycle consistency networks

Chengjia Wang*, Gillian Macnaught, Giorgos Papanastasiou, Tom MacGillivray, David Newby

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

23 Citations (Scopus)

Abstract

Recently, the cycle-consistent generative adversarial networks (CycleGAN) has been widely used for synthesis of multi-domain medical images. The domain-specific nonlinear deformations captured by CycleGAN make the synthesized images difficult to be used for some applications, for example, generating pseudo-CT for PET-MR attenuation correction. This paper presents a deformation-invariant CycleGAN (DicycleGAN) method using deformable convolutional layers and new cycle-consistency losses. Its robustness dealing with data that suffer from domain-specific nonlinear deformations has been evaluated through comparison experiments performed on a multi-sequence brain MR dataset and a multi-modality abdominal dataset. Our method has displayed its ability to generate synthesized data that is aligned with the source while maintaining a proper quality of signal compared to CycleGAN-generated data. The proposed model also obtained comparable performance with CycleGAN when data from the source and target domains are alignable through simple affine transformations.

Original languageEnglish
Title of host publicationSimulation and Synthesis in Medical Imaging. SASHIMI 2018
EditorsOrcun Goksel, Ipek Oguz, Ali Gooya, Ninon Burgos
PublisherSpringer
Pages52-60
Number of pages9
ISBN (Electronic)9783030005368
ISBN (Print)9783030005351
DOIs
Publication statusPublished - 12 Sept 2018
Event3rd International Workshop on Simulation and Synthesis in Medical Imaging 2018 - Granada, Spain
Duration: 16 Sept 201816 Sept 2018

Publication series

NameLecture Notes in Computer Science
Volume11037
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference3rd International Workshop on Simulation and Synthesis in Medical Imaging 2018
Abbreviated titleSASHIMI 2018
Country/TerritorySpain
CityGranada
Period16/09/1816/09/18
OtherHeld in Conjunction with 21st International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2018.

Keywords

  • Deep learning
  • GAN
  • Synthesis
  • Unsupervised learning

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint

Dive into the research topics of 'Unsupervised learning for cross-domain medical image synthesis using deformation invariant cycle consistency networks'. Together they form a unique fingerprint.

Cite this