TPSDicyc: Improved Deformation Invariant Cross-domain Medical Image Synthesis

Chengjia Wang*, Giorgos Papanastasiou, Sotirios Tsaftaris, Guang Yang, Calum Gray, David Newby, Gillian Macnaught, Tom MacGillivray

*Corresponding author for this work

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

17 Citations (Scopus)


Cycle-consistent generative adversarial network (CycleGAN) has been widely used for cross-domain medical image systhesis tasks particularly due to its ability to deal with unpaired data. However, most CycleGAN-based synthesis methods can not achieve good alignment between the synthesized images and data from the source domain, even with additional image alignment losses. This is because the CycleGAN generator network can encode the relative deformations and noises associated to different domains. This can be detrimental for the downstream applications that rely on the synthesized images, such as generating pseudo-CT for PET-MR attenuation correction. In this paper, we present a deformation invariant model based on the deformation-invariant CycleGAN (DicycleGAN) architecture and the spatial transformation network (STN) using thin-plate-spline (TPS). The proposed method can be trained with unpaired and unaligned data, and generate synthesised images aligned with the source data. Robustness to the presence of relative deformations between data from the source and target domain has been evaluated through experiments on multi-sequence brain MR data and multi-modality abdominal CT and MR data. Experiment results demonstrated that our method can achieve better alignment between the source and target data while maintaining superior image quality of signal compared to several state-of-the-art CycleGAN-based methods.

Original languageEnglish
Title of host publicationMachine Learning for Medical Image Reconstruction. MLMIR 2019
EditorsFlorian Knoll, Andreas Maier, Daniel Rueckert, Jong Chul Ye
Number of pages10
ISBN (Electronic)9783030338435
ISBN (Print)9783030338428
Publication statusPublished - 24 Oct 2019
Event2nd International Workshop on Machine Learning for Medical Image Reconstruction 2019 - Shenzhen, China
Duration: 17 Oct 201917 Oct 2019

Publication series

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


Conference2nd International Workshop on Machine Learning for Medical Image Reconstruction 2019
OtherHeld in Conjunction with 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2019.

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science


Dive into the research topics of 'TPSDicyc: Improved Deformation Invariant Cross-domain Medical Image Synthesis'. Together they form a unique fingerprint.

Cite this