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

arXiv: https://arxiv.org/abs/1808.03944 · HTML: https://mlsanity.com/paper/1808.03944/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2018.

## Built on by (most cited first, 10 of 10)

- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Estimating Image Depth in the Comics Domain](https://mlsanity.com/paper/2110.03575/) (2021)
- [Deformation equivariant cross-modality image synthesis with paired non-aligned training data](https://mlsanity.com/paper/2208.12491/) (2022)
- [Unsupervised-learning-based method for chest MRI-CT transformation using structure constrained unsupervised generative attention networks](https://mlsanity.com/paper/2106.08557/) (2021)
- [Exploring Cycle Consistency Learning in Interactive Volume Segmentation](https://mlsanity.com/paper/2303.06493/) (2023)
- [Anatomical feature-prioritized loss for enhanced MR to CT translation](https://mlsanity.com/paper/2410.10328/) (2024)
- [Structure-aware Unsupervised Tagged-to-Cine MRI Synthesis with Self Disentanglement](https://mlsanity.com/paper/2202.12474/) (2022)
- [Dense Multitask Learning to Reconfigure Comics](https://mlsanity.com/paper/2307.08071/) (2023)
- [Cross Modality Medical Image Synthesis for Improving Liver Segmentation](https://mlsanity.com/paper/2503.00945/) (2025)
- [Quantitative Imaging Principles Improves Medical Image Learning](https://mlsanity.com/paper/2206.06663/) (2022)

## Abstract (arXiv)

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.