# Structure Preserving Cycle-GAN for Unsupervised Medical Image Domain Adaptation

arXiv: https://arxiv.org/abs/2304.09164 · HTML: https://mlsanity.com/paper/2304.09164/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 18 Apr 2023.

## Builds on (most cited first, 16 of 16)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [A Brief Review of Domain Adaptation](https://mlsanity.com/paper/2010.03978/) (2020)
- [Tversky loss function for image segmentation using 3D fully convolutional deep networks](https://mlsanity.com/paper/1706.05721/) (2017)
- [A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation](https://mlsanity.com/paper/1810.07842/) (2018)
- [Multivariate mixture model for myocardium segmentation combining multi-source images](https://mlsanity.com/paper/1612.08820/) (2016)
- [Unsupervised Cross-Domain Image Generation](https://mlsanity.com/paper/1611.02200/) (2016)
- [Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory & Practice](https://mlsanity.com/paper/1911.01685/) (2019)
- [CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation](https://mlsanity.com/paper/2201.02831/) (2022)
- [Unsupervised Domain Adaptation via CycleGAN for White Matter Hyperintensity Segmentation in Multicenter MR Images](https://mlsanity.com/paper/2009.04985/) (2020)
- [Self-Training Based Unsupervised Cross-Modality Domain Adaptation for Vestibular Schwannoma and Cochlea Segmentation](https://mlsanity.com/paper/2109.10674/) (2021)
- [Edge-preserving Domain Adaptation for semantic segmentation of Medical Images](https://mlsanity.com/paper/2111.09847/) (2021)

## Built on by (most cited first, 5 of 5)

- [Domain Adaptation of Echocardiography Segmentation Via Reinforcement Learning](https://mlsanity.com/paper/2406.17902/) (2024)
- [Reinforcement Learning for Unsupervised Domain Adaptation in Spatio-Temporal Echocardiography Segmentation](https://mlsanity.com/paper/2510.14244/) (2025)
- [Gaze-Assisted Human-Centric Domain Adaptation for Cardiac Ultrasound Image Segmentation](https://mlsanity.com/paper/2502.03781/) (2025)
- [Source-Free Domain Adaptation via Multi-view Contrastive Learning](https://mlsanity.com/paper/2507.03321/) (2025)
- [Scheduled Style Injection: Expanding the Style-Content Pareto Frontier in Training-Free Diffusion-based Style Transfer](https://mlsanity.com/paper/2605.26538/) (2026)

## Abstract (arXiv)

The presence of domain shift in medical imaging is a common issue, which can greatly impact the performance of segmentation models when dealing with unseen image domains. Adversarial-based deep learning models, such as Cycle-GAN, have become a common model for approaching unsupervised domain adaptation of medical images. These models however, have no ability to enforce the preservation of structures of interest when translating medical scans, which can lead to potentially poor results for unsupervised domain adaptation within the context of segmentation. This work introduces the Structure Preserving Cycle-GAN (SP Cycle-GAN), which promotes medical structure preservation during image translation through the enforcement of a segmentation loss term in the overall Cycle-GAN training process. We demonstrate the structure preserving capability of the SP Cycle-GAN both visually and through comparison of Dice score segmentation performance for the unsupervised domain adaptation models. The SP Cycle-GAN is able to outperform baseline approaches and standard Cycle-GAN domain adaptation for binary blood vessel segmentation in the STARE and DRIVE datasets, and multi-class Left Ventricle and Myocardium segmentation in the multi-modal MM-WHS dataset. SP Cycle-GAN achieved a state of the art Myocardium segmentation Dice score (DSC) of 0.7435 for the MR to CT MM-WHS domain adaptation problem, and excelled in nearly all categories for the MM-WHS dataset. SP Cycle-GAN also demonstrated a strong ability to preserve blood vessel structure in the DRIVE to STARE domain adaptation problem, achieving a 4% DSC increase over a default Cycle-GAN implementation.