# Unsupervised Domain Adaptation via CycleGAN for White Matter Hyperintensity Segmentation in Multicenter MR Images

arXiv: https://arxiv.org/abs/2009.04985 · HTML: https://mlsanity.com/paper/2009.04985/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2020.

## Built on by (most cited first, 15 of 15)

- [CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation](https://mlsanity.com/paper/2201.02831/) (2022)
- [Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives](https://mlsanity.com/paper/2308.01265/) (2023)
- [Multiple Sclerosis Lesion Analysis in Brain Magnetic Resonance Images: Techniques and Clinical Applications](https://mlsanity.com/paper/2104.10029/) (2021)
- [Domain shifts in dermoscopic skin cancer datasets: Evaluation of essential limitations for clinical translation](https://mlsanity.com/paper/2304.06968/) (2023)
- [Multi-center anatomical segmentation with heterogeneous labels via landmark-based models](https://mlsanity.com/paper/2211.07395/) (2022)
- [Structure Preserving Cycle-GAN for Unsupervised Medical Image Domain Adaptation](https://mlsanity.com/paper/2304.09164/) (2023)
- [IGUANe: a 3D generalizable CycleGAN for multicenter harmonization of brain MR images](https://mlsanity.com/paper/2402.03227/) (2024)
- [MS Lesion Segmentation: Revisiting Weighting Mechanisms for Federated Learning](https://mlsanity.com/paper/2205.01509/) (2022)
- [Soft-CP: A Credible and Effective Data Augmentation for Semantic Segmentation of Medical Lesions](https://mlsanity.com/paper/2203.10507/) (2022)
- [Towards Reliable WMH Segmentation under Domain Shift: An Application Study using Maximum Entropy Regularization to Improve Uncertainty Estimation](https://mlsanity.com/paper/2506.14497/) (2025)
- [AdaptDiff: Cross-Modality Domain Adaptation via Weak Conditional Semantic Diffusion for Retinal Vessel Segmentation](https://mlsanity.com/paper/2410.04648/) (2024)
- [Fault Detection in New Wind Turbines with Limited Data by Generative Transfer Learning](https://mlsanity.com/paper/2504.17709/) (2025)
- [Adapting to Unseen Vendor Domains for MRI Lesion Segmentation](https://mlsanity.com/paper/2108.06434/) (2021)
- [Neural Style Transfer and Unpaired Image-to-Image Translation to deal with the Domain Shift Problem on Spheroid Segmentation](https://mlsanity.com/paper/2112.09043/) (2021)
- [Unsupervised Domain Adaptation via Content Alignment for Hippocampus Segmentation](https://mlsanity.com/paper/2510.13075/) (2025)

## Abstract (arXiv)

Automatic segmentation of white matter hyperintensities in magnetic resonance images is of paramount clinical and research importance. Quantification of these lesions serve as a predictor for risk of stroke, dementia and mortality. During the last years, convolutional neural networks (CNN) specifically tailored for biomedical image segmentation have outperformed all previous techniques in this task. However, they are extremely data-dependent, and maintain a good performance only when data distribution between training and test datasets remains unchanged. When such distribution changes but we still aim at performing the same task, we incur in a domain adaptation problem (e.g. using a different MR machine or different acquisition parameters for training and test data). In this work, we explore the use of cycle-consistent adversarial networks (CycleGAN) to perform unsupervised domain adaptation on multicenter MR images with brain lesions. We aim at learning a mapping function to transform volumetric MR images between domains, which are characterized by different medical centers and MR machines with varying brand, model and configuration parameters. Our experiments show that CycleGAN allows us to reduce the Jensen-Shannon divergence between MR domains, enabling automatic segmentation with CNN models on domains where no labeled data was available.