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

TL;DR

This paper presents an unsupervised domain adaptation method using CycleGAN to improve white matter hyperintensity segmentation across multicenter MR images with different scanners and acquisition settings.

Contribution

It introduces a CycleGAN-based approach for domain adaptation in medical imaging, enabling CNN segmentation without labeled data in target domains.

Findings

CycleGAN reduces domain divergence in MR images.

Improved segmentation accuracy in unlabeled target domains.

Enables cross-center MRI analysis without additional annotations.

Abstract

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.