# Multi-Domain Adaptation in Brain MRI through Paired Consistency and Adversarial Learning

## TL;DR

This paper introduces a novel multi-domain adaptation method for brain MRI segmentation that leverages paired data, consistency loss, and adversarial learning to improve generalization across different acquisition domains.

## Contribution

The paper proposes a new multi-domain adaptation approach using paired data, combining consistency loss with adversarial learning, specifically for brain MRI segmentation tasks.

## Key findings

- Significantly outperforms existing domain adaptation methods
- Effective in adapting across multiple target domains
- Improves segmentation accuracy in brain MRI applications

## Abstract

Supervised learning algorithms trained on medical images will often fail to generalize across changes in acquisition parameters. Recent work in domain adaptation addresses this challenge and successfully leverages labeled data in a source domain to perform well on an unlabeled target domain. Inspired by recent work in semi-supervised learning we introduce a novel method to adapt from one source domain to $n$ target domains (as long as there is paired data covering all domains). Our multi-domain adaptation method utilises a consistency loss combined with adversarial learning. We provide results on white matter lesion hyperintensity segmentation from brain MRIs using the MICCAI 2017 challenge data as the source domain and two target domains. The proposed method significantly outperforms other domain adaptation baselines.