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

• Published in: arXiv.org 2019-09
• Main Authors: Orbes-Arteaga, Mauricio, Varsavsky, Thomas, Sudre, Carole H, Eaton-Rosen, Zach, Haddow, Lewis J, Sørensen, Lauge, Nielsen, Mads, Pai, Akshay, Ourselin, Sébastien, Modat, Marc, Nachev, Parashkev, Cardoso, M Jorge
• Format: Article
• Language: English
• Subjects: Adaptation; Algorithms; Brain; Consistency; Domains; Image acquisition; Image segmentation; Machine learning; Medical imaging
• ISSN: 2331-8422

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.