King's College London

Research portal

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

Research output: Contribution to journalArticle

Mauricio Orbes-Arteaga, Thomas Varsavsky, Carole H. Sudre, Zach Eaton-Rosen, Lewis J. Haddow, Lauge Sørensen, Mads Nielsen, Akshay Pai, Sébastien Ourselin, Marc Modat, Parashkev Nachev, M. Jorge Cardoso

Original languageEnglish
Pages (from-to)54-62
Number of pages9
JournalDART 2019
DOIs
Publication statusPublished - 16 Aug 2019

Bibliographical note

Accepted at 1st International Workshop on Domain Adaptation and Representation Transfer held at MICCAI 2019

Documents

  • 1908.05959v2

    1908.05959v2.pdf, 595 KB, application/pdf

    23/10/2019

King's Authors

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.

Download statistics

No data available

View graph of relations

© 2018 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454