Multi-domain Adaptation in Brain MRI Through Paired Consistency and Adversarial Learning.

Adversarial learning Brain MR Domain adaptation

Journal

Domain Adaptation and Representation Transfer and Medical Image Learning with Less Labels and Imperfect Data : first MICCAI Workshop, DART 2019, and first International Workshop, MIL3ID 2019, Shenzhen, held in conjunction with MICCAI 20...
Titre abrégé: Domain Adapt Represent Transf Med Image Learn Less Labels Imperfect Data (2019)
Pays: Switzerland
ID NLM: 101758324

Informations de publication

Date de publication:
2019
Historique:
entrez: 10 6 2021
pubmed: 1 1 2019
medline: 1 1 2019
Statut: ppublish

Résumé

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

Identifiants

DOI: 10.1007/978-3-030-33391-1_7 PMID: 34109324 PMC: PMC7610933
pubmed: 34109324
doi: 10.1007/978-3-030-33391-1_7
pmc: PMC7610933
mid: EMS126674
doi:

Types de publication

Journal Article

Langues

eng

Pagination

54-62

Subventions

Organisme : Wellcome Trust
Pays : United Kingdom
Organisme : Wellcome Trust
ID : 203148
Pays : United Kingdom
Organisme : Wellcome Trust
ID : 213038
Pays : United Kingdom
Organisme : EPA
ID : EP-W-17-011
Pays : United States

Références

Brief Bioinform. 2018 Nov 27;19(6):1236-1246
pubmed: 28481991
AIDS Res Hum Retroviruses. 2019 May;35(5):453-460
pubmed: 30667282
Neuroimage. 2019 Jul 1;194:1-11
pubmed: 30898655
IEEE Trans Med Imaging. 2019 Nov;38(11):2556-2568
pubmed: 30908194

Auteurs

Mauricio Orbes-Arteaga (M)

Biomedical Engineering and Imaging Sciences, King's College London, London, UK.
Biomediq A/S, Copenhagen, Denmark.

Thomas Varsavsky (T)

Biomedical Engineering and Imaging Sciences, King's College London, London, UK.
Department of Medical Physics and Biomedical Engineering, UCL, London, UK.

Carole H Sudre (CH)

Biomedical Engineering and Imaging Sciences, King's College London, London, UK.
Department of Medical Physics and Biomedical Engineering, UCL, London, UK.
Institute of Neurology, University College London, London, UK.

Zach Eaton-Rosen (Z)

Biomedical Engineering and Imaging Sciences, King's College London, London, UK.
Department of Medical Physics and Biomedical Engineering, UCL, London, UK.

Lewis J Haddow (LJ)

Chelsea and Westminster Hospital NHS Foundation Trust, London, UK.

Lauge Sørensen (L)

Biomediq A/S, Copenhagen, Denmark.
Cereriu A/S, Copenhagen, Denmark.
Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.

Mads Nielsen (M)

Biomediq A/S, Copenhagen, Denmark.
Cereriu A/S, Copenhagen, Denmark.
Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.

Akshay Pai (A)

Biomediq A/S, Copenhagen, Denmark.
Cereriu A/S, Copenhagen, Denmark.
Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.

Sébastien Ourselin (S)

Biomedical Engineering and Imaging Sciences, King's College London, London, UK.

Marc Modat (M)

Biomedical Engineering and Imaging Sciences, King's College London, London, UK.

Parashkev Nachev (P)

Institute of Neurology, University College London, London, UK.

M Jorge Cardoso (MJ)

Biomedical Engineering and Imaging Sciences, King's College London, London, UK.

Classifications MeSH