Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentation

Xiao Liu*, Spyridon Thermos, Alison O'Neil, Sotirios A. Tsaftaris

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Generalising deep models to new data from new centres (termed here domains) remains a challenge. This is largely attributed to shifts in data statistics (domain shifts) across source and unseen domains. Recently, gradient-based meta-learning approaches where the training data are split into meta-train and meta-test sets to simulate and handle the domain shifts during training have shown improved generalisation performance. However, the current fully supervised meta-learning approaches are not scalable for medical image segmentation, where large effort is required to create pixel-wise annotations. Meanwhile, in a low data regime, the simulated domain shifts may not approximate the true domain shifts well across source and unseen domains. To address this problem, we propose a novel semi-supervised meta-learning framework with disentanglement. We explicitly model the representations related to domain shifts. Disentangling the representations and combining them to reconstruct the input image allows unlabeled data to be used to better approximate the true domain shifts for meta-learning. Hence, the model can achieve better generalisation performance, especially when there is a limited amount of labeled data. Experiments show that the proposed method is robust on different segmentation tasks and achieves state-of-the-art generalisation performance on two public benchmarks. Code is publicly available at: https://github.com/vios-s/DGNet
Original languageEnglish
Title of host publicationMedical Image Computing and Computer Assisted Intervention – MICCAI 2021
Subtitle of host publication24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part II
PublisherSpringer
Pages307-317
Volume12902
ISBN (Electronic)978-3-030-87196-3
ISBN (Print)978-3-030-87195-6
DOIs
Publication statusE-pub ahead of print - 21 Sep 2021
Event24th International Conference on Medical Image Computing and Computer Assisted Intervention: MICCAI 2021 - Virtual
Duration: 27 Sep 20211 Oct 2021
https://miccai2021.org/en/default.asp

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume12902
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference24th International Conference on Medical Image Computing and Computer Assisted Intervention
Abbreviated titleMICCAI
Period27/09/211/10/21
Internet address

Keywords

  • Domain generalisation
  • Disentanglement
  • Medical image segmentation

Fingerprint

Dive into the research topics of 'Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentation'. Together they form a unique fingerprint.

Cite this