English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

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) between source and unseen domains. Recently, gradient-basedmeta-learning approaches where the training data are split into meta-train andmeta-test sets to simulate and handle the domain shifts during training haveshown improved generalisation performance. However, the current fullysupervised meta-learning approaches are not scalable for medical imagesegmentation, where large effort is required to create pixel-wise annotations.Meanwhile, in a low data regime, the simulated domain shifts may notapproximate the true domain shifts well across source and unseen domains. Toaddress this problem, we propose a novel semi-supervised meta-learningframework with disentanglement. We explicitly model the representations relatedto domain shifts. Disentangling the representations and combining them toreconstruct the input image allows unlabeled data to be used to betterapproximate the true domain shifts for meta-learning. Hence, the model canachieve better generalisation performance, especially when there is a limitedamount of labeled data. Experiments show that the proposed method is robust ondifferent segmentation tasks and achieves state-of-the-art generalisationperformance on two public benchmarks.

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