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

Unsupervised domain adaptation (UDA) aims to learn a model trained on sourcedomain and performs well on unlabeled target domain. In medical imagesegmentation field, most existing UDA methods depend on adversarial learning toaddress the domain gap between different image modalities, which is ineffectivedue to its complicated training process. In this paper, we propose a simple yeteffective UDA method based on frequency and spatial domain transfer unermulti-teacher distillation framework. In the frequency domain, we firstintroduce non-subsampled contourlet transform for identifying domain-invariantand domain-variant frequency components (DIFs and DVFs), and then keep the DIFsunchanged while replacing the DVFs of the source domain images with that of thetarget domain images to narrow the domain gap. In the spatial domain, wepropose a batch momentum update-based histogram matching strategy to reduce thedomain-variant image style bias. Experiments on two cross-modality medicalimage segmentation datasets (cardiac, abdominal) show that our proposed methodachieves superior performance compared to state-of-the-art methods.

Reducing Domain Gap in Frequency and Spatial domain for Cross-modality Domain Adaptation on Medical Image Segmentation