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

Automatic tissue segmentation of fetal brain images is essential for thequantitative analysis of prenatal neurodevelopment. However, producingvoxel-level annotations of fetal brain imaging is time-consuming and expensive.To reduce labeling costs, we propose a practical unsupervised domain adaptation(UDA) setting that adapts the segmentation labels of high-quality fetal brainatlases to unlabeled fetal brain MRI data from another domain. To address thetask, we propose a new UDA framework based on Appearance and StructureConsistency, named ASC. We adapt the segmentation model to the appearances ofdifferent domains by constraining the consistency before and after afrequency-based image transformation, which is to swap the appearance betweenbrain MRI data and atlases. Consider that even in the same domain, the fetalbrain images of different gestational ages could have significant variations inthe anatomical structures. To make the model adapt to the structural variationsin the target domain, we further encourage prediction consistency underdifferent structural perturbations. Extensive experiments on FeTA 2021benchmark demonstrate the effectiveness of our ASC in comparison toregistration-based, semi-supervised learning-based, and existing UDA-basedmethods.

ASC: Appearance and Structure Consistency for Unsupervised Domain Adaptation in Fetal Brain MRI Segmentation