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

For medical image segmentation, imagine if a model was only trained using MRimages in source domain, how about its performance to directly segment CTimages in target domain? This setting, namely generalizable cross-modalitysegmentation, owning its clinical potential, is much more challenging thanother related settings, e.g., domain adaptation. To achieve this goal, we inthis paper propose a novel dual-normalization model by leveraging the augmentedsource-similar and source-dissimilar images during our generalizablesegmentation. To be specific, given a single source domain, aiming to simulatethe possible appearance change in unseen target domains, we first utilize anonlinear transformation to augment source-similar and source-dissimilarimages. Then, to sufficiently exploit these two types of augmentations, ourproposed dual-normalization based model employs a shared backbone yetindependent batch normalization layer for separate normalization. Afterward, weput forward a style-based selection scheme to automatically choose theappropriate path in the test stage. Extensive experiments on three publiclyavailable datasets, i.e., BraTS, Cross-Modality Cardiac, and AbdominalMulti-Organ datasets, have demonstrated that our method outperforms otherstate-of-the-art domain generalization methods. Code is available athttps://github.com/zzzqzhou/Dual-Normalization.

Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalization