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

Domain Generalization (DG) aims to reduce domain shifts between domains toachieve promising performance on the unseen target domain, which has beenwidely practiced in medical image segmentation. Single-source domaingeneralization (SDG) is the most challenging setting that trains on only onesource domain. Although existing methods have made considerable progress on SDGof medical image segmentation, the performances are still far from theapplicable standards when faced with a relatively large domain shift. In thispaper, we leverage the Segment Anything Model (SAM) to SDG to greatly improvethe ability of generalization. Specifically, we introduce a parallel framework,the source images are sent into the SAM module and normal segmentation modulerespectively. To reduce the calculation resources, we apply a merging strategybefore sending images to the SAM module. We extract the bounding boxes from thesegmentation module and send the refined version as prompts to the SAM module.We evaluate our model on a classic DG dataset and achieve competitive resultscompared to other state-of-the-art DG methods. Furthermore, We conducted aseries of ablation experiments to prove the effectiveness of the proposedmethod. The code is publicly available at https://github.com/SARIHUST/SAMMed.

Leveraging SAM for Single-Source Domain Generalization in Medical Image Segmentation