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/

Zendy Plus

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

Zendy Tools

Zendy Open

The Segment Anything Model (SAM) has recently emerged as a groundbreakingfoundation model for prompt-driven image segmentation tasks. However, both theoriginal SAM and its medical variants require slice-by-slice manual promptingof target structures, which directly increase the burden for applications.Despite attempts of auto-prompting to turn SAM into a fully automatic manner,it still exhibits subpar performance and lacks of reliability especially in thefield of medical imaging. In this paper, we propose UR-SAM, an uncertaintyrectified SAM framework to enhance the reliability for auto-prompting medicalimage segmentation. Building upon a localization framework for automatic promptgeneration, our method incorporates a prompt augmentation module to obtain aseries of input prompts for SAM for uncertainty estimation and anuncertainty-based rectification module to further utilize the distribution ofestimated uncertainty to improve the segmentation performance. Extensiveexperiments on two public 3D medical datasets covering the segmentation of 35organs demonstrate that without supplementary training or fine-tuning, ourmethod further improves the segmentation performance with up to 10.7 % and 13.8% in dice similarity coefficient, demonstrating efficiency and broadcapabilities for medical image segmentation without manual prompting.

Enhancing the Reliability of Segment Anything Model for Auto-Prompting Medical Image Segmentation with Uncertainty Rectification