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

The Segment Anything Model (SAM) is a recently developed all-range foundationmodel for image segmentation. It can use sparse manual prompts such as boundingboxes to generate pixel-level segmentation in natural images but struggles inmedical images such as low-contrast, noisy ultrasound images. We propose arefined test-phase prompt augmentation technique designed to improve SAM'sperformance in medical image segmentation. The method couples multi-box promptaugmentation and an aleatoric uncertainty-based false-negative (FN) andfalse-positive (FP) correction (FNPC) strategy. We evaluate the method on twoultrasound datasets and show improvement in SAM's performance and robustness toinaccurate prompts, without the necessity for further training or tuning.Moreover, we present the Single-Slice-to-Volume (SS2V) method, enabling 3Dpixel-level segmentation using only the bounding box annotation from a single2D slice. Our results allow efficient use of SAM in even noisy, low-contrastmedical images. The source code will be released soon.

False Negative/Positive Control for SAM on Noisy Medical Images