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

Recently, weakly-supervised image segmentation using weak annotations likescribbles has gained great attention, since such annotations are much easier toobtain compared to time-consuming and label-intensive labeling at thepixel/voxel level. However, because scribbles lack structure information ofregion of interest (ROI), existing scribble-based methods suffer from poorboundary localization. Furthermore, most current methods are designed for 2Dimage segmentation, which do not fully leverage the volumetric information ifdirectly applied to image slices. In this paper, we propose a scribble-basedvolumetric image segmentation, Scribble2D5, which tackles 3D anisotropic imagesegmentation and improves boundary prediction. To achieve this, we augment a2.5D attention UNet with a proposed label propagation module to extend semanticinformation from scribbles and a combination of static and active boundaryprediction to learn ROI's boundary and regularize its shape. Extensiveexperiments on three public datasets demonstrate Scribble2D5 significantlyoutperforms current scribble-based methods and approaches the performance offully-supervised ones. Our code is available online.

Scribble2D5: Weakly-Supervised Volumetric Image Segmentation via Scribble Annotations