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

Tumor region segmentation is an essential task for the quantitative analysisof digital pathology. Recently presented deep neural networks have shownstate-of-the-art performance in various image-segmentation tasks. However,because of the unclear boundary between the cancerous and normal regions inpathology images, despite using modern methods, it is difficult to producesatisfactory segmentation results in terms of the reliability and accuracyrequired for medical data. In this study, we propose an interactivesegmentation method that allows users to refine the output of deep neuralnetworks through click-type user interactions. The primary method is toformulate interactive segmentation as an optimization problem that leveragesboth user-provided click constraints and semantic information in a feature mapusing a click-guided attention module (CGAM). Unlike other existing methods,CGAM avoids excessive changes in segmentation results, which can lead to theoverfitting of user clicks. Another advantage of CGAM is that the model size isindependent of input image size. Experimental results on pathology imagedatasets indicated that our method performs better than existingstate-of-the-art methods.

CGAM: Click-Guided Attention Module for Interactive Pathology Image Segmentation via Backpropagating Refinement