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

When studying the results of a segmentation algorithm using convolutionalneural networks, one wonders about the reliability and consistency of theresults. This leads to questioning the possibility of using such an algorithmin applications where there is little room for doubt. We propose in this papera new attention gate based on the use of Chan-Vese energy minimization tocontrol more precisely the segmentation masks given by a standard CNNarchitecture such as the U-Net model. This mechanism allows to obtain aconstraint on the segmentation based on the resolution of a PDE. The study ofthe results allows us to observe the spatial information retained by the neuralnetwork on the region of interest and obtains competitive results on the binarysegmentation. We illustrate the efficiency of this approach for medical imagesegmentation on a database of MRI brain images.

Chan-Vese Attention U-Net: An attention mechanism for robust segmentation