Chan-Vese Attention U-Net: An attention mechanism for robust segmentation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

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

Résumé

When studying the results of a segmentation algorithm using convolutional neural networks, one wonders about the reliability and consistency of the results. This leads to questioning the possibility of using such an algorithm in applications where there is little room for doubt. We propose in this paper a new attention gate based on the use of Chan-Vese energy minimization to control more precisely the segmentation masks given by a standard CNN architecture such as the U-Net model. This mechanism allows to obtain a constraint on the segmentation based on the resolution of a PDE. The study of the results allows us to observe the spatial information retained by the neural network on the region of interest and obtains competitive results on the binary segmentation. We illustrate the efficiency of this approach for medical image segmentation on a database of MRI brain images.
Fichier principal
Vignette du fichier
arxiv/GSI-051.pdf (3.65 Mo) Télécharger le fichier

Dates et versions

hal-04145428 , version 1 (30-06-2023)

Identifiants

Citer

Nicolas Makaroff, Laurent D. Cohen. Chan-Vese Attention U-Net: An attention mechanism for robust segmentation. 6th conference on Geometric Science of Information (GSI2023), Aug 2023, Saint-Malo, France. ⟨hal-04145428⟩
83 Consultations
40 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More