Graph-based multi-resolution segmentation of histological whole slide images

Abstract : In this paper, we present a graph-based multi-resolution approach for mitosis extraction in breast cancer histological whole slide images. The proposed segmentation uses a multiresolution approach which reproduces the slide examination done by a pathologist. Each resolution level is analyzed with a focus of attention resulting from a coarser resolution level analysis. At each resolution level, a spatial refinement by semi-supervised clustering is performed to obtain more accurate segmentation around edges. The proposed segmentation is fully unsupervised by using domain specific knowledge.
Type de document :
Communication dans un congrès
International Symposium on Biomedical Imaging, 2010, Netherlands. pp.153-156, 2010, 〈10.1109/ISBI.2010.5490390〉
Liste complète des métadonnées

Littérature citée [5 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00521067
Contributeur : Image Greyc <>
Soumis le : lundi 24 février 2014 - 10:56:40
Dernière modification le : jeudi 8 novembre 2018 - 15:26:02
Document(s) archivé(s) le : samedi 24 mai 2014 - 10:35:26

Fichier

Isbi2010-2.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Vincent Roullier, Vinh Thong Ta, Olivier Lezoray, Abderrahim Elmoataz. Graph-based multi-resolution segmentation of histological whole slide images. International Symposium on Biomedical Imaging, 2010, Netherlands. pp.153-156, 2010, 〈10.1109/ISBI.2010.5490390〉. 〈hal-00521067〉

Partager

Métriques

Consultations de la notice

179

Téléchargements de fichiers

117