Lymphocite segmentation using mixture of Gaussians and the transferable belief model. - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Lymphocite segmentation using mixture of Gaussians and the transferable belief model.

Résumé

In the context of several pathologies, the presence of lym- phocytes has been correlated with disease outcome. The ability to au- tomatically detect lymphocyte nuclei on histopathology imagery could potentially result in the development of an image based prognostic tool. In this paper we present a method based on the estimation of a mixture of Gaussians for determining the probability distribution of the princi- pal image component. Then, a post-processing stage eliminates regions, whose shape is not similar to the nuclei searched. Finally, the Transfer- able Belief Model is used to detect the lymphocyte nuclei, and a shape based algorithm possibly splits them under an equal area and an eccen- tricity constraint principle.
Fichier principal
Vignette du fichier
ICPR2010Emmanuel.pdf (153.85 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00546691 , version 1 (14-12-2010)

Identifiants

  • HAL Id : hal-00546691 , version 1

Citer

Costas Panagiotakis, Emmanuel Ramasso, Georgios Tziritas. Lymphocite segmentation using mixture of Gaussians and the transferable belief model.. 20th IEEE International Conference on Pattern Recognition, ICPR'10., Aug 2010, Istanbul, Turkey. pp.1-8. ⟨hal-00546691⟩
87 Consultations
40 Téléchargements

Partager

Gmail Facebook X LinkedIn More