An Efficient Segmentation Method for Ultrasound Images based on a Semi-supervised Approach and Patch-based Features

Détails

ID Serval
serval:BIB_8C933F116BF4
Type
Actes de conférence (partie): contribution originale à la littérature scientifique, publiée à l'occasion de conférences scientifiques, dans un ouvrage de compte-rendu (proceedings), ou dans l'édition spéciale d'un journal reconnu (conference proceedings).
Collection
Publications
Titre
An Efficient Segmentation Method for Ultrasound Images based on a Semi-supervised Approach and Patch-based Features
Titre de la conférence
Proceedings of the 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2011
Auteur(s)
Ciurte A.R., Houhou N., Nedevschi S., Pica A., Munier F., Thiran J.P., Bresson X., Bach Cuadra M.
Adresse
Chicago, Illinois, USA, March 30 - April 2, 2011
ISBN
1945-7928
Statut éditorial
Publié
Date de publication
2011
Volume
2011
Série
Biomedical Imaging
Pages
969-972
Langue
anglais
Résumé
Segmenting ultrasound images is a challenging problemwhere standard unsupervised segmentation methods such asthe well-known Chan-Vese method fail. We propose in thispaper an efficient segmentation method for this class ofimages. Our proposed algorithm is based on asemi-supervised approach (user labels) and the use ofimage patches as data features. We also consider thePearson distance between patches, which has been shown tobe robust w.r.t speckle noise present in ultrasoundimages. Our results on phantom and clinical data show avery high similarity agreement with the ground truthprovided by a medical expert.
Mots-clé
Semi-supervised segmentation, Ultrasonography, Patch features, Min-cut algorithms, Bipartite graph, LTS5, CIBM-SPC
Création de la notice
29/11/2011 16:40
Dernière modification de la notice
20/08/2019 14:50
Données d'usage