Thumbnail - No thumbnail

Real-Time 3D Image Segmentation by User-Constrained Template Deformation

Ardon, Roberto; Mory, Benoît; Prevost, Raphaël; Somphone, Oudom (2012), Real-Time 3D Image Segmentation by User-Constrained Template Deformation, dans Nicholas Ayache, Hervé Delingette, Polina Golland, Kensaku Mori, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012 15th International Conference, Nice, France, October 1-5, 2012, Proceedings, Part I, Springer : Berlin Heidelberg, p. 561-568. 10.1007/978-3-642-33415-3_69

Type
Communication / Conférence
Lien vers un document non conservé dans cette base
https://hal.archives-ouvertes.fr/hal-00779423
Date
2012
Pays du colloque
FRANCE
Titre de l'ouvrage
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012 15th International Conference, Nice, France, October 1-5, 2012, Proceedings, Part I; MICCAI 2012
Auteurs de l’ouvrage
Nicholas Ayache, Hervé Delingette, Polina Golland, Kensaku Mori
Éditeur
Springer
Ville d’édition
Berlin Heidelberg
Isbn
978-3-642-33414-6
Pages
561-568
Identifiant publication
Métadonnées
Afficher la notice complète
Auteur(s)
Ardon, Roberto
Mory, Benoît
Prevost, Raphaël
Somphone, Oudom
Résumé (EN)
We describe an algorithm for 3D interactive image segmenta- tion by non-rigid implicit template deformation, with two main original features. First, our formulation incorporates user input as inside/outside labeled points to drive the deformation and improve both robustness and accuracy. This yields inequality constraints, solved using an Augmented Lagrangian approach. Secondly, a fast implementation of non-rigid template-to-image registration enables interactions with a real-time visual feedback. We validated this generic technique on 21 Contrast-Enhanced Ultrasound images of kidneys and obtained accurate segmentation results (Dice> 0:93) in less than 3 clicks in average.
Mots-clés
3D image segmentation