Abstract : We propose a new method combining a population-specific nonlinear template atlas approach with non-local patch-based structure segmentation for whole brain segmentation into individual structures. This way, we benefit from the efficient intensity-driven segmentation of the non-local means framework and from the global shape constraints imposed by the nonlinear template matching.
Type de document :
Communication dans un congrès
MICCAI 2012 Workshop on Multi-Atlas Labeling, Oct 2012, Nice, France. pp.63-66, 2012
https://hal.archives-ouvertes.fr/hal-00739285
Contributeur : Pierrick Coupé <>
Soumis le : dimanche 7 octobre 2012 - 14:39:28
Dernière modification le : lundi 8 octobre 2012 - 10:11:25
Document(s) archivé(s) le : mardi 8 janvier 2013 - 03:48:22
Vladimir Fonov, Pierrick Coupé, Simon Eskildsen, Jose Manjon, Louis Collins. Multi-atlas labeling with population-specific template and non-local patch-based label fusion. MICCAI 2012 Workshop on Multi-Atlas Labeling, Oct 2012, Nice, France. pp.63-66, 2012. <hal-00739285>
