4DGVF: Segmentation variationnelle pour images 3D multicomposantes

4DGVF: Variational segmentation of 3D vector-valued images;
4DGVF: Variational segmentation for multicomponent 3D Warehouse

dc.creatorJaouen, Vincent
dc.creatorGonzález-Gutiérrez, Paulo
dc.creatorStute, Simon
dc.creatorGuilloteau, Denis
dc.creatorChalon, Sylvie
dc.creatorBuvat, Irene
dc.creatorTauber, Clovis
dc.date2017-11-13T14:19:34Z
dc.date2017-11-13T14:19:34Z
dc.date2014
dc.date.accessioned2019-11-20T15:09:54Z
dc.date.available2019-11-20T15:09:54Z
dc.identifierhttp://repositorio.ucm.cl:8080/handle/ucm/1221
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/3033036
dc.descriptionIn this paper, we generalize the gradient vector flow field to vector-valued images. We base our method on the definition of a structure tensor that is calculated according to a blind estimation of contrast in the different channels and that exploits the whole spatio-spectral information, hence reducing sensitivity to noise and better defining orientations of the force field. The resulting field takes profit of both magnitude and direction of the vector-valued gradient. Applied to biological volume delineation in 3D dynamic Positron Emission Tomography (PET) imaging, we validate our method on realistic Monte Carlo simulations of numerical phantoms and present results on real dynamic PET data. Performances observed on such images confirm the potential of the proposed active surface approach for vector-valued data.
dc.languagefr
dc.rightsAtribución-NoComercial-SinDerivadas 3.0 Chile
dc.rightshttp://creativecommons.org/licenses/by-nc-nd/3.0/cl/
dc.sourceTraitement du Signal, 31(1-2), 9-38
dc.subject3D segmentation
dc.subjectDeformable models
dc.subjectDynamic PET
dc.subjectSegmentation 3D
dc.subjectModèles déformables
dc.subjectTEP dynamique
dc.title4DGVF: Segmentation variationnelle pour images 3D multicomposantes
dc.title4DGVF: Variational segmentation of 3D vector-valued images
dc.title4DGVF: Variational segmentation for multicomponent 3D Warehouse
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución