4DGVF: Segmentation variationnelle pour images 3D multicomposantes
In 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 redu...
| Autor Principal: | Jaouen, Vincent |
|---|---|
| Otros Autores: | González-Gutiérrez, Paulo, Stute, Simon, Guilloteau, Denis, Chalon, Sylvie, Buvat, Irene, Tauber, Clovis |
| Formato: | Artículo |
| Idioma: | French |
| Publicado: |
2017
|
| Materias: | |
| Acceso en línea: |
http://repositorio.ucm.cl:8080/handle/ucm/1221 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: |
In 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. |
|---|