Flux driven automatic centerline extraction.
Med Image Anal
; 9(3): 209-21, 2005 Jun.
Article
en En
| MEDLINE
| ID: mdl-15854842
ABSTRACT
We present a fast, robust and automatic method for computing centerline paths through tubular structures for application to virtual endoscopy. The key idea is to utilize a skeletonization algorithm which exploits properties of the average outward flux of the gradient vector field of a Euclidean distance function from the boundary of the structure. The algorithm is modified to yield a collection of 3D curves, each of which is locally centered. The approach requires no user interaction, is virtually parameter free and has low computational complexity. We validate the method quantitatively on a number of synthetic data sets with known centerlines and qualitatively on colon and vessel data segmented from CT and CRA images.
Buscar en Google
Bases de datos:
MEDLINE
Asunto principal:
Algoritmos
/
Interfaz Usuario-Computador
/
Reconocimiento de Normas Patrones Automatizadas
/
Inteligencia Artificial
/
Interpretación de Imagen Asistida por Computador
/
Imagenología Tridimensional
/
Cirugía Asistida por Computador
/
Endoscopía
Tipo de estudio:
Evaluation_studies
Idioma:
En
Revista:
Med Image Anal
Asunto de la revista:
DIAGNOSTICO POR IMAGEM
Año:
2005
Tipo del documento:
Article
País de afiliación:
Estados Unidos