Robust RANSAC-based blood vessel segmentation

Ahmed Yureidini 1, 2 Erwan Kerrien 2 Stéphane Cotin 1
1 SHACRA - Simulation in Healthcare using Computer Research Advances
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, Inria Nancy - Grand Est
2 MAGRIT - Visual Augmentation of Complex Environments
Inria Nancy - Grand Est, LORIA - ALGO - Department of Algorithms, Computation, Image and Geometry
Abstract : Many vascular clinical applications require a vessel segmentation process that is able to both extract the centerline and the surface of the blood vessels. However, noise and topology issues (such as kissing vessels) prevent existing algorithms from being able to easily retrieve such a complex system as the brain vasculature. We propose here a new blood vessel tracking algorithm that 1) detect the vessel centerline; 2) provide a local radius estimate; and 3) extracts a dense set of points at the blood vessel surface. This algorithm is based on a RANSAC-based robust fitting of successive cylinders along the vessel. Our method was validated against the Multiple Hypothesis Testing (MHT) algorithm on 10 3DRA patient data of the brain vasculature. Over 30 blood vessels of various sizes were considered for each patient. Our results demonstrated a greater ability of our algorithm to track small, tortuous and touching vessels (96% success rate), compared to MHT (65% success rate). The computed centerline precision was below 1 voxel when compared to MHT. Moreover, our results were obtained with the same set of parameters for all patients and all blood vessels, except for the seed point for each vessel, also necessary for MHT. The proposed algorithm is thereafter able to extract the full intracranial vasculature with little user interaction.
Type de document :
Communication dans un congrès
Dave R. Haynor and Sébastien Ourselin. SPIE Medical Imaging, Feb 2012, San Diego, CA, United States. SPIE Press, 8314, pp.8314M, 2012, Image Processing. 〈10.1117/12.911670〉
Liste complète des métadonnées

Littérature citée [8 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00642003
Contributeur : Erwan Kerrien <>
Soumis le : vendredi 12 octobre 2012 - 11:46:56
Dernière modification le : vendredi 30 mars 2018 - 10:02:03
Document(s) archivé(s) le : mardi 13 décembre 2016 - 18:42:19

Fichier

spie2012.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Ahmed Yureidini, Erwan Kerrien, Stéphane Cotin. Robust RANSAC-based blood vessel segmentation. Dave R. Haynor and Sébastien Ourselin. SPIE Medical Imaging, Feb 2012, San Diego, CA, United States. SPIE Press, 8314, pp.8314M, 2012, Image Processing. 〈10.1117/12.911670〉. 〈hal-00642003〉

Partager

Métriques

Consultations de la notice

1005

Téléchargements de fichiers

652