Vessel Extraction Using Crossing-Adaptive Minimal Path Model with Anisotropic Enhancement and Curvature Constraint

Liu, Li; Chen, Da; Cohen, Laurent D.; Huazhong, Shu; Pâques, Michel

Liu, Li; Chen, Da; Cohen, Laurent D.; Huazhong, Shu; Pâques, Michel (2019), Vessel Extraction Using Crossing-Adaptive Minimal Path Model with Anisotropic Enhancement and Curvature Constraint, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), IEEE - Institute of Electrical and Electronics Engineers : Piscataway, NJ. 10.1109/ISBI.2019.8759435

Type

Communication / Conférence

Date

2019

Titre du colloque

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)

Date du colloque

2019-04

Ville du colloque

Venise

Pays du colloque

Italy

Titre de l'ouvrage

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)

Éditeur

IEEE - Institute of Electrical and Electronics Engineers

Ville d’édition

Piscataway, NJ

Chen, Da

Cohen, Laurent D.
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Huazhong, Shu
Centre de Recherche en Information Biomédicale sino-français [CRIBS]
Pâques, Michel
Institut de la Vision

Résumé (EN)

In this work, we propose a new minimal path model with a dynamic Riemannian metric to overcome the shortcuts problem in vessel extraction. The invoked metric consists of a crossing-adaptive anisotropic radius-lifted tensor field and a front freezing indicator. It is able to reduce the anisotropy of the metric on the crossing points and steer the front evolution by freezing the points causing high curvature of a geodesic. We validate our model on the DRIVE and IOSTAR datasets, and the segmentation accuracy is 0.861 and 0.881, respectively. The proposed method can extract the centreline position and vessel width efficiently and accuracy.

Mots-clés

Geodesic; anisotropy enhancement; Riemannian metric; path feature; tubular structure segmentation