Semi-automatic teeth segmentation in cone-beam computed tomography by graph-cut with statistical shape priors

Evain, Timothée; Ripoche, Xavier; Atif, Jamal; Bloch, Isabelle

Evain, Timothée; Ripoche, Xavier; Atif, Jamal; Bloch, Isabelle (2017), Semi-automatic teeth segmentation in cone-beam computed tomography by graph-cut with statistical shape priors, dans Olivier Salvado, Gary Egan, 14th IEEE International Symposium on Biomedical Imaging (ISBI), IEEE Signal Processing Society : New York, p. 1197-1200. 10.1109/ISBI.2017.7950731

Type

Communication / Conférence

Date

2017

Titre de l'ouvrage

14th IEEE International Symposium on Biomedical Imaging (ISBI)

Auteurs de l’ouvrage

Olivier Salvado, Gary Egan

Éditeur

IEEE Signal Processing Society

Ville d’édition

New York

Isbn

978-1-5090-1172-8

Pages

1197-1200

Résumé (EN)

We propose a new semi-automatic framework for tooth segmentation in Cone-Beam Computed Tomography (CBCT) combining shape priors based on a statistical shape model and graph cut optimization. Poor image quality and similarity between tooth and cortical bone intensities are overcome by strong constraints on the shape and on the targeted area. The segmentation quality was assessed on 64 tooth images for which a reference segmentation was available, with an overall Dice coefficient above 0.95 and a global consistency error less than 0.005.

Mots-clés

Medical imaging; machine learning