Semi-automatic teeth segmentation in cone-beam computed tomography by graph-cut with statistical shape prior - Archive ouverte HAL Access content directly
Conference Papers Year : 2017

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

Abstract

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.
Not file

Dates and versions

hal-02288484 , version 1 (14-09-2019)

Identifiers

  • HAL Id : hal-02288484 , version 1

Cite

Timothée Evain, Xavier Ripoche, J. Atif, Isabelle Bloch. Semi-automatic teeth segmentation in cone-beam computed tomography by graph-cut with statistical shape prior. IEEE International Symposium on Biomedical Imaging, 2017, Melbourne, Australia. pp.1197-1200. ⟨hal-02288484⟩
35 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More