Proposition of local automatic algorithm for landmark detection in 3D cephalometry

This study proposes a new contribution to solve the problem of automatic landmarks detection in three-dimensional cephalometry. 3D images obtained from CBCT (cone beam computed tomography) equipment were used for identification twelve landmarks. The proposed method is based on local geometry and intensity criteria skull structures. After step preprocessing binarization, algorithm segments into three structures using information nasal cavity teeth. Each targeted landmark was detected geometrical volume interest containing this landmark. ICC confidence interval (95% CI) each direction 0, 91 (0.75 0.96) x- direction; 0.92 (0.83 0.97) y-direction; (0.79 z-direction. mean error calculated Euclidian distance between coordinates manually automatically overall 2.76 mm with standard deviation 1.43 mm. Our approach cephalometric capable detecting 12 which can be facilitate use cephalometry orthodontists.