Automatic localization of cephalometric landmarks

Abstract

A system for automatic detection of cephalometric landmarks is study is carried out through the measurement of distances presented. Landmark detection is carried out in two steps: a line detec- and angles between significant structures. Comparison of tion module searches for significant, well-contrasted lines of the image, these measurements with the standards accepted for the same such as the jaw line or the nasal spine. The landmark detection module age, race, and sex is a valuable tool for diagnosis, treatment uses the lines located in the first module to determine the search areas and then applies a pattern detection algorithm, based on mathematical monitoring, and prediction of orthodontic treatment results. morphology techniques. Relations between landmarks and lines are It was d’Arcy Thomson, in 1917 [1], who for the first time determined by means of a training process. The system has been tested analyzed the growth of the head using anatomical landmarks. for the detection of 17 landmarks on 20 images: more than 90% of These landmarks were the nodes of a grid, so changes in their the landmarks are accurately identified. q 2001 Academic Press position resulted in deformations of the grid. His method,