Investigation of filter sets for supervised pixel classification of cephalometric landmarks by spatial spectroscopy.

The diagnostic process of orthodontics requires the analysis of a cephalometric radiograph. Image landmarks on this two-dimensional lateral projection image of the patient's head are manually identified and spatial relationships are evaluated. This method is very time consuming. A reliable method for automatic computer landmark identification does not exist. Spatial Spectroscopy is a proposed method of automatic landmark identification on cephalometric radiographs, that decomposes an image by convolving it with a set of filters followed by a statistical decision process. The purpose of this paper is to discuss and test appropriate filter sets for the application of Spatial Spectroscopy for automatic identification of cephalometric radiographic landmarks. This study evaluated two different filter sets with 15 landmarks on fourteen images. Spatial Spectroscopy was able to consistently locate landmarks on all 14 cephalometric radiographs tested. The mean landmark identification error of 0.841 +/- 1.253 pixels for a Multiscale Derivative filter set and 0.912 +/- 1.364 pixels for an Offset Gaussian filter set was not significantly different. Furthermore, there were no significant differences between identification of individual landmarks for the Multiscale Derivative and the Offset Gaussian filter set (P > 0.05). These results suggest that Spatial Spectroscopy may be useful in landmark identification tasks.