Automated 2-D cephalometric analysis of X-ray by image registration approach based on least square approximator

Abstract

This paper presents a new approach to cephalometric x-ray landmark localization. This approach is based on extracting features from face profile of the lateral skull x-ray. The extracted side profile is then segmented based on knowledge of known local facial structures. Once the face profile is properly segmented, nine perceptually significant landmarks (fiducial points) on the face are registered based on a local maximum curvature computation. These fiducial points are used for point-by-point correspondence to find the transformation coefficients of the control points between two images of a scene. Next, we use the obtained coefficients to find the locations of other landmarks on the target image by mapping the landmarks of the reference image. The algorithm was tested on more than 80 x-ray images to locate 20 landmarks. It was possible to locate the landmarks with accuracy of +/-2mm on more 90% of the landmarks.