Automatic Detection, Identification, and Registration of Anatomical Landmarks

Abstract

This paper describes a signal processing method for automated detection, identification, and registration (ALDIR) of optically marked anatomical fiduciary landmarks from 3-D laser digitized body segment measurements. The method described is a multistage process. In the first stage, body surface reflectivity and topography information is used to detect optical markers in digitized measurement data. In the second stage, a maximum likelihood identification is used to identify each of the detected landmarks. Finally, the method identified landmarks and their relative spatial coordinates are registered and output. This can be used in a prosthetics-orthotics (or other) computer-aided design and computer-aided manufacturing (CAD/CAM) system to compute a quantitative diagnostic measure of the patient's physiological state; as a measure of efficacy of a given medical treatment regimen; or an addition to an anthropometric/medical data base.