Segmentation of proximal femur in digital radiographic image using principal component model

In this paper we propose a segmentation of femur bone based on principal component model (PCM). The PCM is an analysis of principal component along with shape and appearance model of an object. Principal Component Analysis (PCA) is mostly used as a tool in exploratory data analysis and for making predictive models. An active shape model segmentation scheme is presented that is steered by optimal local features in the original formulation. A nonlinear NN-classifier is used, instead of the linear Mahalanobis distance, to find optimal displacements for landmarks. For each of the landmarks that describe the shape, at each resolution level taken into account during the segmentation procedure, a distinct set of optimal features is determined. The selection of features is automatic, using the training images and sequential feature forward and backward selection. The PCM based femur bone segmentation approach was tested on right proximal femur digital X-ray images obtained from 50 [n=50, age ± SD= 50.12 ± 13.7 years] Indian women and has produced 74% and 70% of sensitivity and specificity respectively.