Statistical Shape Analysis Using Fixed Topology Skeletons: Corpus Callosum Study

Abstract

The goal of this work is to develop an approach to shape representation and classification that will allow us to detect and quantify differences in shape of anatomical structures due to various disorders. We used a robust version of skeletons for feature extraction and linear discriminant analysis (the Fisher linear discriminant and the linear Support Vectors method) for classification. We propose a way to map the classification results back into the image domain, interpreting shape differences as a deformation required to bring a shape from one class to the other. An example of analyzing corpus callosum shape in schizophrenia is reported, as well as the results of the study of the statistical properties of the classifier using cross validation techniques.