Comparison of Linear Discriminant Analysis and Support Vector Machine in Classification of Subdural and Extradural Hemorrhages

Abstract

This paper describes new features for the classification of different types of extra-axial intracranial hemorrhages namely subdural hemorrhage(SDH) and extradural hemorrhage(EDH) on brain computed tomography(CT) scans. The main objective is to create an automatic retrieval system to reduce the time spent searching manually for the hemorrhagic images. Besides, the challenge is to locate suitable features to differentiate the SDH and EDH. One of the methods to distinguish EDH and SDH is through their shapes. Thus, a shape-based feature extraction is proposed in order to differentiate the SDH and EDH. For the classification part, we present a comparative study of linear discriminant analysis(LDA) and support vector machine(SVM) with linear kernal for the classification of SDH, EDH and normal regions. Both pattern classification techniques map pattern vectors to a high dimensional feature space to construct the optimal margin separating hyperplane. To conclude, SVM outperforms LDA from the obtained classification results.