Comparison of Feature Selection Techniques for Detection of Malignant Tumor in Brain Images

Abstract

This paper presents and compares feature selection algorithms for the detection of glioblastoma multiforme in brain images. Texture features are extracted from normal and tumor regions (ROI) using spatial gray level dependence method and wavelet transform. An artificial neural network has been used for classification. A very difficult problem in classification. techniques is the choice of features to distinguish between classes. The feature optimization problem is addressed using a genetic algorithm (GA) as a search method. Principal component analysis, classical sequential methods and floating search algorithm are compared against the genetic approach in terms of the best recognition rate achieved and the optimal number of features. The classification performance of 97.3% is achieved in GA with optimal features compared to sequential methods and Principal component analysis.