Feature Selection and Mass Classification Using Particle Swarm Optimization and Support Vector Machine

摘要: This paper proposes an effective technique to classify regions of interests (ROIs) digitized mammograms into mass and normal breast tissue by using particle swarm optimization (PSO) based feature selection Support Vector Machine (SVM). Twenty-three texture features were derived from the gray level co-occurrence matrix (GLCM) histogram each ROI. PSO is used search for gamma C parameters SVM with RBF kernel which will give best classification accuracy, all 23 features. Using found PSO, determine significant Experimental results show that proposed can find improve accuracy SVM. The approach has better specificity sensitivity when compared other techniques.