MRI Brain Tumor Classification Using Cuckoo Search Support Vector Machines and Particle Swarm Optimization Based Feature Selection

This paper presents an advance of a novel approach for automated diagnosis, on basis of classification of Magnetic Resonance Imaging (MRI) human brain images. Wavelet Transform is utilized for feature extraction. For feature selection Particle Swarm Optimization (PSO) is applied to decrease features size. To optimize support vector machine (SVM) parameters we utilize Cuckoo Search and Support Vector Machine (CS-SVM) model. SVM is applied to create the classifier.