BRAIN TUMOR DETECTION USING PSO AND TEXTURE ANALYSIS OF MRI IMAGES USING PCA FOLLOWED BY ICA

Abstract

Brain tumor segmentation and MRI image analysis is one of the crucial procedures in surgical and treatment planning. Brain tumor segmentation using MRI has been an intense research area. Brain tumors can have various sizes and shapes and may appear at different locations. Brain tumor segmentation consists of separating the different tumor tissues. The method proposed for analysis is segmentation using PSO and analysis through texture feature reduction PCA followed by ICA. In our project we will be using Particle swarm optimization method for image segmentation as it is swarm intelligence based method and so a better optimization technique for segmentation. For tumor detection and analysis, texture or shape analysis can be done. Here we will be using texture analysis for the detection of tumor in brain. In our project we will be extracting GLCM features and then reducing the feature set using PCA followed by ICA. The reduction of features is done in order to reduce the complexity and redundancy as the features obtained are large in number. The classification will be done using SVM and different parameters like accuracy and time will be computed in order to compare with other methods that were being used earlier like PCA, LDA etc. The technology used in our project for implementation MATLAB 2015.