HYBRID FIREFLY SWARM INTELLIGENCE BASED FEATURE SELECTION FOR MEDICAL DATA CLASSIFICATION AND SEGMENTATION IN SVD - NSCT DOMAIN.

In this paper, the diagnosis of childhood Atypical Teratoid /Rhabdoid tumor (AT/RT) in magnetic resonance brain images and Hemochromatosis in Computed Tomography (CT) liver images, through the hybridization of particle swarm optimization and firefly (PSO-FF) algorithms for feature selection has been presented. Here, the features are extracted through Non-sub Sampled Contourlet Transform (NSCT) to collect the information in all the directions including the edges from the images, Singular Value Decomposition (SVD) to enhance the image and to get the algebraic details, Gray Level Co-occurrence Matrix (GLCM) method to obtain the statistical textural features from the images. All these features are fused together, then the hybridized meta-heuristics algorithms are applied to extract the salient features from the feature set. The ability of global thinking (gbest) in PSO has been combined with the local search capability of firefly to achieve good results. The Radial Basis Function - Support Vector Machine (RBF-SVM) classifier has been used for the classification of brain and liver disease. The affected part was segmented by using expectation maximization algorithm.