A Concise Review Of MRI Feature Extraction And Classification With Kernel Functions

Magnetic resonance imaging is a common medical imaging tool for the identification and monitoring of brain diseases. Accurate classification of MRI brain pictures is extremely beneficial for early diagnosis and therapy planning. In this study, a method for MRI classification and feature extraction using a Support Vector Machine (SVM) and hybrid RBF which is radial Basis function kernel is proposed. Some of the interconnected steps in the suggested methodology include pre-processing, hybrid RBF kernel creation, feature extraction, SVM classification, feature selection, model evaluation, and model optimization. The GLCM technique is utilized to derive texture characteristics from MRI images. A blend of multiple RBF kernels with different parameter settings yields a hybrid RBF kernel. Performance indicators are used to assess the SVM classifier after it has been trained on a training dataset. The hybrid RBF kernel and the SVM's parameters are altered using model optimization. The suggested methodology intends to classify MRI brain pictures appropriately for enhanced treatment planning and disease diagnosis.