الفهرس | Only 14 pages are availabe for public view |
Abstract Brain diseases constitute one of the major causes of cancer related death among children and adults in the world. Brain diseases like brain tumors are characterized as the growing of abnormal cells inside or around the brain. There are various imaging techniques, which are used for brain tumor detection. Among all imaging techniques, Magnetic Resonance Imaging (MRI) is widely used for brain tumor detection. The MRI is a safe, fast, and non-invasive imaging technique. The early detection of brain diseases is very important. So, Computer-Aided-Diagnosis (CAD) systems are used. This thesis presents two approaches for the classification of MR images. The first proposed system implements a Gray Wolf Optimizer (GWO) combined with a supervised Artificial Neural Network (ANN) classifier to achieve enhanced MRI classification accuracy via selecting the optimal parameters of the ANN. The proposed GWO-ANN method classifies the given MR brain image as normal or abnormal. The second proposed system is a hybrid system based on a combination of GWO and a Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel to classify a given MR brain image as either benign or malignant. A standard real dataset consisting of T2-weighted magnetic resonance brain images in an axial plane and 256×256 in plane resolution is utilized to validate the proposed scheme. The experimental results show that the suggested schemes achieve better results than those of the state-of-the-art techniques. |