الفهرس | Only 14 pages are availabe for public view |
Abstract Alzheimer{u2019}s disease (AD) is a considered one of the common elderly disease that causes changes in behavioral and memory loss because of the death of brain cells. There are three stages for Alzheimer disease named: Alzheimer{u2019}s Disease patient (AD), Mild cognitive impairment (MCI) and Early stage. In this work, we purpose the use of the Gaussian map descriptors to distinguish between AD, MCI and normal (N) subjects, by analyzing the hippocampus and amygdala. Based on Gaussian maps, several features were extracted such as the Gaussian curvatures, the mean curvature and Gaussian shape operator, which are then fed to the Support Vector Machine (SVM) in order to employ the classification task. The proposed workflow consists of seven main steps: Eddy current correction, Brain extraction, registration, segmentation, Gaussian map features calculations, and evaluation and validation of results. This thesis gives a detailed implementation for each mentioned steps |