Combination of Multiple Features in Support Vector Machine with Principal Component Analysis in Application for Alzheimer's Disease Diagnosis

Alzheimer's disease (AD) is a progressively neuro-degenerative disorder characterized by symptoms such as memory loss and cognitive degeneration. In the AD-related research, the volumetric analysis of hippocampus is the most extensive study. However, the segmentation and identification of the hippocampus are highly complicated and time-consuming. Therefore, we designed a MRI-based classification framework to distinguish AD's patients from normal individuals. First, volumetric features and shape features were extracted from MRI data. Afterward, Principle component analysis (PCA) was utilized to decrease the dimensions of feature space. Finally, a SVM classifier was trained for AD classification. With the proposed framework, the classification accuracy is improved from 73.08% or 76.92%, by only using volumetric features or shape features, to 92.31% by using three kinds of volume features and two kinds of shape features.