Computer-aided diagnosis of neurodegenerative disease using multiple image features with hybrid PSO-SVM

Mild cognitive impairment (MCI) has a high risk to convert into Alzheimer's disease (AD). In the 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 an MRI-based classification framework to distinguish the patients of MCI and AD from normal individuals. First, volumetric and shape features were extracted from MRI data. Principal component analysis (PCA) was utilized to decrease the dimensions of feature space. Support vector machine (SVM) classifier was trained for classification. Finally, a hybrid classification system based on particle swarm optimization (PSO) improved the performance of the SVM classifier. With the hybrid classification framework based on PSO, the result achieved up to 95.35% and 82.35% in AD and in MCI.