Computers in Biology and Medicine
| Hi-index | 0.00 |
The purpose of this study was to explore the automatic method of detecting the gray matter loss of Alzheimer’s disease (AD) patients with magnetic resonance imaging (MRI). In this paper, voxel-based morphometry(VBM) and Support Vector Machine(SVM )were combined and introduced to diagnose Alzheimer's disease(AD) for clinical applications. Firstly, with the VBM method, 20 features were obtained from the accurate structure imaging of possible AD and the controls, and then the principal component analysis(PCA) was used for feature dimensionality reduction to improve the efficiency. Then, a SVM classifier with linear kernel function was used to distinguish AD from healthy controls. Finally, the performance of SVM was evaluated. The accuracy of classifier is proportional to the number of training samples. With 18 training samples, the predictive capability of SVM could reach 100%. And the results will be slightly better under the process of PCA with fewer features. In conclusion, the results of this study confirmed that the method of combining VBM with SVM could be used as an automatic tool for the early diagnosis of AD.