A study of feature extraction for Alzheimer's disease based on resting-state fMRI

The Alzheimer's Disease (AD) has become a major threat of human health with its incidence rate ascending year by year. Early diagnosis of AD is very important for AD patients to keep life quality. The resting-state fMRI (rs-fMRI) which precisely reflects the brain changes on the resting state of individuals provides a quantitative approach, which has been introduced to distinguish AD patients from normal population. In this study, we proposed a method to find the most distinctive features identifying AD patients from rs-fMRI images. The ALFF and ReHo parameters based on pre-processed rs-fMRI data were extracted, and some key parameters of the brain functional network based on graph theory were calculated. Then we tested the recognition performance of different classifiers, and the best classification algorithm, that is, Support Vector Machine (SVM) with linear-kernel are selected. Finally through a recursive feature selection procedure, we got the most distinctive feature set. Additionally, this study also implies that there may be several changes in some particular ROIs of the brain during the AD development.