Application of KPCA and AdaBoost algorithm in classification of functional magnetic resonance imaging of Alzheimer’s disease

Abstract

With the rapid development of modern brain imaging techniques and big data analysis that measures brain processes, researchers are increasingly looking to reveal the pathogenesis of Alzheimer’s disease. In order to find effective classification of magnetic resonance images of Alzheimer’s disease, this paper constructed a feature classification model for Alzheimer’s disease based on AdaBoost algorithm and KPCA algorithm, and selected 21 patients with Alzheimer’s disease (AD). The trial included 6 patients with advanced Alzheimer’s disease (LAD), 7 patients with early Alzheimer’s disease, and 8 healthy individuals (HC) who underwent different levels of analysis. The results show that the article uses the KPCA algorithm to obtain the highest classification accuracy of the two groups: 94.77%, the single feature distinguishing ability is the node degree, and the accuracy of 90.94% can be achieved in the imaging diagnosis of AD. The article can significantly improve the classification of magnetic resonance images of Alzheimer’s disease. This result is a good test of the effectiveness of the selected algorithm and has profound clinical significance for the diagnosis and classification of AD using magnetic resonance imaging.