摘要
Abstract
In Alzheimer′s Disease (AD) diagnostic method,analyzing brain images has become an important means to accurate diagnosis.In this paper,we only consider brain featuresextracted from single modality brain images MRI,propose a new identification algorithm based on principal component analysis (PCA) and linear discriminant analysis (LDA) for AD classification recognition algorithm.First,it makes PCA in the original brain feature extracted from single modality brain images MRI.Second,it makes LDA in low dimensional features from PCA method,so that we obtain the combinational feature vector.Finally,we adopt nearest neighbor algorithm incombinational feature vector toclassification and recognize unknown type brain features.Experimental results have shown that,compared with the related algorithms,the proposed algorithm possesses higher classification accuracy,sensitivity and specificity.Therefore,our algorithm is effective.关键词
阿尔茨海默病/脑图像分析/主成分分析/线性鉴别分析/最邻近算法Key words
Alzheimer′s disease/brain image analysis/principal component analysis/linear discriminant analysis/nearest neighbor algorithm分类
信息技术与安全科学
