基于监督局部线性嵌入方法的阿尔茨海默病磁共振成像分类研究

Supervised locally linear embedding for magnetic resonance imaging based Alzheimer's disease classification

针对阿尔茨海默病(AD)早期阶段分类这一研究难题,传统的线性特征提取算法很难从其高维特征中挖掘出鉴别能力较强的信息来有效地表示样本特征。因此,本文采用监督局部线性嵌入(SLLE)特征提取算法,对412例受试者的大脑皮质厚度(CTH)和脑感兴趣区域体积(VOI)特征进行提取,减少其冗余特征以提高识别精度。受试者来源于阿尔茨海默病神经影像学(ADNI)数据集,包含93例稳定型轻度认知障碍(s MCI)、96例遗忘型轻度认知障碍(a MCI)、86例AD患者和137例认知正常对照老年人(CN)样本。本文采用的SLLE算法是通过添加距离修正项来计算每个样本点的近邻点,并用近邻点线性表示样本,得到局部重建权值矩阵,进而求出高维数据的低维映射。为验证该算法在分类识别中的有效性,本文将主成分分析(PCA)、近邻最小最大投影(NMMP)、局部线性映射(LLE)及SLLE等特征提取算法分别与支持向量机(SVM)分类器组合,对CN与s MCI、CN与a MCI、CN与AD、s MCI与a MCI、s MCI与AD和a MCI与AD六组实验数据进行分类识别。结果显示,以VOI为特征,利用SLLE和SVM的复合算法对s MCI和a MCI的分类准确度、灵敏度、特异性分别为65.16%、63.33%、67.62%,基于LLE和SVM的复合算法分类结果分别为64.08%、66.14%、62.77%,而基于传统SVM则分别为57.25%、56.28%、58.08%。经比较,发现SLLE和SVM组合算法的识别精度较LLE和SVM的组合算法提高了1.08%,较SVM提高了7.91%。因此,利用SLLE和SVM这一复合算法进行分类识别更有利于AD的早期诊断。

In order to solve the problem of early classification of Alzheimer＇s disease（AD）, the conventional linear feature extraction algorithm is difficult to extract the most discriminative information from the highdimensional features to effectively classify unlabeled samples. Therefore, in order to reduce the redundant features and improve the recognition accuracy, this paper used the supervised locally linear embedding（SLLE） algorithm to transform multivariate data of regional brain volume and cortical thickness to a locally linear space with fewer dimensions. The 412 individuals were collected from the Alzheimer＇s Disease Neuroimaging Initiative（ADNI）including stable mild cognitive impairment（s MCI, n = 93）, amnestic mild cognitive impairment（a MCI, n = 96）, AD（n =86） and cognitive normal controls（CN, n = 137）. The SLLE algorithm used in this paper is to calculate the nearest neighbors of each sample point by adding the distance correction term, and the locally linear reconstruction weight matrix was obtained from its nearest neighbors, then the low dimensional mapping of the high dimensional data can be calculated. In order to verify the validity of SLLE in the task of classification, the feature extraction algorithms such as principal component analysis（PCA）, Neighborhood Min Max Projection（NMMP）, locally linear mapping（LLE） and SLLE were respectively combined with support vector machines（SVM） classifier to obtain the accuracy of classification of CN and s MCI, CN and a MCI, CN and AD, s MCI and a MCI, s MCI and AD, and a MCI and AD, respectively.Experimental results showed that our method had improvements（accuracy/sensitivity/specificity： 65.16%/63.33%/67.62%） on the classification of s MCI and a MCI by comparing with the combination algorithm of LLE and SVM（accuracy/sensitivity/specificity： 64.08%/66.14%/62.77%） and SVM（accuracy/sensitivity/specificity：57.25%/56.28%/58.08%）. In detail the accuracy of the combination algorithm of SLLE and SVM is 1.08% higher than the combination algorithm of LLE and SVM, and 7.91% higher than SVM. Thus, the combination of SLLE and SVM is more effective in the early diagnosis of Alzheimer＇s disease.