Hybrid multivariate pattern analysis combined with extreme learning machine for Alzheimer's dementia diagnosis using multi-measure rs-fMRI spatial patterns
Hybrid multivariate pattern analysis combined with extreme learning machine for Alzheimer's dementia diagnosis using multi-measure rs-fMRI spatial patterns
复制标题
DOI：
10.1371/journal.pone.0212582
复制
发表时间：
2019-02-22
期刊：
影响因子：
3.7
通讯作者：
Lee, Boreom
中科院分区：
文献类型：
--
作者：
Duc Thanh Nguyen;Ryu, Seungjun;Lee, Boreom
研究背景阿尔茨海默病（Alzheimer 'sdisease，AD）和轻度认知功能障碍（mildcognitiveimpairment，MCI）的早期诊断是及时治疗的关键.机器学习和多变量模式分析（MVPA）用于大脑疾病的诊断正在引起神经影像学界的关注。在本文中，我们提出了一个适用于多测量静息状态fMRI（rs-fMRI）的体素判别框架，该框架集成了混合MVPA和极端学习机（ELM），用于自动判别AD和MCI与认知正常（CN）状态。公共阿尔茨海默病神经影像学倡议数据库（ADNI 2）和来自韩国的内部阿尔茨海默病队列，两者都包括AD，MCI和正常对照的个体。在提取三维（3-D）模式测量区域的连贯性和功能连接在休息状态下，我们进行了单变量统计t检验，以生成一个3-D掩模，只保留体素显示显着的变化。给定初始单变量特征，为了增强鉴别模式，我们使用支持向量机递归特征消除（SVM-RFE）和最小绝对收缩和选择算子（LASSO）结合单变量t检验实现MVPA特征约简。ELM进行分类，其效率进行了比较，线性和非线性（径向基函数）SVM。
BackgroundEarly diagnosis of Alzheimer's disease (AD) and Mild Cognitive Impairment (MCI) is essential for timely treatment. Machine learning and multivariate pattern analysis (MVPA) for the diagnosis of brain disorders are explicitly attracting attention in the neuroimaging community. In this paper, we propose a voxel-wise discriminative framework applied to multi-measure resting-state fMRI (rs-fMRI) that integrates hybrid MVPA and extreme learning machine (ELM) for the automated discrimination of AD and MCI from the cognitive normal (CN) state.Materials and methodsWe used two rs-fMRI cohorts: the public Alzheimer's disease Neuroimaging Initiative database (ADNI2) and an in-house Alzheimer's disease cohort from South Korea, both including individuals with AD, MCI, and normal controls. After extracting three-dimensional (3-D) patterns measuring regional coherence and functional connectivity during the resting state, we performed univariate statistical t-tests to generate a 3-D mask that retained only voxels showing significant changes. Given the initial univariate features, to enhance discriminative patterns, we implemented MVPA feature reduction using support vector machine-recursive feature elimination (SVM-RFE), and least absolute shrinkage and selection operator (LASSO), in combination with the univariate t-test. Classifications were performed by an ELM, and its efficiency was compared to linear and nonlinear (radial basis function) SVMs.ResultsThe maximal accuracies achieved by the method in the ADNI2 cohort were 98.86% (p