Department of Biomedical Science and Engineering (BMSE), Institute of Integrated Technology (IIT), Gwangju Institute of Science and Technology (GIST), Gwangju, Republic of Korea.
Translational Neuroimaging Laboratory, The McGill University Research Center for Studies in Aging (MCSA), McGill University, Montreal, Canada.
PLoS One. 2019 Feb 22;14(2):e0212582. doi: 10.1371/journal.pone.0212582. eCollection 2019.
Early 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.
We 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.
The maximal accuracies achieved by the method in the ADNI2 cohort were 98.86% (p<0.001) and 98.57% (p<0.001) for AD and MCI vs. CN, respectively. In the in-house cohort, the same accuracies were 98.70% (p<0.001) and 94.16% (p<0.001).
From a clinical perspective, combining extreme learning machine and hybrid MVPA applied on concatenations of multiple rs-fMRI biomarkers can potentially assist the clinicians in AD and MCI diagnosis.
阿尔茨海默病（AD）和轻度认知障碍（MCI）的早期诊断对于及时治疗至关重要。机器学习和多变量模式分析（MVPA）在脑疾病诊断中的应用在神经影像学领域受到了特别关注。在本文中，我们提出了一种体素级别的判别框架，应用于多模态静息态 fMRI（rs-fMRI），该框架集成了混合 MVPA 和极限学习机（ELM），用于自动区分 AD 和 MCI 与认知正常（CN）状态。
我们使用了两个 rs-fMRI 队列：公共阿尔茨海默病神经影像学倡议数据库（ADNI2）和来自韩国的内部阿尔茨海默病队列，两者均包括 AD、MCI 和正常对照组的个体。在提取测量静息状态下区域相干性和功能连接的三维（3-D）模式后，我们进行了单变量统计 t 检验，生成了一个保留仅显示显著变化的体素的 3-D 掩模。给定初始的单变量特征，为了增强判别模式，我们使用支持向量机递归特征消除（SVM-RFE）和最小绝对值收缩和选择算子（LASSO）结合单变量 t 检验来进行 MVPA 特征降维。分类由 ELM 执行，并将其效率与线性和非线性（径向基函数）SVM 进行比较。
该方法在 ADNI2 队列中的最大准确率为 AD 和 MCI 与 CN 相比分别为 98.86%（p<0.001）和 98.57%（p<0.001）。在内部队列中，相同的准确率为 98.70%（p<0.001）和 94.16%（p<0.001）。
从临床角度来看，将极限学习机和混合 MVPA 结合应用于多个 rs-fMRI 生物标志物的串联，可以为临床医生在 AD 和 MCI 诊断中提供帮助。
