A Brainnetome Atlas Based Mild Cognitive Impairment Identification Using Hurst Exponent.

Zhuqing Long,Hongwen Chen,Bin Jing,Bo Li,Feiyi Cui,Ru Guo,Tingting Wang

doi:10.3389/fnagi.2018.00103

Abstract

Mild cognitive impairment (MCI), which generally represents the transition state between normal aging and the early changes related to Alzheimer’s disease (AD), has drawn increasing attention from neuroscientists due that efficient AD treatments need early initiation ahead of irreversible brain tissue damage. Thus effective MCI identification methods are desperately needed, which may be of great importance for the clinical intervention of AD. In this article, the range scaled analysis, which could effectively detect the temporal complexity of a time series, was utilized to calculate the Hurst exponent (HE) of functional magnetic resonance imaging (fMRI) data at a voxel level from 64 MCI patients and 60 healthy controls (HCs). Then the average HE values of each region of interest (ROI) in brainnetome atlas were extracted and compared between MCI and HC. At last, the abnormal average HE values were adopted as the classification features for a proposed support vector machine (SVM) based identification algorithm, and the classification performance was estimated with leave-one-out cross-validation (LOOCV). Our results indicated 83.1% accuracy, 82.8% sensitivity and 83.3% specificity, and an area under curve of 0.88, suggesting that the HE index could serve as an effective feature for the MCI identification. Furthermore, the abnormal HE brain regions in MCI were predominately involved in left middle frontal gyrus, right hippocampus, bilateral parahippocampal gyrus, bilateral amygdala, left cingulate gyrus, left insular gyrus, left fusiform gyrus, left superior parietal gyrus, left orbital gyrus and left basal ganglia.

Highlights

Applying the proposed support vector machine (SVM)-based classification method to identify Mild cognitive impairment (MCI) patients from healthy controls (HCs) subjects, our results indicated 83.1% accuracy, 82.8% sensitivity and 83.3% specificity
This study proposed an effective classification method to identify MCI patients from HC subjects using Hurst exponent (HE) index of rs-Functional magnetic resonance imaging (fMRI)
A promising classification performance was obtained with an accuracy of 83.1% and an area under curve value of 0.88, suggesting that the proposed SVM-based method was effective in identifying MCI from HC subjects, and the calculated HE index could serve as an effective feature for the SVM-based classification algorithm

Summary

Introduction

Mild cognitive impairment (MCI), which is characterized by memory complaints, attention deficits and other reduced cognitive functions (Petersen, 2007; Han et al, 2011; Zhang et al, 2012), generally represents the transition state between normal aging and the early changes related to Alzheimer’s disease (AD; Desikan et al, 2009; Wang et al, 2015).MCI Identification With Hurst ExponentOverall, MCI patients progress to AD at a rate of 10%–15% per year (Khazaee et al, 2016), and roughly half of them will evolve to AD within 3–5 years (Long et al, 2016). Mild cognitive impairment (MCI), which is characterized by memory complaints, attention deficits and other reduced cognitive functions (Petersen, 2007; Han et al, 2011; Zhang et al, 2012), generally represents the transition state between normal aging and the early changes related to Alzheimer’s disease (AD; Desikan et al, 2009; Wang et al, 2015). Many recent studies employed rs-fMRI data to identify MCI or AD from healthy controls (HCs) by extracting a single type of feature or multi-level characteristics (Chen et al, 2011; Dai et al, 2012; Zhang et al, 2012; Brier et al, 2014; Long et al, 2016), and the recognition accuracies were varied with a wide range, suggesting the MCI or AD discrimination needs to be continued. An effective rs-fMRI based MCI or AD discrimination method should: (I) exhibit an excellent discrimination accuracy between MCI or AD and HC; (II) quantify fundamental characteristics of Alzheimer’s pathology in individuals with MCI or AD

Methods

Results

Conclusion