北京生物医学工程

基于静息态fMRI信号复杂度的MCI识别研究

MCI recognition based on the complexity of resting state fMRI signal

作者：董建鑫王川

单位：首都医科大学燕京医学院（北京 101300） <br />通信作者：董建鑫。E-mail: dongjianxin@ccmu.edu.cn 

关键词：轻度认知障碍；静息态功能磁共振成像；Hurst指数；独立成份分析；支持向量机

分类号：R318.04

出版年·卷·期（页码）：2022·41·6（564-568）

摘要：

目的基于静息态功能磁共振图像，提取默认网络特征脑区的信号复杂度参数建立轻度认知障碍（mild cognitive impairment, MCI）的分类模型。方法研究数据来源于阿尔茨海默症神经成像数据库，包含48名正常对照人群和53位MCI。首先进行独立成份分析，针对分离出的独立成份分别计算对应时间序列的Hurst指数。然后在体素水平上采用双样本T检验选择左侧眶部额下回、左侧额上回和左侧额中回作为特征脑区，计算其Hurst指数作为分类特征。最后用支持向量机对MCI患者进行识别，并评价模型的准确率、灵敏度、特异度以及接收操作特征（receiver operating characteristics, ROC）曲线下面积。结果基于MCI和正常对照两组构建的分类模型，获得了最高88.71%的分类准确率、90.91%的灵敏度和86.21%的特异度。此外，ROC曲线的最大线下面积为0.96。结论 Hurst指数可以反映MCI患者异常脑功能活动，基于独立成份分析和支持向量机的方法能有效地识别MCI患者，具有一定的临床辅助诊断意义。

Objective Based on resting-state functional magnetic resonance images, signal complexity parameters of the default network characteristic brain regions were extracted to establish the classification model of mild cognitive impairment (MCI). Methods Data is from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database included 48 normal controls and 53 MCI patients. Firstly, the independent component analysis is carried out, and the Hurst exponent of corresponding time series is calculated for the separated independent components. Then, at the voxel level, two-sample T test was used to select the left orbital part of inferior frontal gyrus, left superior frontal gyrus and left middle frontal grus as characteristic brain regions, and their Hurst exponent was calculated as classification features. Finally, support vector machine was used to identify MCI patients, and the accuracy, sensitivity, specificity and area under receiver operating characteristics (ROC) curve of the model were evaluated. Results The classification model based on MCI and normal control group obtained the highest classification accuracy of 88.71%, sensitivity of 90.91% and specificity of 86.21%. In addition, the maximum area under ROC curve was 0.96. Conclusions Hurst exponent can reflect abnormal brain functional activities of MCI patients. Methods based on independent component analysis and support vector machine can effectively identify MCI patients, which has certain clinical diagnostic significance.

参考文献：

[1] Petersen RC, Smith GE , Waring SC, et al. Mild cognitive impairment: clinical characterization and outcome[J]. Archives of Neurology, 1999, 56(3): 303-308.?
[2] Landau SM, Harvey D, Madison CM, et al. Comparing predictors of conversion and decline in mild cognitive impairment[J]. Neurology, 2010, 75(3): 230-238.
[3] Pozueta A, Rodríguez-Rodríguez E, ?Vazquez-Higuera JL, et al. Detection of early Alzheimer's disease in MCI patients by the combination of MMSE and an episodic memory test[J]. BMC Neurology, 2011, 11: 78.
[4] Mueller SG, Weiner MW, Thal LJ, et al. Ways toward an early diagnosis in Alzheimer's disease: the Alzheimer's Disease Neuroimaging Initiative (ADNI)[J]. Alzheimers & Dementia, 2005, 1(1): 55-66.
[5] 文玉, 刘擘, 王效春. 脑静息态功能磁共振局部一致性分析在轻度认知障碍患者中的初步研究[J]. 磁共振成像, 2020,11(4): 253-258.
Wen Y, Liu B, Wang XC. Preliminary study of brain resting state functional magnetic resonance local consistency analysis in patients with mild cognitive impairment[J]. Chinese Journal of Magnetic Resonance Imaging, 2020,11(4): 253-258.
[6] Li Y, Wang X, Li Y, et al. Abnormal resting-state functional connectivity strength in mild cognitive impairment and its conversion to Alzheimer's disease[J]. Neural Plasticity, 2016, 2016: 4680972.
[7] Liu J, Zhang X, Yu C, et al. Impaired parahippocampus connectivity in mild cognitive impairment and Alzheimer's disease[J]. Journal of Alzheimer's Disease, 2016, 49(4):1051-1064.
[8] Maxim V, ?endur L, Fadili J, et al. Fractional Gaussian noise, functional MRI and Alzheimer's disease[J]. Neuroimage, 2005, 25(1):141-158.
[9] 杨宇轩, 陶玲, 钱志余. 基于Hurst指数的脑胶质瘤分级方法[J]. 北京生物医学工程, 2019, 38(3): 271-276.
Yang YX, Tao L, Qian ZY. Grading method of gliomas based on Hurst index[J]. Beijing Biomedical Engineering, 2019, 38(3): 271-276.
[10] 邹燕,王松伟,李霁,等. 脑默认模式网络显示临床慢性疼痛程度变化的研究[J]. 中国医学计算机成像杂志, 2017,23(6): 504-507.
Zou Y, Wang SW, Li J, et al. Study of the effect of variation intensities of chronic pain on the default mode network at resting-state[J]. Chinese Computed Medical Imaging, 2017, 23(6): 504-507.
[11] Porcaro C, Mayhew SD, Marino M, et al. Characterisation of haemodynamic activity in resting state networks by fractal analysis[J]. International Journal of Neural Systems, 2020, 30(12): 2050061.
[12] Veer IM, Beckmann CF, van Tol MJ, et al. Whole brain resting-state analysis reveals decreased functional connectivity in major depression[J]. Frontiers in Systems Neuroscience, 2010, 4: 41.
[13] Zuo XN, Kelly C, Adelstein JS, et al. Reliable intrinsic connectivity networks: test–retest evaluation using ICA and dual regression approach[J]. Neuroimage, 2010, 49: 2163-2177.
[14] Koch W, Teipel S, Mueller S, et al. Diagnostic power of default mode network resting state fMRI in the detection of Alzheimer's disease[J]. Neurobiology of Aging, 2012, 33(3): 466-478.
[15] Greicius MD, Srivastava G, Reiss AL, et al. Default-mode network activity distinguishes Alzheimer's disease from healthy aging: evidence from functional MRI[J]. PNAS, 2004, 101(13): 4637-4642.
[16] Pereira F, Mitchell T, Botvinick M. Machine learning classifiers and fMRI: a tutorial overview[J]. Neuroimage, 2009, 45(1 Suppl): S199-S209.
[17] Dosenbach NU, Nardos B, Cohen AL, et al. Prediction of individual brain maturity using fMRI[J]. Science, 2010, 329(5997): 1358-1361.
[18] Dai Z, Yan C, Wang Z, et al. Discriminative analysis of early Alzheimer's disease using multi-modal imaging and multi-level characterization with multi-classifier (M3)[J]. Neuroimage, 2012, 59(3): 2187-2195.
[19] Gerardin E, Chételat G, Chupin M. Multidimensional classification of hippocampal shape features discriminates Alzheimer's disease and mild cognitive impairment from normal aging[J]. Neuroimage, 2009, 47(4): 1476-1486.?
[20] Desikan RS, Cabral HJ, Hess CP, et al. Automated MRI measures identify individuals with mild cognitive impairment and Alzheimer's disease[J]. Brain, 2009, 132(Pt 8): 2048-2057.
[21] Zhang D, Wang Y, Zhou L, et al. Multimodal classification of Alzheimer's disease and mild cognitive impairment[J]. Neuroimage, 2011, 55(3): 856-867.
[22] Long Z, Jing B, Ru G, et al. A brainnetome atlas based mild cognitive impairment identification using Hurst exponent[J]. Frontiers in Aging Neuroence, 2018, 10: 103.
[23] Hmlinen A, Tervo S, Grau-Olivares M, et al. Voxel-based morphometry to detect brain atrophy in progressive mild cognitive impairment[J]. Neuroimage, 2007, 37(4): 1122-1131

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录