A comprehensive analysis of resting state fMRI measures to classify individual patients with Alzheimer's disease

被引:136
作者
de Vos, Frank [1 ,2 ,3 ]
Koini, Marisa [4 ]
Schouten, Tijn M. [1 ,2 ,3 ]
Seiler, Stephan [4 ]
van der Grond, Jeroen [2 ]
Lechner, Anita [4 ]
Schmidt, Reinhold [4 ]
de Rooij, Mark [1 ,3 ]
Rombouts, Serge A. R. B. [1 ,2 ,3 ]
机构
[1] Leiden Univ, Inst Psychol, Wassenaarseweg 52, NL-2333 AK Leiden, Netherlands
[2] Leiden Univ, Med Ctr, Dept Radiol, Albinusdreef 2, NL-2333 ZA Leiden, Netherlands
[3] Leiden Inst Brain & Cognit, Albinusdreef 2, NL-2333 ZA Leiden, Netherlands
[4] Med Univ Graz, Dept Neurol, Auenbruggerpl 22, A-8036 Graz, Austria
关键词
Resting state fMRI; Alzheimer's disease; Classification; Independent component analysis; Dual regression; Dynamic functional connectivity; MILD COGNITIVE IMPAIRMENT; DYNAMIC FUNCTIONAL CONNECTIVITY; INDEPENDENT COMPONENT ANALYSIS; EIGENVECTOR CENTRALITY; BRAIN ACTIVITY; NETWORK; CLASSIFICATION; MRI; IMPLEMENTATION; PREDICTION;
D O I
10.1016/j.neuroimage.2017.11.025
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
Alzheimer's disease (AD) patients show altered patterns of functional connectivity (FC) on resting state functional magnetic resonance imaging (RSfMRI) scans. It is yet unclear which RSfMRI measures are most informative for the individual classification of AD patients. We investigated this using RSfMRI scans from 77 AD patients (MMSE = 20.4 +/- 4.5) and 173 controls (MMSE = 27.5 +/- 1.8). We calculated i) FC matrices between resting state components as obtained with independent component analysis (ICA), ii) the dynamics of these FC matrices using a sliding window approach, iii) the graph properties (e.g., connection degree, and clustering coefficient) of the FC matrices, and iv) we distinguished five FC states and administered how long each subject resided in each of these five states. Furthermore, for each voxel we calculated v) FC with 10 resting state networks using dual regression, vi) FC with the hippocampus, vii) eigenvector centrality, and viii) the amplitude of low frequency fluctuations (ALFF). These eight measures were used separately as predictors in an elastic net logistic regression, and combined in a group lasso logistic regression model. We calculated the area under the receiver operating characteristic curve plots (AUC) to determine classification performance. The AUC values ranged between 0.51 and 0.84 and the highest were found for the FC matrices (0.82), FC dynamics (0.84) and ALFF (0.82). The combination of all measures resulted in an AUC of 0.85. We show that it is possible to obtain moderate to good AD classification using RSfMRI scans. FC matrices, FC dynamics and ALFF are most discriminative and the combination of all the resting state measures improves classification accuracy slightly.
引用
收藏
页码:62 / 72
页数:11
相关论文
共 82 条
  • [61] Amyloid Plaques Disrupt Resting State Default Mode Network Connectivity in Cognitively Normal Elderly
    Sheline, Yvette I.
    Raichle, Marcus E.
    Snyder, Abraham Z.
    Morris, John C.
    Head, Denise
    Wang, Suzhi
    Mintun, Mark A.
    [J]. BIOLOGICAL PSYCHIATRY, 2010, 67 (06) : 584 - 587
  • [62] Decoding Subject-Driven Cognitive States with Whole-Brain Connectivity Patterns
    Shirer, W. R.
    Ryali, S.
    Rykhlevskaia, E.
    Menon, V.
    Greicius, M. D.
    [J]. CEREBRAL CORTEX, 2012, 22 (01) : 158 - 165
  • [63] A Sparse-Group Lasso
    Simon, Noah
    Friedman, Jerome
    Hastie, Trevor
    Tibshirani, Robert
    [J]. JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS, 2013, 22 (02) : 231 - 245
  • [64] Advances in functional and structural MR image analysis and implementation as FSL
    Smith, SM
    Jenkinson, M
    Woolrich, MW
    Beckmann, CF
    Behrens, TEJ
    Johansen-Berg, H
    Bannister, PR
    De Luca, M
    Drobnjak, I
    Flitney, DE
    Niazy, RK
    Saunders, J
    Vickers, J
    Zhang, YY
    De Stefano, N
    Brady, JM
    Matthews, PM
    [J]. NEUROIMAGE, 2004, 23 : S208 - S219
  • [65] Functional connectomics from resting-state fMRI
    Smith, Stephen M.
    Vidaurre, Diego
    Beckmann, Christian F.
    Glasser, Matthew F.
    Jenkinson, Mark
    Miller, Karla L.
    Nichols, Thomas E.
    Robinson, Emma C.
    Salimi-Khorshidi, Gholamreza
    Woolrich, Mark W.
    Barch, Deanna M.
    Ugurbil, Kamil
    Van Essen, David C.
    [J]. TRENDS IN COGNITIVE SCIENCES, 2013, 17 (12) : 666 - 682
  • [66] Temporally-independent functional modes of spontaneous brain activity
    Smith, Stephen M.
    Miller, Karla L.
    Moeller, Steen
    Xu, Junqian
    Auerbach, Edward J.
    Woolrich, Mark W.
    Beckmann, Christian F.
    Jenkinson, Mark
    Andersson, Jesper
    Glasser, Matthew F.
    Van Essen, David C.
    Feinberg, David A.
    Yacoub, Essa S.
    Ugurbil, Kamil
    [J]. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2012, 109 (08) : 3131 - 3136
  • [67] Network modelling methods for FMRI
    Smith, Stephen M.
    Miller, Karla L.
    Salimi-Khorshidi, Gholamreza
    Webster, Matthew
    Beckmann, Christian F.
    Nichols, Thomas E.
    Ramsey, Joseph D.
    Woolrich, Mark W.
    [J]. NEUROIMAGE, 2011, 54 (02) : 875 - 891
  • [68] REST: A Toolkit for Resting-State Functional Magnetic Resonance Imaging Data Processing
    Song, Xiao-Wei
    Dong, Zhang-Ye
    Long, Xiang-Yu
    Li, Su-Fang
    Zuo, Xi-Nian
    Zhu, Chao-Zhe
    He, Yong
    Yan, Chao-Gan
    Zang, Yu-Feng
    [J]. PLOS ONE, 2011, 6 (09):
  • [69] The potential of functional MRI as a biomarker in early Alzheimer's disease
    Sperling, Reisa
    [J]. NEUROBIOLOGY OF AGING, 2011, 32 : S37 - S43
  • [70] Combination of resting state fMRI, DTI, and sMRI data to discriminate schizophrenia by N-way MCCA plus jICA
    Sui, Jing
    He, Hao
    Yu, Qingbao
    Chen, Jiayu
    Rogers, Jack
    Pearlson, Godfrey D.
    Mayer, Andrew
    Bustillo, Juan
    Canive, Jose
    Calhoun, Vince D.
    [J]. FRONTIERS IN HUMAN NEUROSCIENCE, 2013, 7