Abstract
Independent component analysis (ICA) on group-level voxel-based morphometry (VBM) produces the coefficient matrix and the component matrix. The former contains variability among multiple subjects for further statistical analysis, and the latter reveals spatial maps common for all subjects. ICA algorithms converge to local optimization points in practice and the mostly applied stability investigation approach examines the stability of the extracted components. We found that the practically stable components do not guarantee to produce the practically stable coefficients of ICA decomposition for the further statistical analysis. Consequently, we proposed a novel approach including two steps: (1), the stability index for the coefficient matrix and the stability index for the component matrix were examined, respectively; (2) the two indices were multiplied to analyze the stability of ICA decomposition. The proposed approach was used to study the sMRI data of Type II diabetes mellitus group and the healthy control group (HC). Group differences in VBM were found in the superior temporal gyrus. Besides, it was revealed that the VBMs of the region of the HC group were significantly correlated with Montreal Cognitive Assessment (MoCA) describing the level of cognitive disorder. In contrast to the widely applied approach to investigating the stability of the extracted components for ICA decomposition, we proposed to examine the stability of ICA decomposition by fusion the stability of both coefficient matrix and the component matrix. Therefore, the proposed approach can examine the stability of ICA decomposition sufficiently.
Similar content being viewed by others
References
Alagiakrishnan K, Zhao N, Mereu L, Senior PA, Senthilselvan A (2014) Montreal cognitive assessment is superior to standardized mini-mental status exam in detecting mild cognitive impairment in the middle-aged and elderly patients with type 2 diabetes mellitus (vol 2013, 186106, 2013). Biomed Res Int 2013:648472
Ashburner J, Friston KJ (2000) Voxel-based morphometry—the methods. Neuroimage 11:805–821
Barnathan M, Megalooikonomou V, Faloutsos C, Faro S, Mohamed FB (2011) TWave: high-order analysis of functional MRI. Neuroimage 58:537–548
Calhoun VD, Adali T, Giuliani NR, Pekar JJ, Kiehl KA, Pearlson GD (2006) Method for multimodal analysis of independent source differences in schizophrenia: Combining gray matter structural and auditory oddball functional data. Human Brain Mapp 27(1):47-62
Chen Z, Li L, Sun J, Ma L (2012) Mapping the brain in type II diabetes: voxel-based morphometry using DARTEL. Eur J Radiol 81:1870–1876
Cong F, Kalyakin I, Ristaniemi T (2011a) Can back-projection fully resolve polarity indeterminacy of independent component analysis in study of event-related potential? Biomed Signal Process Control 6:422–426
Cong F, Kalyakin I, Chang Z, Ristaniemi T (2011b) Analysis on subtracting projection of extracted independent components from EEG recordings. Biomed Eng-Biomed Te 56(4):223–234
Cong F, Puoliväli T, Alluri V, Sipola T, Burunat I, Toiviainen P, Nandi AK, Brattico E, Ristaniemi T (2014) Key issues in decomposing fMRI during naturalistic and continuous music experience with independent component analysis. J Neurosci Methods 223:74–84
Correa N, Adalı T, Calhoun VD (2007) Performance of blind source separation algorithms for fMRI analysis using a group ICA method. Magn Reson Imaging 25(5):684–694
Cong F, Lin Q-H, Kuang L-D, Gong X-F, Astikainen P, Ristaniemi T (2015) Tensor decomposition of EEG signals: a brief review. J Neurosci Methods 248:59–69
Déli E, Tozzi A, Peters JF (2017) Relationships between short and fast brain timescales. Cogn Neurodyn 11:539–552
Eklund A, Nichols TE, Knutsson H (2016) Cluster failure: why fMRI inferences for spatial extent have inflated false-positive rates. Proc Natl Acad Sci 113:201602413
Erus G, Battapady H, Zhang T, Lovato J, Miller ME, Williamson JD, Launer LJ, Bryan RN, Davatzikos C (2015) Spatial patterns of structural brain changes in type 2 diabetic patients and their longitudinal progression with intensive control of blood glucose. Diabetes Care 38:97–104
Gupta CN, Calhoun VD, Rachakonda S, Chen J, Patel V, Liu J, Segall J, Franke B, Zwiers MP, Arias-Vasquez A, Buitelaar J, Fisher SE, Fernandez G, van Erp TG, Potkin S, Ford J, Mathalon D, McEwen S, Lee HJ, Mueller BA, Greve DN, Andreassen O, Agartz I, Gollub RL, Sponheim SR, Ehrlich S, Wang L, Pearlson G, Glahn DC, Sprooten E, Mayer AR, Stephen J, Jung RE, Canive J, Bustillo J, Turner JA (2015) Patterns of Gray Matter Abnormalities in Schizophrenia Based on an International Mega-analysis. Schizophr Bull 41(5):1133–1142
Himberg J, Hyvärinen A, Esposito F (2004) Validating the independent components of neuroimaging time series via clustering and visualization. Neuroimage 22:1214–1222
Hyvarinen A (1999) Fast and robust fixed-point algorithm for independent component analysis. IEEE Trans Neural Netw Learn Syst 10:626–634
Hyvärinen A, Karhunenen J, Oja E (2001) Independent component analysis. Neural Comput 13:504
Kim DJ, Yu JH, Shin MS, Shin YW, Kim MS (2016) Hyperglycemia reduces efficiency of brain networks in subjects with type 2 diabetes. PLoS ONE 11:1–14
Kurth F, Luders E, Angeles L (2015) Voxel-based morphometry. Neuroimage 1:345–349
Li Y-O, Adalı T, Calhoun VD (2007) Estimating the number of independent components for functional magnetic resonance imaging data. Human Brain Mapp 28(11):1251–1266
Luo L, Xu L, Jung R, Pearlson G, Adali T, Calhoun VD (2012) Constrained Source-Based Morphometry Identifies Structural Networks Associated with Default Mode Network. Brain Connect 2(1):33–43
Ma S, Correa NM, Li X-L, Eichele T, Calhoun VD, Adali T (2011) Automatic identification of functional clusters in fMRI data using spatial dependence. IEEE Trans Biomed Eng 58:3406–3417
Maldjian JA, Laurienti PJ, Kraft RA, Burdette JH (2003) An automated method for neuroanatomic and cytoarchitectonic atlas-based interrogation of fMRI data sets. Neuroimage 19:1233–1239
Mccrimmon RJ, Phd R, Mccrimmon RJ, Ryan CM, Frier BM (2012) Diabetes 2 Diabetes and cognitive dysfunction. www.thelancet.com. Lancet 379:2291–2299
Moran C, Phan TG, Chen J, Blizzard L, Beare R, Venn A, Münch G, Wood AG, Forbes J, Greenaway TM, Pearson S, Srikanth V (2013) Brain atrophy in type 2 diabetes: regional distribution and influence on cognition. Diabetes Care 36:4036–4042
Segall JM, Allen EA, Jung RE, Erhardt EB, Arja SK, Kiehl K, Calhoun VD (2012) Correspondence between structure and function in the human brain at rest. Front Neuroinform 6:10. https://doi.org/10.3389/fninf.2012.00010
Sejnowski TJ, Bell AJ (1995) Information-maximization approach to blind separation and blind deconvolution. Neural Computation 7:1129–1159
Spauwen PJJ, Köhler S, Verhey FRJ, Stehouwer CDA, Van Boxtel MPJ (2013) Effects of type 2 diabetes on 12-year cognitive change: results from the maastricht aging study. Diabetes Care 36:1554–1561
Sui J, Adali T, Yu Q, Chen J, Calhoun VD (2012) A review of multivariate methods for multimodal fusion of brain imaging data. J Neurosci Methods 204(1):68–81
Tzourio-Mazoyer N, Landeau B, Papathanassiou D, Crivello F, Etard O, Delcroix N, Mazoyer B, Joliot M (2002) Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain. Neuroimage 15:273–289
Xu L, Groth KM, Pearlson G, Schretlen DJ, Vince D (2009) Source-Based morphometry: the use of independent component analysis to identify gray matter differences with application to Schizophrenia. Human Brain Mapp 30:711–724
Yan CG, Wang XD, Zuo XN, Zang YF (2016) DPABI: data processing and analysis for (resting-state) brain imaging. Neuroinformatics 14:339–351
Zhang Y, Zhang X, Zhang J, Liu C, Yuan Q, Yin X, Wei L, Cui J, Tao R, Wei P, Wang J (2014) Gray matter volume abnormalities in type 2 diabetes mellitus with and without mild cognitive impairment. Neurosci Lett 562:1–6
Acknowledgements
This work was supported by National Natural Science Foundation of China (Grant Nos. 81471742, 81371526) and the Fundamental Research Funds for the Central Universities [DUT16JJ(G)03] in Dalian University of Technology in China. Gratitude goes forward to the Affiliated Zhongshan Hospital of Dalian University for DICOM data collection and Xichu Zhu and Jianrong Li in Dalian University of Technology for language editing.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Qing Zhang and Guoqiang Hu have contributed equal to this work.
Rights and permissions
About this article
Cite this article
Zhang, Q., Hu, G., Tian, L. et al. Examining stability of independent component analysis based on coefficient and component matrices for voxel-based morphometry of structural magnetic resonance imaging. Cogn Neurodyn 12, 461–470 (2018). https://doi.org/10.1007/s11571-018-9484-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11571-018-9484-2