Login Register Cart 0
Generic placeholder image

Current Bioinformatics

Editor-in-Chief

ISSN (Print): 1574-8936
ISSN (Online): 2212-392X

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

Classifying Cognitive Normal and Early Mild Cognitive Impairment of Alzheimer’s Disease by Applying Restricted Boltzmann Machine to fMRI Data

Author(s): Shengbing Pei and Jihong Guan*

Volume 16, Issue 2, 2021

Published on: 18 June, 2020

Page: [252 - 260] Pages: 9

DOI: 10.2174/1574893615999200618152109

Price: $65

Abstract

Background: Neuroimaging is an important tool in early detection of Alzheimer’s disease (AD), which is a serious neurodegenerative brain disease among the elderly subjects. Independent component analysis (ICA) is arguably one of the most widely used algorithm for the analysis of brain imaging data, which can be used to extract intrinsic networks of brain from functional magnetic resonance imaging (fMRI).

Methods: Witnessed by recent studies, a more flexible model known as restricted Boltzmann machine (RBM) can also be used to extract spatial maps and time courses of intrinsic networks from resting state fMRI, moreover, RBM shows superior temporal features than ICA. Here, we seek to employ RBM to improve the performance of classifying individuals. Experiments are performed on healthy controls and subjects at the early stage of AD, i.e., cognitive normal (CN) and early mild cognitive impairment participants (EMCI), and two types of data, i.e., structural magnetic resonance imaging (sMRI) and fMRI data.

Results: (1) By separately employing ICA for sMRI and fMRI, the features extracted from fMRI improve classification accuracy by 7.5% for CN and EMCI; (2) instead of applying ICA to fMRI, using RBM further improves classification accuracy by 7.75% for CN and EMCI; (3) the lesions at the early stage of AD are more likely to occur in the regions around slices 4, 6, 10, 14, 19, 51 and 59 of the whole brain in the longitudinal direction.

Conclusion: By using fMRI instead of sMRI and RBM instead of ICA, we can classify CN and EMCI more efficiently.

Keywords: Alzheimer's disease, magnetic resonance imaging, independent component analysis, restricted boltzmann machine, classification, neuronal.

« Previous Next »
Graphical Abstract

[1]
Shi J, Zheng X, Li Y, Zhang Q, Ying S. Multimodal neuroimaging feature learning with multimodal stacked deep polynomial networks for diagnosis of Alzheimer’s disease. IEEE J Biomed Health Inform 2018; 22(1): 173-83.
[http://dx.doi.org/10.1109/JBHI.2017.2655720] [PMID: 28113353]
[2]
Filippi M, Agosta F. Structural and functional network connectivity breakdown in Alzheimer’s disease studied with magnetic resonance imaging techniques. J Alzheimers Dis 2011; 24(3): 455-74.
[http://dx.doi.org/10.3233/JAD-2011-101854] [PMID: 21297259]
[3]
Ray S, Hossain SM, Khatun L, et al. A comprehensive analysis on preservation patterns of gene co-expression networks during Alzheimer’s disease progression. BMC Bioinformatics 2017; 18(1): 579.
[http://dx.doi.org/10.1186/s12859-017-1946-8]
[4]
Alzheimer’s Association. 2012 Alzheimer’s disease facts and figures. Alzheimers Dement 2012; 8(2): 131-68.
[http://dx.doi.org/10.1016/j.jalz.2012.02.001] [PMID: 22404854]
[5]
Fang C, Li CF, Cabrerizo M, et al. A Gaussian discriminant analysis-based generative learning algorithm for the early diagnosis of mild cognitive impairment in Alzheimer’s disease. IEEE International Conference on Bioinformatics and Biomedicine. Kansas City, Missouri, USA. 2017; pp. 538-42.
[http://dx.doi.org/10.1109/BIBM.2017.8217705]
[6]
Li Q, Wu X, Xu L, Chen K, Yao L. Alzheimer’s disease neuroimaging initiative. classification of alzheimer’s disease, mild cognitive impairment, and cognitively unimpaired individuals using multi-feature kernel discriminant dictionary learning. Front Comput Neurosci 2018; 11: 117.
[http://dx.doi.org/10.3389/fncom.2017.00117] [PMID: 29375356]
[7]
Chiang HS, Pao SC. An EEG-based fuzzy probability model for early diagnosis of Alzheimer’s disease. J Medical Syst 2016; 40(5): 125:1-9..
[8]
Westman E, Muehlboeck JS, Simmons A. Combining MRI and CSF measures for classification of Alzheimer’s disease and prediction of mild cognitive impairment conversion. Neuroimage 2012; 62(1): 229-38.
[http://dx.doi.org/10.1016/j.neuroimage.2012.04.056] [PMID: 22580170]
[9]
Sherif FF, Zayed N, Fakhr MA. Discovering alzheimer genetic biomarkers using bayesian networks 2015.
[10]
Garali I, Adel M, Bourennane S, et al. Brain region ranking for 18FDG-PET computer-aided diagnosis of Alzheimer’s disease. Biomed Signal Process Control 2016; 27: 15-23.
[http://dx.doi.org/10.1016/j.bspc.2016.01.009]
[11]
Beheshti I, Demirel H, Farokhian F, Yang C, Matsuda H. Alzheimer’s Disease Neuroimaging Initiative. Structural MRI-based detection of Alzheimer’s disease using feature ranking and classification error. Comput Methods Programs Biomed 2016; 137: 177-93.
[http://dx.doi.org/10.1016/j.cmpb.2016.09.019] [PMID: 28110723]
[12]
Chaddad A, Desrosiers C, Toews M. Local discriminative characterization of MRI for Alzheimer’s disease. IEEE 13th International Symposium on Biomedical Imaging, Prague, Czech Republic. 2016, 1-5..
[http://dx.doi.org/10.1109/ISBI.2016.7493197]
[13]
Sanganahalli BG, Herman P, Behar KL, Blumenfeld H, Rothman DL, Hyder F. Functional MRI and neural responses in a rat model of Alzheimer’s disease. Neuroimage 2013; 79: 404-11.
[http://dx.doi.org/10.1016/j.neuroimage.2013.04.099] [PMID: 23648961]
[14]
Zhou LP, Wang YP, Li Y, et al. .Hierarchical anatomical brain networks for MCI prediction: revisiting volumetric measures. PLoS One 2011; 6(7):. , e21935:1.
[15]
Rombouts SARB, Barkhof F, Goekoop R, Stam CJ, Scheltens P. Altered resting state networks in mild cognitive impairment and mild Alzheimer’s disease: an fMRI study. Hum Brain Mapp 2005; 26(4): 231-9.
[http://dx.doi.org/10.1002/hbm.20160] [PMID: 15954139]
[16]
Fox MD, Snyder AZ, Vincent JL, Corbetta M, Van Essen DC, Raichle ME. The human brain is intrinsically organized into dynamic, anticorrelated functional networks. Proc Natl Acad Sci USA 2005; 102(27): 9673-8.
[http://dx.doi.org/10.1073/pnas.0504136102] [PMID: 15976020]
[17]
Buckner RL, Andrews-Hanna JR, Schacter DL. The brain’s default network: anatomy, function, and relevance to disease. Ann N Y Acad Sci 2008; 1124(1): 1-38.
[http://dx.doi.org/10.1196/annals.1440.011] [PMID: 18400922]
[18]
Rodriguez PA, Anderson M, Calhoun VD, Adali T. General nonunitary constrained ICA and its application to complex-valued fMRI data. IEEE Trans Biomed Eng 2015; 62(3): 922-9.
[http://dx.doi.org/10.1109/TBME.2014.2371791] [PMID: 25420255]
[19]
Du W, Li H, Li XL, et al. ICA of fMRI data: performance of three ICA algorithms and the importance of taking correlation information into account. IEEE International Symposium on Biomedical Imaging. Chicago, IL, USA. 2011; pp. 1573-6.
[http://dx.doi.org/ 10.1109/ISBI.2011.5872702]
[20]
Liu C. JaJa J, Pessoa L. LEICA: Laplacian eigenmaps for group ICA decomposition of fMRI data. Neuroimage 2018; 169: 363-73.
[http://dx.doi.org/10.1016/j.neuroimage.2017.12.018] [PMID: 29246846]
[21]
Schmidt SA, Akrofi K, Carpenter-Thompson JR, Husain FT. Default mode, dorsal attention and auditory resting state networks exhibit differential functional connectivity in tinnitus and hearing loss. PLoS One 2013; 8(10)e76488
[http://dx.doi.org/10.1371/journal.pone.0076488] [PMID: 24098513]
[22]
Hinton GE. Training products of experts by minimizing contrastive divergence. Neural Comput 2002; 14(8): 1771-800.
[http://dx.doi.org/10.1162/089976602760128018] [PMID: 12180402]
[23]
Schmah T, Hinton GE, Zemel RS, et al. Generative versus discrimi- native training of RBMs for classification of fMRI images. Proceedings of the 21st International Conference on Neural Information Processing Systems. Vancouver, British Columbia, Canada. 2008; pp. 1409-6.
[24]
Hinton GE, Salakhutdinov RR. Reducing the dimensionality of data with neural networks. Science 2006; 313(5786): 504-7.
[http://dx.doi.org/10.1126/science.1127647] [PMID: 16873662]
[25]
Hjelm RD, Calhoun VD, Salakhutdinov R, Allen EA, Adali T, Plis SM. Restricted Boltzmann machines for neuroimaging: an application in identifying intrinsic networks. Neuroimage 2014; 96: 245-60.
[http://dx.doi.org/10.1016/j.neuroimage.2014.03.048] [PMID: 24680869]
[26]
Plis SM, Hjelm DR, Salakhutdinov R, et al. Deep learning for neuroimaging: a validation study. Front Neurosci 2014; 8: 229-39.
[http://dx.doi.org/10.3389/fnins.2014.00229] [PMID: 25191215]
[27]
Ramzan F, Khan MUG, Rehmat A, et al. A Deep learning approach for automated diagnosis and multi-Class classification of Alzheimer’s disease stages using resting-state fMRI and residual neural networks. J Med Syst 2019; 44(2): 37.
[http://dx.doi.org/10.1007/s10916-019-1475-2] [PMID: 31853655]
[28]
Sarraf S, Tofighi G. Deep learning-based pipeline to recognize Alzheimer’s disease using fMRI data. Future Technologies Conference. San Francisco, CA, USA. 2016; pp. 816-20.
[http://dx.doi.org/10.1109/FTC.2016.7821697]
[29]
Bell AJ, Sejnowski TJ. An information-maximization approach to blind separation and blind deconvolution. Neural Comput 1995; 7(6): 1129-59.
[http://dx.doi.org/10.1162/neco.1995.7.6.1129] [PMID: 7584893]
[30]
Ruan Z, Wei P, Qian G, et al. Fully-complex Infomax for blind separation of delayed sources. IEICE T Fund Electr 2016; 99(5): 973-7.
[http://dx.doi.org/10.1587/transfun.E99.A.973]
[31]
Li YO, Adali T, Calhoun VD. Estimating the number of independent components for functional magnetic resonance imaging data. Hum Brain Mapp 2007; 28(11): 1251-66.
[http://dx.doi.org/10.1002/hbm.20359] [PMID: 17274023]
[32]
Balan RV. Estimator for number of sources using minimum description length criterion for blind sparse source mixtures. International Conference on Independent Component Analysis and Signal Separation. 2007; pp. 333-40.
[http://dx.doi.org/10.1007/978-3-540-74494-8_42]
[33]
Bengio Y, Courville A, Vincent P. Unsupervised feature learning and deep learning: a review and new perspectives . Comput Res Repository 2012. abs/1206.5538..
[34]
Nair V, Hinton GE. Rectified linear units improve restricted Boltzmann machines. Proceedings of the 27th International Conference on Machine Learning. Haifa, Israel. 2010; pp. 807-14.
[35]
Welling M, Rosen-Zvi M, Hinton GE. Exponential family harmoniums with an application to information retrieval. Proceedings of the 17st International Conference on Neural Information Processing Systems. Vancouver, British Columbia, Canada. 2004; pp. 1481-8.
[36]
Bengio Y, Lamblin P, Popovici D, et al. Greedy layer-wise training of deep networks. Proceedings of the 19st International Conference on Neural Information Processing Systems. Vancouver, British Columbia, Canada. 2006; pp. 153-60.
[37]
Hastie T, Tibshirani R, Friedman J. The Elements of statistical learning. Berlin: Springer 2009.
[http://dx.doi.org/10.1007/978-0-387-84858-7]
[38]
Jang H, Plis SM, Calhoun VD, Lee JH. Task-specific feature extraction and classification of fMRI volumes using a deep neural network initialized with a deep belief network: Evaluation using sensorimotor tasks. Neuroimage 2017; 145(Pt B): 314-28.
[http://dx.doi.org/10.1016/j.neuroimage.2016.04.003] [PMID: 27079534]

Rights & Permissions Print Cite
Article Metrics
19
1
© 2024 Bentham Science Publishers | Privacy Policy