پیش‌بینی بیماری آلزایمر با استفاده از الگوریتم‌های انتخاب ویژگی محاسبات نرم و بر پایه rs-fMRI و sMRI

نوع مقاله : علمی-پژوهشی

نویسندگان

1 دانشکده مهندسی برق و کامپیوتر - دانشگاه صنعتی نوشیروانی بابل

2 دانشکده مهندسی برق و کامپیوتر - دانشگاه بجنورد

3 دانشکده آناتومی و نوروبیولوژی- دانشگاه مرکز علوم بهداشت تنسی– ممفیس - آمریکا

چکیده

بیماری آلزایمر (AD)، یک بیماری پیشرفته و غیرقابل‌برگشت است که اغلب در افراد مسن رخ می‌دهد و به‌تدریج مناطق مغز را که مسئول حافظه، تفکر، یادگیری و رفتار هستند، از بین می‌برد. در این مقاله پیش‌بینی AD  بر اساس تصاویر rs-fMRI و sMRI بررسی می‌شود. در این مطالعه سه الگوریتم انتخاب ویژگی بر اساس روش محاسبات نرم ارائه شده، که طبقه‌بندی MCI-C از MCI-NC با آموزش و آزمایش الگوریتم SVM انجام می‌شود. این اولین مطالعه‌ای است که از ادغام rs-fMRI و sMRI برای پیش‌بینی AD استفاده کرده است. نتایج حاصل از این مطالعه می‌تواند به مناطق شناخته شده مغز )عملکردی و ساختاری( که در بیماری آلزایمر دچار اختلال شده‌اند، منجر شود. علاوه بر این، روش NBS بر روی تقسیم‌بندی‌های عملکردی مغز، برای جداسازی MCI-C از MCI-NC و تشخیص زیر شبکه‌هایی که دارای قابلیت تشخیصی برای پیش‌بینی AD هستند، به کار گرفته شده است.

کلیدواژه‌ها


عنوان مقاله [English]

Predicting Alzheimer's Disease using Soft Computing Feature selection algorithms and Based on rs-fMRI and sMRI

نویسندگان [English]

  • S. H. Hojjati 1
  • A. Ebrahimzadeh 1
  • A. Khazaee 2
  • A. Babajani-Feremi 3
1 Department of Electrical Engineering, Babol University of Technology, Babol, Iran
2 Department of Electrical Engineering, University of Bojnord, Bojnord, Iran
3 Department of Pediatrics, Division of Clinical Neurosciences, University of Tennessee Health Science Center, Memphis, TN, USA
چکیده [English]

Alzheimer’s disease (AD), a progressive, irreversible neurodegenerative disorder, occurs most frequently in older adults and gradually destroys regions of the brain that are responsible for memory, thinking, learning, and behavior. In this paper, AD prediction is investigated based on rs-fMRI and sMRI analysis. Three feature selection algorithms based on soft computing method has been proposed to classify MCI-C from MCI-NC through training SVM. This is the first study used to integrate rs-fMRI and sMRI for AD prediction. The results refer to the significant brain areas (functional and structural) impaired in AD. Furthermore, NBS method on brain functional parcellations has been utilized for separating MCI-C from MCI-NC and detecting the discriminative ability networks for AD prediction. 

کلیدواژه‌ها [English]

  • Alzheimer’s disease
  • predicting
  • graph theory
  • statistical information
  • sMRI
  • network based analysis
[1] A. M. Howseman, R. W. Bowtel, Functional magnetic resonance imaging: imaging techniques and contrast mechanisms, Philosophical Transactions of the Royal Society B, Biological Sciences, vol. 354, no. 1179-1194, 1999.
[2] M. N. Moussa, P. J. Laurienti, S. Hayasaka, Consistency of network modules in resting-state FMRI connectome data, PloS one, no. 28-44, 2012.
[3] V. J. R. Wolz , J. Koikkalainen , E. Niskanen , D. P. Zhang, D. Rueckert , H. Soininen , J. Lötjönen, Multi-Method Analysis of MRI Imagesin Early Diagnostics of Alzheimer's Disease, Plos one, 2016.
[4] R Cuingneta, J. Tessieras, G. Auzias, S. Lehéricy, M. O. Habert, M. Chupin, H. Benalid, O. Colliot, Automatic classification of patients with Alzheimer's disease from structural MRI, A comparison of ten methods using the ADNI database, Neuroimage, vol. 56, no. 766-781, 2011.
[5] C. Misra, Y. Fan, C. Davatzikos, Baseline and longitudinal patterns of brain atrophy in MCI patients, and their use in prediction of short-term conversion to AD:results from ADNI, Neuroimage, vol.14, no. 22-44, 2009.
[6] E. Moradi, Machine learning framework for early MRI-based Alzheimer's conversion prediction in MCI subjects, Neuroimage,vol.104, no. 298-412, 2015.
[7] K. Supekar, D. Rubin, M. Musen, M. D. Greicius, Network Analysis of Intrinsic Functional Brain Connectivity in Alzheimer's Disease, Computational Biology, 2008.
[8] C. C. Armstrong, J.  D. Feusner, J. T. McCracken, S. Chang, J. G. Levitt, J. C. Piacentini, J. O’Neill, Graph-theoretical analysis of resting-state fMRI in pediatric obsessive–compulsive disorder, journal of affective disorders, vol.84, no. 175-193, 2016.
[9] طناز اکبرپور ، سبلان دانشور، « افزایش کیفیت ادغام تصاویر MRI و PET با استفاده از ترکیب موجک گابور و مدل شبکیه»، مجله مهندسی برق دانشگاه تبریز، جلد 54 ،شماره 5، 74-85،زمستان 94.
[10] S. F. Eskildsena, P. Coupé, D. García-Lorenzo, V. Fonov, J. C. Pruessner, D. L. Collins, Prediction of Alzheimer's disease in subjects with mild cognitive impairment from the ADNI cohort using patterns of cortical thinning, Neuroimage, vol. 65, no 511-521, 2013.
[11] R. Wolz, J.  Koikkalainen, E.  Niskanen, D. P. Zhang, D. Rueckert, H. Soininen, J. Lötjönen. Multi-Method Analysis of MRI Images in Early Diagnostics of Alzheimer's Disease, Plos one, vol. 10, 2013.
[12] E. Moradi, A. C. Gaser, H. Huttunen, J. Tohka, Machine learning framework for early MRI-based Alzheimer's conversion prediction in MCI subjects, Neuroimage, vol. 104, no. 398-412, 2015.
[13] D. Zhang, D. Shen, Predicting Future Clinical Changes of MCI Patients Using Longitudinal and Multimodal Biomarkers, Plos one, 2012.
[14] C. Davatzikos, P. Bhatt, L. M. Shaw, K. N. Batmanghelich, J. Q. Trojanowski, Prediction of MCI to AD conversion, via MRI, CSF biomarkers, and pattern classification, Neurobiological Aging, vol. 19, no. 27-32, 2010.
[15] F. de Vos, T. M. Schouten, A. Hafkemeijer, E. G. Dopper, J. C. Van Swieten, M. de Rooij, et al. Combining multiple anatomical MRI measures improves Alzheimer's disease classification, Human Brain Mapping, vol. 37, no. 1920-1929, 2016.
[16] B. Cheng , D. Zhang , D. Shen, Domain transfer learning for MCI conversion prediction, IEEE Transactions on Biomedical Engineering, vol. 62, no. 1805-1817, 2015.
[17] P. Martijn v. d. Heuvel, Exploring the brain network: A review on resting-state fMRI functional connectivity, European neuropsychopharmacology, vol. 20, no. 519-534, 2010.
[18] A. Khazaee, A. Ebrahimzadeh, A. Babajani-Feremi, Application of advanced machine learning methods on resting-state fMRI network for identification of mild cognitive impairment and Alzheimer’s disease, Brain Imaging and Behavior, vol. 10, no. 799-817, 2015.
[19] A. Khazaee, A. Ebrahimzadeh, A. Babajani-Feremi, Identifying patients with Alzheimer’s disease using resting-state fMRI and graph theory, Clinical Neurophysiology, vol. 126, no. 2126-2141, 2015.
[20] Z. Liu, Y. Zhang, L. Bai, Yan, R. Dai, C. Zhong, et al, Investigation of the effective connectivity of resting state networks in Alzheimer's disease: a functional MRI study combining independent components analysis and multivariate Granger causality analysis, NMR in Biomedicine, vol. 25, no. 1311-1320, 2012.
[21] M. D. G. Menon, K. Ben, L. R. Allan, Functional connectivity in the resting brain: A network analysis of the default mode hypothesis, vol. 100, no. 253-258, 2003.
[22] C. R. L. Minati, Resting-state brain networks: literature review and clinical applicati, Neurology Sciences, vol. 32, 773-785, 2011.
[23] C. R. Jack, M. A. Bernstein, N. C. Fox, P. Thompson , G. Alexander G, D. Harvey, et al, The Alzheimer'sdisease neuroimaging initiative (ADNI): MRI methods. Journal of Magnetic Resonance Imagin, vol. 27, no. 685-691, 2008.
[24] Y. Chao-Gan, Z. Yu-Feng, DPARSF: A MATLAB Toolbox for "Pipeline" Data Analysis of Resting-State fMRI, Frontntier System Neuroscience, vol. 13, 2010.
[25] K. J. Friston, C. D. Frith, R. S. Frackowiak, R. Turner, Characterizing dynamic brain responses with fMRI: a multivariate approach, Neuroimage, vol. 2, no. 166-172, 1995.
[26] H. Lu, Y. Zuo, H. Gu, J. A. Waltz, W. Zhan, C. A. Scholl, et al, Synchronized delta oscillations correlate with theresting-state functional MRI signal, Proceedings of the National Academy of Sciences, vol. 104, no. 18265-18269, 2007.
[27] A. Kelly, L. Q. Uddin, B. B. Biswal BB, F. X. Castellanos, M. P.  Milham, Competition between functional brain networks mediates behavioral variability, Neuroimage. vol. 527, no 37-39, 2008.
[28] B. Fischl, D. H. Salat, E. Busa, M. Albert, M. Dieterich, C. Haselgrove, et al. Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain, Neuron, vol. 341, no. 33-55, 2002.
[29] B. Fischl, D. H. Salat, A. J. van der Kouw,N. Makris, F.  Segonne, B. T. Quinn, et al, Sequence-independent segmentation of magnetic resonance images, Neuroimage, vol. 23, no. 69-84, 2004.
[30] F.  Segonne, A. M. Dale, E. Busa, M. Glessner, D. Salat, H. K. Hahn, et al, A hybrid approach to the skull stripping problem in MRI, Neuroimage, vol. 22, no. 1060-1075, 2004.
[31] B. Fischl, A. Liu, A. M. Dale, Automated manifold surgery: constructing geometrically accurate and topologically correct models of the human cerebral cortex. IEEE Transaction Medical Imaging, vol. 20, no. 70-80, 2001.
[32] R. C. Craddock, R. Circle, G. A. James, P. E. Holtzheimer, et al, A whole brain fMRI atlas generated via spatially constrained spectral clustering, Human Brain Mapping, vol. 33, no. 1914-1928, 2016.
[33] C. R. Minjie, P. Lopez-Garcia, S. C. Carter, J. H. Aizenstein, Optimum template selection for atlas-based segmentation, Neuroimage, vol. 34, no. 1612-1618, 2007.
[34] N. T. Mazoyer, D. Papathanassiou, F. Crivello, O. Etard, N. Delcroix, B. Mazoyer, M. Joliot, Automated Anatomical Labeling of Activations in SPM Using a Macroscopic Anatomical Parcellation of the MNI MRI Single-Subject Brain, Neuroimage, vol. 15, no. 273-289, 2002.
[35] N. U. Dosenbach, B. Nardos, A. L. Cohen, D. A. Fair, J. D. Power, J. A. Church, et al, Prediction of individual brain maturity using fMRI, Science. vol. 329, no. 1358-1361, 2010.
[36] M. Rubinov, S. A. Knock, C. J. Stam, S. Micheloyannis, A. W. Harris, L. M. Williams, et al, Smallworld properties of nonlinear brain activity in schizophrenia, Human brain mapping.  vol. 30, no. 403-416, 2009.
[37] C. Destrieux, B. Fischl, A. Dale, E. Halgren, Automatic parcellation of human cortical gyri and sulci using standard anatomical nomenclature, Neuroimage, vol. 53, no. 1-15, 2010.
[38] M. Rubinov, O. Sporns, Complex network measures of brain connectivity: uses and interpretations, Neuroimage, vol.52, no. 1059-1069, 2010.
[39] S. Sivanandam, S. Deepa, Introduction to genetic algorithms, Springer Science & Business Media, 2007.
[40] C. Yang, D. Simon, A new particle swarm optimization technique, Systems Engineering International Conference on IEEE, 2005.
[41] Y.  Fan, N. Batmanghelich, C. M. Clark, C. Davatzikos, Alzheimer's Disease Neuroimaging Spatial patterns of brain atrophy in MCI patients, identified via high-dimensional pattern classification, predict subsequent cognitive decline, Neuroimage, vol. 39, no. 1731-1743, 2008.
[42] C. Davatzikos, D. Shen, R. C. Gur, X. Wu, D. Liu, Y. Fan, et al, Whole-brain morphometric study of schizophrenia revealing a spatially complex set of focal abnormalities, Archives of general psychiatry, vol. 62, no. 1218-1227, 2005.
[43] علیرضا سردار، رمضان هاونگی، « بهبود عملکرد الگوریتم خوشه‌یابی خودکار تصاویر رنگی به کمک پیش‌پردازش با شبکه عصبی خودسامانده (SOM)»، مجله مهندسی برق دانشگاه تبریز، جلد 47 ،شماره 3 ،1073-1082، پاییز1396.
[44] J. Krause, J. Cordeiro, R. S. Parpinelli, H. S. Lopes, A survey of swarm algorithms applied to discrete optimization problems, Swarm Intelligence and Bio-Inspired Computation, vol. 4, no. 169-191, 2013.
[45] F. Bai F, W. Liao, D. R. Watson, Y. Shi, Y. Wang, C. Yue, et al, Abnormal whole-brain functional connection in amnestic mild cognitive impairment patients, Behavioural brain research, vol. 216, no. 666-672, 2011.
[46] Z. Wang, X. Jia, P. Liang, Z. Qi, Y. Yang, W. Zhou, et al, Changes in thalamus connectivity in mild cognitive impairment: Evidence from resting state fMRI, European journal of radiology, vol.81, no. 277-285, 2012.
[47] C. Wee, P. Yap, K. Denny, J. N. Browndyke, G. G Potter, K. A. Welsh-Bohmer, et al, Resting-state multi-spectrum functional connectivity networks for identification of MCI patients, PloS one, 2012.
[48] G. Chen, B. D. Ward, G. Chen, S. J. Li, Decreased effective connectivity from cortices to the right parahippocampal gyrus in Alzheimer's disease subjects, Brain Connect, vol.4, no 702-708, 2014.
[49] C. Xie, F. Bai, H. Yu, Y. Shi, Y. Yuan, G. Chen, et al, Abnormal insula functional network is associated with episodicmemory decline in amnestic mild cognitive impairment, Neuroimage, vol. 63, no. 320-327, 2012.
[50] A. Khazaee, A. Ebrahimzadeh, A. Babajani-Feremi, Alzheimer's Disease Neuroimaging Classification of patients with MCI and AD from healthy controls using directed graphmeasures of resting-state fMRI,  Behavioural brain research, vol. 322, no. 339-350, 2017.
[51] S. K. Madsen, A. J. Ho, X. Hua, P. S. Saharan, A. W. Toga, C. Jack, et al, 3D maps localize caudate nucleus atrophy in 400Alzheimer’s disease, mild cognitive impairment, and healthy elderly subjects,  Neurobiology of aging, vol. 31, no. 1312- 1325, 2010.
[52] J. Koivunen, N. Scheinin, J. Virta, S. Aalto, T. Vahlberg, K. Någren, et al, Amyloid PET imaging in patients with mild cognitive impairment A 2-year follow-up study, Neurology, vol. 76, no. 1085-1090, 2011.
[53] M. D. Ikonomovic, W. E. Klunk, E. E. Abrahamson, C. A. Mathis , J. C. Price, N. D. Tsopelas, et al, Post-mortem correlates of in vivo PiB-PET amyloid imaging in a typical case of Alzheimer's disease, Brain, vol. 131, no. 1630-1645, 2008.
[54] S. Bozeat, C. A. Gregory, M. Ralph, J. R. Hodges, Which neuropsychiatric and behavioural features distinguish frontal and temporal variants of frontotemporal dementia from Alzheimer's disease, Journal of Neurology, Neurosurgery & Psychiatry, vol. 69, no. 178-186, 2000.
[55] S. E. Arnold, B. T. Hyman, J. Flory, A. R. Damasio, G. W. Van Hoesen, The topographical and neuroanatomical distribution of neurofibrillary tangles and neuritic plaques in the cerebral cortex of patients with Alzheimer's disease, Cerebral Cortex, vol. 1, no. 103-116, 1991.
[56] A. Abu-Akel, S. Shamay-Tsoory, Neuroanatomical and neurochemical bases oftheory of mind, Neuropsychologia, vol. 49, no. 2971-2984, 2011.
[57] W. W. Seeley, Anterior insula degeneration in frontotemporal dementia, Brain Structure and Function, vol. 214, no. 465-475, 2010.
[58] W. W.  Seeley, D. A. Carlin, J. M. Allman, M. N. Macedo, Bush C, B. L. Miller, et al, Early frontotemporal dementia targets neurons unique to apes and humans, Annual Neurology, vol. 60, no 660-667, 2006.
[59] E. Salmon, P. Ruby, D. Perani, E. Kalbe, S. Laureys, S. Adam, et al, Two aspects of impaired consciousness in Alzheimer's disease, Progress in brain research, vol. 150, no. 287-298, 2005.