نوع مقاله : مقاله کامل پژوهشی

نویسندگان

1 دانشجوی دکتری مهندسی پزشکی، دانشکده‌ی علوم و فناوری‌های پزشکی، دانشگاه آزاد اسلامی، واحد علوم و تحقیقات، تهران، ایران

2 دانشیار، دانشکده‌ی مهندسی برق، دانشگاه صنعتی شریف، تهران، ایران

3 استاد، گروه مهندسی پزشکی، دانشکده‌ی فنی و مهندسی، دانشگاه شاهد، تهران، ایران

10.22041/ijbme.2020.128322.1598

چکیده

تصویربرداری تشدید مغناطیسی عمل‌کردی روشی غیرتهاجمی برای بررسی عمل‌کرد مغز از طریق نوسانات فرکانس پایین سیگنال­های وابسته به سطح اکسیژن خون می­باشد. آنالیز عمل‌کردی شبکه‌های مغزی بر پایه‌ی سری­های زمانی تصویربرداری تشدید مغناطیسی عمل‌کردی معمولا با استفاده از محاسبه‌ی ضریب همبستگی پیرسون بین نواحی مختلف مغز انجام می­شود. از آن‌جا که همبستگی پیرسون ارتباطات خطی را آشکار ساخته و در مورد همبستگی­های غیرخطی محدودیت دارد، در این تحقیق با استفاده از روش کرنل ارتباطات عمل‌کردی غیرخطی در داده­های تصویربرداری تشدید مغناطیسی عمل‌کردی بیماران آلزایمر مورد ارزیابی قرار گرفته است. روش کرنل با افزایش بعد فضا و انجام محاسبات در فضای جدید که معادل رابطه‌ی غیرخطی در فضای اولیه است، امکان ارزیابی ارتباطات عمل‌کردی غیرخطی را فراهم می­سازد. برای ساخت گراف­های وزن­دار بدون جهت از توابع کرنل مختلف با پارامترهای گوناگون استفاده شده، سپس ویژگی­های سراسری گراف از جمله درجه، قدرت، طول مسیر مشخصه، ماژولاریتی، جهان کوچک و بهره­وری محاسبه شده و آنالیز آماری غیرپارامتری جایگشتی انجام می­شود. نتایج آنالیز آماری نشان می­دهد که همبستگی به دست آمده از روش کرنل در مقایسه با همبستگی پیرسون تمایز بیش‌تری بین گروه بیمار و کنترل ایجاد کرده که می­تواند به دلیل وجود ارتباطاتی غیرخطی باشد که روش پیرسون قادر به آشکارسازی آن­ها نیست. هم‌چنین در بین توابع کرنل مختلف بیش‌ترین تمایز آماری هنگام استفاده از کرنل چندجمله­ای درجه‌ی سوم حاصل شده است. به منظور حصول اطمینان، از طبقه­بند ماشین بردار پشتیبان با کرنل­های مختلف نیز استفاده شده که بیش‌ترین صحت طبقه‌بندی برابر با 79/0±68/98% به دست آمده است. آنالیز شبکه‌ی حالت پایه نیز با روش کرنل و پیرسون انجام شده که در آن روش کرنل تفاوت آماری معنی­دار بیش‌تری نشان داده است. شایان ذکر است که نواحی آنگولار راست و چپ که جزئی از شبکه‌ی حالت پایه هستند با هیچ کدام از دو روش تمایزی نشان نداده و می­توان نتیجه گرفت که بیماری آلزایمر بر ارتباط عمل‌کردی این نواحی تاثیر چندانی ندارد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Investigation of Non-Linear Functional Connectivity in Alzheimer’s Disease utilizing Resting State fMRI Data and Graph Theory

نویسندگان [English]

  • Hessam Ahmadi 1
  • Emad Fatemizadeh 2
  • Alimotie Nasrabadi 3

1 Ph.D. Student, Department of Biomedical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran

2 Associate Professor, School of Electrical Engineering, Sharif University of Technology, Tehran, Iran

3 Professor, Biomedical Engineering Department, Shahed University, Tehran, Iran

چکیده [English]

Functional Magnetic Resonance Imaging (fMRI) is a non-invasive neuroimaging technique for analyzing the brain functions through low-frequency fluctuations called the Blood-Oxygen-Level-Dependent (BOLD) signals. Measurement of the functional connectivity in brain networks is usually done by the fMRI time-series through Pearson Correlation Coefficients (PCC). As the PCC shows linear dependencies, in this study, non-linear relationships in the fMRI signals of the patients with Alzheimer's Disease (AD) were investigated using the kernel trick method. Kernel trick approach maps the input information into a higher dimension space and implements the linear calculations in a new space that is proportionate to the non-linear relationships in the primary space. After generating the weighted undirected brain graphs based on the Automated Anatomical Labeling (AAL) atlas, different kernel functions with different parameters were applied. Then the graph global measures including degree, strength, small-worldness, modularity, and efficiencies features were computed and the non-parametric permutation test was performed. According to the results, the kernel trick method showed more significant differences with AD and healthy subjects in comparison with the simple PCC and it could be because of the non-linear correlations that are not captured by the PCC. Among different kernel functions, the Polynomial function had the best performance. Applying this kernel, the classification was done by the Support Vector Machine (SVM) classifier. The achieved accuracy was equal to 98.68±0.79%. The Occipital and Temporal lobes and also the Default Mode Network (DMN) were analyzed and the kernel trick method showed more significant differences in all of them. It is worthwhile to mention that the right and left Angular areas of DMN showed no significant changes in none of the methods and it could be concluded that the AD does not affect this areas effectively.

کلیدواژه‌ها [English]

  • fMRI
  • Functional Connectivity
  • Alzheimer’s Disease
  • Graph Theory
  • Kernel trick
  1. Samieri, "Epidemiology and risk factors of Alzheimer’s disease: a focus on diet," in Biomarkers for Preclinical Alzheimer’s Disease: Springer, 2018, pp. 15-42.
  2. Alzheimer’s, "2015 Alzheimer's disease facts and figures," Alzheimer's & dementia: the journal of the Alzheimer's Association, vol. 11, no. 3, p. 332, 2015.
  3. s. Association, "2019 Alzheimer's disease facts and figures," Alzheimer's & Dementia, vol. 15, no. 3, pp. 321-387, 2019.
  4. Pauling and C. D. Coryell, "The Magnetic Properties and Structure of Hemoglobin, Oxyhemoglobin and Carbonmonoxyhemoglobin," Proceedings of the National Academy of Sciences of the United States of America, vol. 22, no. 4, pp. 210-216, 1936. [Online]. Available: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1076743/.
  5. D. Fox and M. E. Raichle, "Spontaneous fluctuations in brain activity observed with functional magnetic resonance imaging," Nature reviews neuroscience, vol. 8, no. 9, pp. 700-711, 2007.
  6. Bullmore and O. Sporns, "Complex brain networks: graph theoretical analysis of structural and functional systems," Nature reviews neuroscience, vol. 10, no. 3, pp. 186-198, 2009.
  7. Lind et al., "Parietal cortex activation predicts memory decline in apolipoprotein E-epsilon4 carriers," (in eng), Neuroreport, vol. 17, no. 16, pp. 1683-6, Nov 06 2006, doi: 10.1097/01.wnr.0000239954.60695.c6.
  8. D. Greicius, B. Krasnow, A. L. Reiss, and V. Menon, "Functional connectivity in the resting brain: a network analysis of the default mode hypothesis," (in eng), Proc Natl Acad Sci U S A, vol. 100, no. 1, pp. 253-8, Jan 07 2003, doi: 10.1073/pnas.0135058100.
  9. Besga et al., "Structural and functional patterns in healthy aging, mild cognitive impairment, and Alzheimer disease," Alzheimer Disease & Associated Disorders, vol. 24, no. 1, pp. 1-10, 2010.
  10. Zhan et al., "Longitudinal study of impaired intra-and inter-network brain connectivity in subjects at high risk for Alzheimer’s disease," Journal of Alzheimer's Disease, vol. 52, no. 3, pp. 913-927, 2016.
  11. -Y. Zhang et al., "Detection of PCC functional connectivity characteristics in resting-state fMRI in mild Alzheimer’s disease," Behavioural brain research, vol. 197, no. 1, pp. 103-108, 2009.
  12. de Vos et al., "A comprehensive analysis of resting state fMRI measures to classify individual patients with Alzheimer's disease," Neuroimage, vol. 167, pp. 62-72, 2018.
  13. Dai et al., "Disrupted structural and functional brain networks in Alzheimer's disease," Neurobiology of aging, vol. 75, pp. 71-82, 2019.
  14. H. Hojjati, A. Ebrahimzadeh, and A. Babajani-Feremi, "Identification of the early stage of Alzheimer’s disease using structural MRI and resting-state fMRI," Frontiers in neurology, vol. 10, p. 904, 2019.
  15. Fatemizadeh and A. M. Nasrabadi, "Multiclass classification of patients during different stages of Alzheimer’s disease using fMRI time-series," Biomedical Physics & Engineering Express, 2020.
  16. H. Hojjati, A. Ebrahimzadeh, A. Khazaee, A. Babajani-Feremi, and A. s. D. N. Initiative, "Predicting conversion from MCI to AD by integrating rs-fMRI and structural MRI," Computers in biology and medicine, vol. 102, pp. 30-39, 2018.
  17. Li, X. Lin, and X. Chen, "Detecting Alzheimer's disease Based on 4D fMRI: An exploration under deep learning framework," Neurocomputing, vol. 388, pp. 280-287, 2020.
  18. Khazaee, A. Ebrahimzadeh, and A. Babajani-Feremi, "Application of pattern recognition and graph theoretical approaches to analysis of brain network in Alzheimer's disease," Journal of Medical Imaging and Health Informatics, vol. 5, no. 6, pp. 1145-1155, 2015.
  19. Khazaee, A. Ebrahimzadeh, and 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. 3, pp. 799-817, 2016.
  20. Khazaee, A. Ebrahimzadeh, A. Babajani-Feremi, and A. s. D. N. Initiative, "Classification of patients with MCI and AD from healthy controls using directed graph measures of resting-state fMRI," Behavioural brain research, vol. 322, pp. 339-350, 2017.
  21. Cao and K. Worsley, "The geometry of correlation fields with an application to functional connectivity of the brain," The Annals of Applied Probability, vol. 9, no. 4, pp. 1021-1057, 1999.
  22. Anzellotti, E. Fedorenko, A. J. Kell, A. Caramazza, and R. Saxe, "Measuring and modeling nonlinear interactions between brain regions with fMRI," bioRxiv, p. 074856, 2017.
  23. Mesejo, S. Saillet, O. David, C. G. Bénar, J. M. Warnking, and F. Forbes, "A differential evolution-based approach for fitting a nonlinear biophysical model to fMRI BOLD data," IEEE Journal of Selected Topics in Signal Processing, vol. 10, no. 2, pp. 416-427, 2015.
  24. Benesty, J. Chen, Y. Huang, and I. Cohen, "Pearson correlation coefficient," in Noise reduction in speech processing: Springer, 2009, pp. 1-4.
  25. A. Lindquist, J. M. Loh, L. Y. Atlas, and T. D. Wager, "Modeling the hemodynamic response function in fMRI: efficiency, bias and mis-modeling," Neuroimage, vol. 45, no. 1, pp. S187-S198, 2009.
  26. McAllester and K. Stratos, "Formal limitations on the measurement of mutual information," in International Conference on Artificial Intelligence and Statistics, 2020, pp. 875-884.
  27. Rudas et al., "Dynamic functional network connectivity using distance correlation," in 10th International Symposium on Medical Information Processing and Analysis, 2015, vol. 9287: International Society for Optics and Photonics, p. 92870P.
  28. Roth and V. Steinhage, "Nonlinear discriminant analysis using kernel functions," in Advances in neural information processing systems, 2000, pp. 568-574.
  29. Diestel, "Graph Theory, vol. 173 of," Graduate Texts in Mathematics, 2005.
  30. Rubinov and O. Sporns, "Complex network measures of brain connectivity: uses and interpretations," Neuroimage, vol. 52, no. 3, pp. 1059-1069, 2010.
  31. Scholkopf and A. J. Smola, Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT press, 2001.
  32. Towsley, J. Pakianathan, and D. H. Douglass, "Correlation angles and inner products: Application to a problem from physics," ISRN Applied Mathematics, vol. 2011, 2011.
  33. -X. Zhou and K. Jetter, "Approximation with polynomial kernels and SVM classifiers," Advances in Computational Mathematics, vol. 25, no. 1-3, pp. 323-344, 2006.
  34. Y. Kung, Kernel methods and machine learning. Cambridge University Press, 2014.
  35. Garreau, W. Jitkrittum, and M. Kanagawa, "Large sample analysis of the median heuristic," arXiv preprint arXiv:1707.07269, 2017.
  36. A. Micchelli and M. Pontil, "Learning the kernel function via regularization," Journal of machine learning research, vol. 6, no. Jul, pp. 1099-1125, 2005.
  37. J. Székely and M. L. Rizzo, "A new test for multivariate normality," Journal of Multivariate Analysis, vol. 93, no. 1, pp. 58-80, 2005.
  38. G. Mueller et al., "The Alzheimer's disease neuroimaging initiative," Neuroimaging Clinics, vol. 15, no. 4, pp. 869-877, 2005.
  39. R. Jack Jr et al., "Magnetic resonance imaging in alzheimer's disease neuroimaging initiative 2," Alzheimer's & Dementia, vol. 11, no. 7, pp. 740-756, 2015.
  40. Shmueli et al., "Low-frequency fluctuations in the cardiac rate as a source of variance in the resting-state fMRI BOLD signal," Neuroimage, vol. 38, no. 2, pp. 306-320, 2007.
    1. Tzourio-Mazoyer et al., "Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain," Neuroimage, vol. 15, no. 1, pp. 273-289, 2002.
    • Liu, M. J. Zuo, X. Zhao, and H. Xu, "An Analytical Approach to Fast Parameter Selection of Gaussian RBF Kernel for Support Vector Machine," J. Inf. Sci. Eng., vol. 31, no. 2, pp. 691-710, 2015.
    • C. Reijneveld, S. C. Ponten, H. W. Berendse, and C. J. Stam, "The application of graph theoretical analysis to complex networks in the brain," Clinical neurophysiology, vol. 118, no. 11, pp. 2317-2331, 2007.
    • D. Humphries and K. Gurney, "Network ‘small-world-ness’: a quantitative method for determining canonical network equivalence," PloS one, vol. 3, no. 4, 2008.
    1. Zhu et al., "Changes of intranetwork and internetwork functional connectivity in Alzheimer’s disease and mild cognitive impairment," Journal of neural engineering, vol. 13, no. 4, p. 046008, 2016.