استخراج الگوهای فضایی طیفی از سیگنال‌های الکتروانسفالوگرام برای تشخیص اختلال شناختی خفیف

نویسندگان

دانشکده مهندسی برق - دانشگاه علم و صنعت ایران

چکیده

اختلال شناختی خفیف (MCI) مرحله ابتدایی بیماری آلزایمر(AD) قلمداد می‌شود. تشخیص زودهنگام این عارضه، احتمال درمان و جلوگیری از تبدیل آن به زوال عقلی را افزایش می‌دهد. هدف این مطالعه، تفکیک و طبقه‌بندی دو گروه افراد سالم و بیماران MCI به‌وسیله روش پردازشی پیشرفته با به‌کارگیری فیلترهای فضایی-طیفی در استخراج ویژگی از سیگنال‌های الکتروانسفالوگرام EEG است. روش پیشنهادی بانک فیلتر الگوی فضایی مشترک (FBCSP) است که اخیراً در مطالعات واسط‌های مغز و کامپیوتر برای جداسازی تصورات حرکتی با موفقیت استفاده شده است ولی تاکنون درکاربرد تشخیص MCI بررسی و به‌کارگیری نشده است. تحلیل و بررسی روی داده‌های 9 فرد بیمار MCI و 12 فرد سالم صورت گرفته و با روش‌های رایج استخراج ویژگی از توان باندهای فرکانسی و الگوی فضایی مشترک (CSP) کلاسیک مقایسه شده است. به‌کارگیری روش FBCSP دقت تفکیک 100 درصد را در ارزیابی بایک نمونه خارج شده درپی داشت. یافته‌های این مطالعه، برتری قابل توجه روش FBCSP نسبت به روش توان باندهای فرکانسی و CSP کلاسیک را در دقت تشخیص MCI نشان می‌دهد. نتایج این مطالعه بر نقش استفاده از ترکیب‌های فضایی یادگیری شده در هریک از زیر باندهای فرکانسی برای استخراج ویژگی‌های مؤثر در تفکیک افراد سالم از بیماران MCI تأکید دارد.

کلیدواژه‌ها


عنوان مقاله [English]

Extracting Spatial Spectral Patterns from EEG Signals for Diagnosis of Mild Cognitive Impairment

نویسندگان [English]

  • M. A. Ganjali
  • V. Shalchyan
Faculty of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran
چکیده [English]

Mild cognitive impairment )MCI( is an early stage of Alzheimer's disease)AD). Early diagnosis of this disease increases the likelihood of the treatment and prevents its conversion to dementia. The purpose of this study is the discrimination and the classification of two groups of healthy and MCI subjects by an advanced method of extracting spatial spectral features from electroencephalographic (EEG) signals. Filter bank common spatial pattern (FBCSP) has been recently used for classifying motor imagery EEG data in brain-computer interface researches. Here, we propose using FBCSP for classifying EEG data from healthy and MCI subjects. The proposed method was tested and compared to the popular method of frequency band-power and to the classic common spatial pattern (CSP) using a dataset of 9 MCI patients and 12 healthy subjects. A leave-one-out cross validation, using FBCSP resulted in a classification accuracy of 100% and outperformed both the frequency band-power and classic CSP methods. These results reveal the important role of using the learned spatial combinations of EEG signals in different frequency bands as effective features for discrimination of MCI and normal subjects.

کلیدواژه‌ها [English]

  • Mild cognitive impairment (MCI)
  • Alzheimer's disease (AD)
  • Electroencephalogram (EEG)
  • Filter bank common spatial pattern (FBCSP)
[1] J. B. Orange and E. B. Ryan "Alzheimer's disease and other dementias." Clinics in geriatric medicine, vol. 16, pp. 153-173, 2000.
[2] E. Gallego-Jutglàa, J. Solé-Casalsa, F. B. Vialatteb, J. Dauwelsc, and A. Cichocki, "A theta-band EEG based index for early diagnosis of Alzheimer's disease Running title: EEG based index to improve AD diagnosis." Journal of Alzheimer's Disease, vol. 43,  pp. 1175-1184, 2015  
[3] B. Czigler, D. Csikós, Z. Hidasi, Z. A. Gaál, É. Csibri, É. Kiss, P. Salacz, and M. Molnár, "Quantitative EEG in early Alzheimer's disease patients—power spectrum and complexity features." International Journal of Psychophysiology, vol. 68, pp. 75-80, 2008.
[4] Y. M. Park, H. J. Che, C. H. Im, H. T. Jung, S. M. Bae, and S.H. Lee, "Decreased EEG synchronization and its correlation with symptom severity in Alzheimer's disease." Neuroscience research, vol. 62, pp. 112-117, 2008.
[5] J. Dauwels, F. Vialatte, T. Musha, and A. Cichocki, "A comparative study of synchrony measures for the early diagnosis of Alzheimer's disease based on EEG." NeuroImage, vol. 49, pp. 668-693, 2010.
[6] M. R. Daliri, "Kernel earth mover's distance for eeg classification." Clinical EEG and neuroscience, vol. 44, pp. 182-187, 2013.
[7] J. C. McBride, X. Zhao, N. B. Munro, C. D. Smith, G. A. Jicha, L. Hively, L. S. Broster, F. A. Schmitt, R. J. Kryscio, and Y. Jiang, "Spectral and complexity analysis of scalp EEG characteristics for mild cognitive impairment and early Alzheimer's disease." Computer methods and programs in biomedicine. vol. 114, pp. 153-163, 2014.
[8] M. R. Daliri, "Automated diagnosis of Alzheimer disease using the scale-invariant feature transforms in magnetic resonance images." Journal of medical systems, vol. 36, vol. 995-1000, 2012.
[9] مرتضی به نام و حسین پورقاسم، «شناسایی صرع بر اساس بهینه‌سازی ویژگی‌های ادغامی‌تبدیل‌هارتلی با مدل ترکیبی MLP و GA همراه با استراتژی یادگیری ممتیک»، مجله مهندسی برق تبریز، جلد 45, شماره 4، صفحه 51-67، 1394.‌
[10] مرتضی جهان‌تیغ و مصطفی چرمی، «افزایش صحت طبقه‌بندی سیگنال‌های EEG تصور حرکتی با ترکیب منطقی طبقه‌بندها و با به‌کارگیری الگوریتم ژنتیک و درختان تصمیم کوچک»، مجله مهندسی برق تبریز، جلد 47، شماره 3، صفحه 931-938، 1396.‌
[11] C. S. Herrmann and T. Demiralp. "Human EEG gamma oscillations in neuropsychiatric disorders." Clinical neurophysiology, vol. 116, pp. 2719-2733, 2005.
[12] C. F. Latchoumane, F. Vialatte, A. Cichocki, and J. Jeong, "Multiway analysis of Alzheimer’s disease: classification based on space-frequency characteristics of EEG time series." In Proceedings of the World Congress on Engineering, vol. 2, pp. 2-4. 2008.
[13] W. Woon, A. Cichocki, F. Vialatte, and T. Musha. "Techniques for early detection of Alzheimer's disease using spontaneous EEG recordings." Physiological Measurement. vol. 28, pp 335-347, 2007.
[14] J. Jaeseung, "EEG dynamics in patients with Alzheimer's disease." Clinical neurophysiology. vol. 115, pp. 1490-1505, 2004.
[15] T. König, L. Prichep, T. Dierks, D. Hubl, L. O. Wahlund, E. R. John, and V. Jelic. "Decreased EEG synchronization in Alzheimer’s disease and mild cognitive impairment." Neurobiology of aging, vol.26, pp. 165-171, 2005.
[16] J. Dauwels, F. Vialatte, C. Latchoumane, J. Jeong, and A. Cichocki. "Loss of EEG synchrony in early-stage AD patients: a study with multiple synchrony measures and multiple EEG data sets." In Proceedings of the 31st annual international conference of the IEEE engineering in medicine and biology society. vol. 2009, pp.2224-2227, 2009.
[17] J. A. Deursen, E. F. Vuurman, F. R. Verhey, V. H. van Kranen-Mastenbroek, and W. J. Riedel, "Increased EEG gamma band activity in Alzheimer’s disease and mild cognitive impairment." Journal of neural transmission, vol. 115, pp. 1301-1311, 2008.
[18] D. V. Moretti, C. Fracassi, M. Pievani, C. Geroldi, G. Binetti, O. Zanetti, K. Sosta, P. M. Rossini, and G. B. Frisoni. "Increase of theta/gamma ratio is associated with memory impairment." Clinical Neurophysiology, vol. 120, pp. 295-303, 2009.
[19] P. Zhao, P. Van-Eetvelt, C. Goh, N. Hudson, S. Wimalaratna, and E. Ifeachor. "Characterization of EEGs in Alzheimer's disease using information theoretic methods." In Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE, vol. 2007 pp. 5127-5131, 2007.
[20] D. Labate, F. L. Foresta, G. Morabito, I. Palamara, and F. C.  Morabito, "Entropic measures of EEG complexity in Alzheimer's disease through a multivariate multiscale approach." IEEE Sensors Journal, vol. 13, pp. 3284-3292, 2013.
[21] D. Abásolo, J. Escudero, R. Hornero, C. Gómez, and P. Espino, "Approximate entropy and auto mutual information analysis of the electroencephalogram in Alzheimer’s disease patients." Medical & biological engineering & computing, vol. 46, pp. 1019-1028, 2008.
[22] F. C. Morabito, D. Labate, A. Bramanti, F. L. Foresta, G.  Morabito, I. Palamara, and H. H. Szu. "Enhanced compressibility of eeg signal in alzheimer's disease patients." IEEE Sensors Journal, vol. 13, pp. 3255-3262, 2013.
[23] J. Jeong, J. C. Gore, and B. S. Peterson. "Mutual information analysis of the EEG in patients with Alzheimer's disease." Clinical neurophysiology, vol. 112, pp. 827-835, 2001.
[24] R. Hornero, D. Abásolo, J. Escudero, and C. Gómez. "Nonlinear analysis of electroencephalogram and magnetoencephalogram recordings in patients with Alzheimer's disease." Philosophical Transactions of the Royal Society of London A: Mathematical, Physical and Engineering Sciences, vol. 367, pp.  317-336, 2009.
[25] M. J. Hogan, G. R. Swanwick, J. Kaiser, M. Rowan, and B. Lawlor. "Memory-related EEG power and coherence reductions in mild Alzheimer's disease." International Journal of Psychophysiology, vol. 49, pp. 147-163, 2003.
[26] J. Dauwels, F. Vialatte, and A. Cichocki, "A comparative study of synchrony measures for the early detection of Alzheimer’s disease based on EEG." In International Conference on Neural Information Processing, vol. 2007, pp. 112-125. 2007.
[27] T. Locatelli, M. Cursi, D. Liberati, M. Franceschi, and G. Comi, "EEG coherence in Alzheimer's disease"Electroencephalography and clinical neurophysiology, vol. 106, pp. 229-237, 1998.
[28] Y. Wada, Y. Nanbu, Y. Koshino, N. Yamaguchi, and T. Hashimoto, "Reduced interhemispheric EEG coherence in Alzheimer disease: analysis during rest and photic stimulation." Alzheimer Disease & Associated Disorders, vol. 12, pp. 175-181, 1998.
[29] D. V. Moretti, Davide V., C. Babiloni, G. Binetti, E. Cassetta, G. D. Forno, F. Ferreric, R. Ferri, B. Lanuzza, C. Miniussi, F. Nobili, G. Rodriguez, S. Salinari and P. M. Rossini, "Individual analysis of EEG frequency and band power in mild Alzheimer's disease." Clinical Neurophysiology, vol. 115, pp.  299-308, 2004.
[30] C. Babiloni, F. Vecchio, R. Lizio, R. Ferri, G. Rodriguez, N.  Marzano, G. B. Frisoni, and P. M. Rossini. "Resting state cortical rhythms in mild cognitive impairment and Alzheimer's disease: electroencephalographic evidence." Journal of Alzheimer's Disease, vol. 26 pp. 201-214, 2011.
[31] R. P. Brenner, R. F. Ulrich, D. G. Spiker, R. J. Sclabassi, C. F. Reynolds, R. S. Marin, and F. Boller. "Computerized EEG spectral analysis in elderly normal, demented and depressed subjects." Electroencephalography and clinical neurophysiology. vol. 64, pp. 483-492, 1986.
[32] K. J. Blinowska, F. Rakowski, M. Kaminski, F. De Vico Fallani, C. Del Percio, R. Lizio, and C. Babiloni. "Functional and effective brain connectivity for discrimination between Alzheimer’s patients and healthy individuals: A study on resting state EEG rhythms." Clinical Neurophysiology, vol. 128, pp. 667-680, 2017.
[33] J. McBride, X. Zhao, N. Munro, C. Smith, G. Jicha, and Y. Jiang, "Resting EEG discrimination of early stage Alzheimer’s disease from normal aging using inter-channel coherence network graphs." Annals of biomedical engineering, vol. 41, pp. 1233-1242, 2013.
[34] F. B. Vialatte, J. Solé-Casals, M. Maurice, C. Latchoumane, N. Hudson, S. Wimalaratna, J. Jeong, and A. Cichocki. "Improving the quality of EEG data in patients with Alzheimer’s disease using ICA." In International Conference on Neural Information Processing, vol. 2008, pp. 979-986, 2008.
[35] C. F. Latchoumane, F. B. Vialatte, J. Solé-Casals, M. Maurice, S. R. Wimalaratna, N. Hudson, J. Jeong, and A. Cichocki. "Multiway array decomposition analysis of EEGs in Alzheimer's disease." Journal of neuroscience methods, vol. 207, pp 41-50, 2012.
[36] H. Ramoser, J. Muller-Gerking, and G. Pfurtscheller. "Optimal spatial filtering of single trial EEG during imagined hand movement." IEEE transactions on rehabilitation engineering, vol. 8, pp. 441-446, 2000.
[37] B. Blankertz, R. Tomioka, S. Lemm, M. Kawanabe, and K. R. Muller. "Optimizing spatial filters for robust EEG single-trial analysis." IEEE Signal processing magazine, vol. 25, pp. 41-56, 2008.
[38] K. K. Ang, Z. Y. Chin, C. Wang, C. Guan, and H. Zhang. "Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b." Frontiers in neuroscience, vol. 6, 2012.
[39] M. Kashefpoor, H. Rabbani, and M. Barekatain. "Automatic diagnosis of mild cognitive impairment using electroencephalogram spectral features." Journal of medical signals and sensors, vol. 6, pp. 25-32, 2016.
[40] H. Liu, J. Sun, L. Liu, and H. Zhang. "Feature selection with dynamic mutual information." Pattern Recognition, vol. 42, pp. 1330-1339, 2009.
[41] S. M. Stigler, "Francis Galton's account of the invention of correlation." Statistical Science. vol. 4, pp. 73-79, 1989.
[42] M. A. Hearst, S. T. Dumais, E. Osuna, J. Platt, and B. Scholkopf. "Support vector machines." IEEE Intelligent Systems and their applications, vol. 13, pp. 18-28, 1998.
[43] P. Ghorbanian, D. M. Devilbiss, A. J. Simon, A. Bernstein, T. Hess, and H. Ashrafiuon. "Discrete wavelet transform EEG features of Alzheimer's disease in activated states." In Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE, pp. 2937-2940, 2012.