تشخیص بیماری‌های عصبی-حرکتی با تحلیل بافت تصاویر طیف سیگنال‌های ماهیچه‌ای

نویسندگان

گروه مهندسی کامپیوتر - دانشکده فنی و مهندسی - دانشگاه رازی

چکیده

مشکلات عصبی-حرکتی دربرگیرنده طیف وسیعی از بیماری‌ها هستند که موجب اختلال در عملکرد ماهیچه‌های ارادی و یا اعصاب می‌شوند. یکی از روش‌های تشخیص خودکار این بیماری‌ها، بررسی سیگنال‌های ماهیچه‌ای توسط برنامه‌های کامپیوتری است. برنامه‌هایی که به این منظور توسعه می‌یابند شامل چندین مرحله پردازش هستند که استخراج ویژگی و دسته‌بندی از مراحل اصلی آن‌ها است. در این مقاله روشی مبتنی بر تحلیل بافت طیف سیگنال برای استخراج ویژگی ارائه شده است که برخلاف روش‌های زمانی، فرکانسی و زمان-فرکانسی مبتنی بر موجک، با استخراج توأمان روابط زمان و فرکانس از سیگنال‌های ماهیچه‌ای موجب تشکیل یک بردار ویژگی با قابلیت تمایز بالا و ابعاد پایین می‌گردد. همچنین، جهت دسته‌بندی ویژگی‌ها، ماشین بردار پشتیبان، k-نزدیک‌ترین همسایه، تحلیل تمایزی، رگرسیون منطقی و ترکیب آن‌ها در دو حالت کلی و با تفکیک باندهای فرکانسی مورد بررسی قرار گرفته‌اند. به‌منظور برآورد روش پیشنهادی در این تحقیق از پایگاه داده سیگنال‌های ماهیچه‌ای اندام تحتانی استفاده شده است. با توجه به نتایج به‌دست‌آمده از آزمایش‌ها ، دقت دسته‌بندی %89.40 با استفاده از ماشین بردار پشتیبان با هسته RBF در حالت تفکیک باندهای فرکانسی حاصل شده است که به میزان %3.40 نسبت به بهترین روش قبلی دقیق‌تر است.

کلیدواژه‌ها

عنوان مقاله [English]

Diagnosis of Neuromuscular Disorders Using Spectrogram Textural Features of EMG Signals

نویسندگان [English]

  • S. M. Tabatabaei
  • A. Chalechale
Department of Computer Engineering, Faculty of Engineering, Razi University, Kermanshah, Iran
چکیده [English]

Neuromuscular disease includes many disorders that damage functioning of muscles or nerves. For automatic diagnosis of these abnormalities, surface EMG signals are processed using computer programs. Feature extraction and classification are two fundamental steps in processing EMG signals by the programs. This paper presents a novel approach based on textural analysis of time-frequency image of EMG signals. In contrast to previous time alone, frequency alone, and time-frequency wavelet-based approaches, exploiting relational time and frequency properties of spectral image of EMG signal, high discrimination is achieved in the form of a compact feature vector by the proposed method. To assign each feature to it ҆s respective class, various classification methods including: KNN, SVM, LDA, logic regression, and their combination are examined in two segmented and holistic modes in the present study. At last, EMG dataset in lower limb is utilized to evaluate the proposed method. Using SVM with RBF kernel to classify segmented features, the classification accuracy of 89.4% obtained by the proposed method. The obtained classification accuracy has been improved by 3.40% over the best previous result.

کلیدواژه‌ها [English]

  • Time-frequency distribution
  • time-frequency image
  • spectrogram
  • texture analysis
  • local binary pattern
  • grey level co-occurrence matrix

مراجع

[1] M. A. Oskoei and H. Hu, “Myoelectric control systems—A survey,” Biomedical Signal Processing and Control, vol. 2, no. 4, pp. 275-294, 2007.‌
[2] G. kamen and G. E. Caldwell, “Physiology and interpretation of the electromyogram,” Journal of Clinical Neurophysiology, vol. 13, no. 5, pp. 366-384, 1996.
[3] E. Criswell, Cram's Introduction to Surface Electromyography, Jones & Bartlett Publishers, pp. 35-39, 2010.‌
[4] R. Merletti and D. Farina,Surface Electromyography: Physiology,Engineering and Applications, John Wiley & Sons, pp. 300-302,‌ 2016.
[5] M. J. Aminoff, Electromyography in Clinical Practice: Electrodiagnostic Aspects of Neuromuscular Disease, Churchill Livingstone, 1987.
[6] H. Jungbluth, T. Basil, H. Darras, Jr. Royden Jones, M. Monique Ryan and C. Danniel De Vivo, editors, Neuromuscular Disorders of Infancy, Childhood and Adolescence–A Clinician's Approach, Academic Press, pp.‌ 1160, 2015.
[7] A. S. U. Doulah, S. A. Fattah, W. P. Zhu and M. O. Ahmad, “Wavelet domain feature extraction scheme based on dominant motor unit action potential of EMG signal for neuromuscular disease classification,” IEEE Transactions on Biomedical Circuits and Systems, vol. 8, no. 2, pp.155-164, 2014.‌
[8] F. Ertuğrul, Y. Kaya and R. Tekin, “A novel approach for sEMG signal classification with adaptive local binary patterns,” Medical & Biological Engineering & Computing, pp. 1-10, 2015.
[9] A. Phinyomark, P. Phukpattaranont and C. Limsakul, “Feature reduction and selection for EMG signal classification,” Expert Systems with Applications, vol. 39, no. 8, pp. 7420-7431, 2012.
[10] I. Elamvazuthi, N. H. X. Duy and Z. S. Ali, “Electromyography (EMG) based classification of neuromuscular disorders using multi-layer perceptron,” Procedia Computer Science, vol. 76, pp. 223-228, 2015.‌
[11] S. Shetty and Y. S. Rao, “SVM based machine learning approach to identify Parkinson's disease using gait analysis,” In Inventive Computation Technologies (ICICT), International Conference on, vol. 2, pp. 1-5, 2014.
[12] A. Goen, “Classification of EMG signals for assessment of neuromuscular disorders,” International Journal of Electronics and Electrical Engineering, vol. 2, no. 3, 2014.‌
[13] S. Koçer and A. E. Tümer, “Classifying neuromuscular diseases using artificial neural networks with applied Autoregressive and Cepstral analysis,” Neural Computing and Applications, pp. 1-8, 2016.
[14] O. Bazgir, J. Frounchi, S. A. H. Habibi, L. Palma and P. Pierleoni, “A neural network system for diagnosis and assessment of tremor in Parkinson disease patients,” In Biomedical Engineering (ICBME), 22nd Iranian Conference on, pp. 1-5, 2015.
[15] H. Pourakbari, Y. Sarbaz, J. Parvin and M. H. Vojudi, “Proper features extraction from the multiple sclerosis disease postural disorders for decision support system definition,” In Applied Mechanics and Materials, vol. 666, pp. 230-234, 2014.‌
[16] P. Kugler, C. Jaremenko, J. Schlachetzki, J. Winkler, J. Klucken and B. Eskofier, “Automatic recognition of Parkinson's disease using surface electromyography during standardized gait tests,” In Engineering in Medicine and Biology Society (EMBC) 35th Annual International Conference of the IEEE, pp. 5781-5784, 2013.
[17] N. H. Ghassemi, F. Marxreiter, C. F.Pasluosta, P. Kugler, J. Schlachetzki, A.Schramm and J. Klucken, “Combined accelerometer and EMG analysis to differentiate essential tremor from Parkinson's disease,” In Engineering in Medicine and Biology Society (EMBC), IEEE 38th Annual International Conference of the, pp. 672-675, 2016.
[18] P. R. Pal, G. Goswami and N. P. Mohanty, “Expert system design based on wavelet transform and linear feature selection,” In Computer Networks and Intelligent Computing, pp. 502-510, Springer Berlin Heidelberg, 2011.
[19] ‌ S. Kalwa and H. T. Patil, “Neuromuscular disease classification based on discrete wavelet transform of dominant motor unit action potential of EMG signal,” In Information Processing (ICIP), International Conference on, pp. 708-713, 2015.
[20] J. Kohlschuetter, J. Peters and E. Rueckert, “Learning probabilistic features from EMG data for predicting knee abnormalities,” In XIV Mediterranean Conference on Medical and Biological Engineering and Computing, pp. 662-666, 2016.
[21] M. Herrera-González, G. A. Martínez-Hernández, J. L. Rodríguez-Sotelo and Ó. F. Avilés-Sánchez, “Knee functional state classification using surface electromyographic and goniometric signals by means of artificial neural networks,” Ingeniería y Universidad, vol. 19, no. 1, pp. 51-66, 2015.
[22] M. Musselman and D. Djurdjanovic, “Time–frequency distributions in the classification of epilepsy from EEG signals,” Expert Systems with Applications, vol. 39, no. 13, pp. 11413-11422, 2012.
[23] J. L. Flanagan,Speech Analysis Synthesis and Perception, Springer Science & Business Media, Vol. 3, 2013.
[24] T. Ojala, M. Pietikainen and T. Maenpaa, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 7, pp. 971-987, 2002.
[25] H. Jin, Q. Liu, H. Lu and X. Tong, “Face detection using improved LBP under Bayesian framework,” In Image and Graphics (ICIG'04), Third International Conference on, pp. 306-309, 2004.
[26] L. Zhang, R. Chu, S. Xiang, S. Liao and S. Z. Li, “Face detection based on multi-block lbp representation,” In International Conference on Biometrics, Springer Berlin Heidelberg, pp. 11-18, 2007‌.
[27] C. Shan, S. Gong and P. W. McOwan, “Robust facial expression recognition using local binary patterns,” In Image Processing, ICIP IEEE International Conference on, vol. 2, pp. II-370, 2005.
[28] حمید صادقی، فضائل آیت‌اللهی و ابوالقاسم. اسدالله راعی، «شناسایی حالت چهره با استفاده از نرمالیزاسیون هندسی و تبدیل موجک مختلط Dual tree»، مجله مهندسی برق دانشگاه تبریز، جلد 45 شماره 3، صفحه 86-80، پاییز 94.
[29] سجاد شفیع‌پور یوردشاهی، میرهادی سیدعربی، علی آقاگل‌زاده «شناسایی چهره بر اساس ظاهر در رشته‌های ویدئویی»، مجله مهندسی برق دانشگاه تبریز، جلد 45 شماره 2، صفحه 83-75، تابستان 94.
[30] E. Bingham, S. Kaski, J. Laaksonen and J. Lampinen, Advances in Independent Component Analysis and Learning Machines. Academic Press, pp. 199-202, 2015.
[31] R. M. Haralick and K. Shanmugam, “Textural features for image classification,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 6, pp. 610-621, 1973.
[32] J. M. Hausdorff, A. Lertratanakul, M. E. Cudkowicz, A. L. Peterson, D. Kaliton and A. L. Goldberger, “Dynamic markers of altered gait rhythm in amyotrophic lateral sclerosis,” Journal of Applied Physiology, vol. 88, pp. 2045-2053, 2000, https://www.physionet.org/physiobank/database/gaitndd.
[33] M. Nikolic, Detailed Analysis of Clinical Electromyography Signals: EMG Decomposition, Findings and Firing Pattern Analysis in Controls and Patients With Myopathy and Amytrophic Lateral Sclerosis, Ph.D Thesis, 2001, http://www.emglab.net, data are available as dataset N2001.
[34] A. Frank and A. Asuncion, UCI Machine Learning Repository, University of California, School of Information and Computer Science, Irvine, http://archive.ics.uci.edu/ml, 2014.
[35] V. Cantarella, Bones and Muscles. An Illustrated Anatomy, New York: Wolf Fly Press‌, pp. 149-155, 1999.
[36] D. L. Donoho and I. M. Johnstone, “Adapting to unknown smoothness via wavelet shrinkage,” Journal of the American Statistical Association, vol. 90, no. 432, pp. 1200-1224, 1995.‌
[37] F. Bianconi and A. Fernández, “On the occurrence probability of local binary patterns: a theoretical study,” Journal of Mathematical Imaging and Vision, vol. 40, no.3, pp. 259-268, 2011.
[38] K. Nazarpour, A. R. Sharafat and S. M. P. Firoozabadi, “Surface EMG signal classification using a selective mix of higher order statistics,” In IEEE Engineering in Medicine and Biology 27th Annual Conference, pp. 4208-4211, 2006.
[39] A. Phinyomark, S. Hirunviriya, C. Limsakul and P. Phukpattaranont, “Evaluation of EMG feature extraction for hand movement recognition based on Euclidean distance and standard deviation,” In Electrical Engineering/Electronics Computer Telecommunications and Information Technology (ECTI-CON), International Conference on, pp. 856-860, 2010.
[40] Y. Al-Assaf, “Surface myoelectric signal analysis: dynamic approaches for change detection and classification,” IEEE Transactions on Biomedical Engineering, vol. 53, no. 11, pp. 2248-2256, 2006.
[41] K. Englehart, B. Hudgins, P. Parker and M. Stevenson, “Time-frequency representation for classification of the transient myoelectric signal,” In Engineering in Medicine and Biology Society, Proceedings of the 20th Annual International Conference of the IEEE, Vol. 5, pp. 2627-2630, 1998.
[42] Ö. F. Ertuğrul, M. E. Tağluk, Y. Kaya and R. Tekin, “EMG signal classification by extreme learning machine,” In Signal Processing and Communications Applications Conference (SIU), 21st, pp. 1-4, 2013.

فایل ها

هم رسانی

ارجاع به این مقاله

آمار