A two-stage method for MUAP classification based on EMG decomposition

A method for the extraction and classification of individual motor unit action potentials (MUAPs) from needle electromyographic signals is presented. The proposed method automatically decomposes MUAPs and classifies them into normal, neuropathic or myopathic using a two-stage feature-based classifier. The method consists of four steps: (i) preprocessing of EMG recordings, (ii) MUAP clustering and detection of superimposed MUAPs, (iii) feature extraction and (iv) MUAP classification using a two-stage classifier. The proposed method employs Radial Basis Function Artificial Neural Networks and decision trees. It requires minimal use of tuned parameters and is able to provide interpretation for the classification decisions. The approach has been validated on real EMG recordings and an annotated collection of MUAPs. The success rate for MUAP clustering is 96%, while the accuracy for MUAP classification is about 89%.

[1]  Constantinos S. Pattichis,et al.  Neural network models in EMG diagnosis , 1995 .

[2]  G. H. Loudon,et al.  New signal processing techniques for the decomposition of EMG signals , 1992, Medical and Biological Engineering and Computing.

[3]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[4]  E Stålberg,et al.  Multi-MUP EMG analysis--a two year experience in daily clinical work. , 1995, Electroencephalography and clinical neurophysiology.

[5]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[6]  S Andreassen,et al.  Methods for computer-aided measurement of motor unit parameters. , 1987, Electroencephalography and clinical neurophysiology. Supplement.

[7]  C. Pattichis,et al.  Autoregressive and cepstral analyses of motor unit action potentials. , 1999, Medical engineering & physics.

[8]  P. Jamieson,et al.  Computerized interpretation of electromyographic data. , 1990, Electroencephalography and clinical neurophysiology.

[9]  Raghavaiah Kanakamedala,et al.  Electrodiagnosis in Diseases of Nerve and Muscle: Principles and Practice. 2nd Edition , 1989 .

[10]  C.I. Christodoulou,et al.  Unsupervised pattern recognition for the classification of EMG signals , 1999, IEEE Transactions on Biomedical Engineering.

[11]  Jun Kimura,et al.  Electrodiagnosis in Diseases of Nerve and Muscle: Principles and Practice , 1983 .

[12]  M. Brooke,et al.  Myology , 1987, Neurology.

[13]  J. Fang,et al.  Decomposition of multiunit electromyographic signals , 1999, IEEE Transactions on Biomedical Engineering.

[14]  L J Dorfman,et al.  AAEE minimonograph #29: Automatic quantitative electromyography , 1988, Muscle & nerve.

[15]  M.H. Hassoun,et al.  NNERVE: Neural Network Extraction of Repetitive Vectors for Electromyography. I. Algorithm , 1994, IEEE Transactions on Biomedical Engineering.

[16]  J Yang,et al.  [Extraction of MUAP from NEMG signal using self-organization competing NN]. , 2001, Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi.

[17]  S. Andreassen,et al.  Quantitative Analysis of Individual Motor Unit Potentials: A Proposition for Standardized Terminology and Criteria for Measurement , 1986, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[18]  Anders Fuglsang-Frederiksen,et al.  The role of different EMG methods in evaluating myopathy , 2006, Clinical Neurophysiology.

[19]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[20]  Kevin C. McGill,et al.  Optimal resolution of superimposed action potentials , 2002, IEEE Transactions on Biomedical Engineering.

[21]  F BUCHTHAL,et al.  Action potential parameters in normal human muscle and their dependence on physical variables. , 1954, Acta physiologica Scandinavica.

[22]  S D Nandedkar,et al.  Analysis of amplitude and area of concentric needle EMG motor unit action potentials. , 1988, Electroencephalography and clinical neurophysiology.

[23]  Christos D. Katsis,et al.  A novel method for automated EMG decomposition and MUAP classification , 2006, Artif. Intell. Medicine.

[24]  D. Stashuk,et al.  Automatic decomposition of selective needle-detected myoelectric signals , 1988, IEEE Transactions on Biomedical Engineering.

[25]  James W. Albers,et al.  Review of Quantitative and Automated Needle Electromyographic Analyses , 1981, IEEE Transactions on Biomedical Engineering.

[26]  D C Boyd,et al.  A review of the methods of automatic analysis in clinical electromyography. , 1976, Computers in biology and medicine.

[27]  George S. Moschytz,et al.  A software package for the decomposition of long-term multichannel EMG signals using wavelet coefficients , 2003, IEEE Transactions on Biomedical Engineering.

[28]  Coatrieux Jl.  Interference electromyogram processing. Part II: Experimental and simulated EMG AR-modeling. , 1983 .

[29]  O. Fokapu,et al.  Automatic identification of motor unit action potential trains from electromyographic signals using fuzzy techniques , 2003, Medical and Biological Engineering and Computing.

[30]  Krzysztof J. Cios,et al.  Uniqueness of medical data mining , 2002, Artif. Intell. Medicine.

[31]  Ronald S. Lefever,et al.  A Procedure for Decomposing the Myoelectric Signal Into Its Constituent Action Potentials - Part I: Technique, Theory, and Implementation , 1982, IEEE Transactions on Biomedical Engineering.

[32]  Alberto Maria Segre,et al.  Programs for Machine Learning , 1994 .

[33]  Itaru Takehara,et al.  Reliability of quantitative motor unit action potential parameters , 2004, Muscle & nerve.

[34]  J L Coatrieux.  Interference electromyogram processing. Part II: Experimental and simulated EMG AR-modeling. , 1983, Electromyography and clinical neurophysiology.

[35]  Kevin C. McGill,et al.  Automatic Decomposition of the Clinical Electromyogram , 1985, IEEE Transactions on Biomedical Engineering.

[36]  Christian Krarup,et al.  Pitfalls in electrodiagnosis , 1999, Journal of Neurology.

[37]  C.S. Pattichis,et al.  Time-scale analysis of motor unit action potentials , 1999, IEEE Transactions on Biomedical Engineering.

[38]  Philip D. Wasserman,et al.  Advanced methods in neural computing , 1993, VNR computer library.

[39]  M Maranzana Figini,et al.  The parametrization of the electromyographic signal: an approach based on simulated EMG signals. , 1984, Electromyography and clinical neurophysiology.