Automatic Classification of Intramuscular EMG to Recognize Pathologies (original) (raw)
Related papers
Emg Based Diagnosis of Myopathy and Neuropathy Using Machine Learning Techniques
2020
Myopathy and Neuropathy are nonprogressive and progressive neuromuscular disorders which weakens the muscles and nerves respectively. Electromyography (EMG) signals are bio signals obtained from the individual muscle cells. EMG based diagnosis for neuromuscular disorders is a safe and reliable method. Integrating the EMG signals with machine learning techniques improves the diagnostic accuracy. The proposed system performs analysis on the clinical raw EMG dataset which is obtained from the publicly available PhysioNet database. The twochannel raw EMG dataset of healthy, myopathy and neuropathy subjects are divided into samples. The Time Domain (TD) features are extracted from divided samples of each subject. The extracted features are annotated with the class label representing the state of the individual. The annotated features split into training and testing set in the standard ratio 70: 30. The comparative classification analysis on the complete annotated features set and promine...
Classification of EMG Signals for Assessment of Neuromuscular Disorders
International Journal of Electronics and Electrical Engineering, 2014
An accurate and computationally efficient means of feature extraction of electromyographic (EMG) signal patterns has been the subject of considerable research effort in recent years. Quantitative analysis of EMG signals provides an important source of information for the classification of neuromuscular disorders. The objective of this study is to discriminate between normal (NOR), myopathic (MYO) and neuropathic (NEURO) subjects. The experiment consisted of 22 pathogenic (11 MYO and 11 NEURO) and 12 healthy persons. The signals were recorded at 30% Maximum Voluntary Contraction (MVC) for 5 seconds. Features of MUAPs extracted in time have been quantitatively analysed. We have used binary SVM for classification. Separation of normal subjects from neuromuscular disease subjects has an accuracy of 83.45%, whereas separation of subjects from the two types of subjects (myopathic and neuropathic) has an accuracy of 68.29% which is again high.
Characterizing EMG Data using Machine- Learning Tools
Comput Biol Med. , 2014
Effective electromyographic (EMG) signal characterization is critical in the diagnosis of neuromuscular disorders. Machine-learning based pattern classification algorithms are commonly used to produce such characterizations. Several classifiers have been investigated to develop accurate and computationally efficient strategies for EMG signal characterization. This paper provides a critical review of some of the classification methodologies used in EMG characterization, and presents the state-of-the-art accomplishments in this field, emphasizing neuromuscular pathology. The techniques studied are grouped by their methodology, and a summary of the salient findings associated with each method is presented.
EMG Signal Classification with Effective Features for Diagnosis
Advances in Intelligent Systems and Computing, 2020
Electromyography (EMG) signals are broadly used in various clinical or biomedical applications, prosthesis or rehabilitation devices, Muscle-Computer Interface (MCI), Evolvable Hardware Chip (EHW) development and many other applications. Electromyography (EMG) signal records the myopathy from nonlinear subjects in both time domain and frequency domain. It becomes very difficult to classify these various statuses. In this paper, a feature extraction and classification method of healthy and myopathy EMG signals are proposed where two features have been extracted on both healthy and myopathy EMG. Mean Squared Error (MSE) has been calculated to observe which feature will give better classification result. Then SVM is used to classify the extracted results. To evaluate the proposed model, a standard dataset collected from physionet.org is used where it shows higher accuracy than the conventional methods.
Robust Classification of Intramuscular EMG Signals to Aid the Diagnosis of Neuromuscular Disorders
IEEE Open Journal of Engineering in Medicine and Biology
This article presents the design and validation of an accurate automatic diagnostic system to classify intramuscular EMG (iEMG) signals into healthy, myopathy, or neuropathy categories to aid the diagnosis of neuromuscular diseases. Methods: First, an iEMG signal is decimated to produce a set of "disjoint" downsampled signals, which are decomposed by the lifting wavelet transform (LWT). The Higuchi's fractal dimensions (FDs) of LWT coefficients in the subbands are computed. The FDs of LWT subband coefficients are fused with one-dimensional local binary pattern derived from each downsampled signal. Next, a multilayer perceptron neural network (MLPNN) determines the class labels of downsampled signals. Finally, the sequence of class labels is fed to the Boyer-Moore majority vote (BMMV) algorithm, which assigns a class to every iEMG signal. Results: The MLPNN-BMMV classifier was experimented with 250 iEMG signals belonging to three categories. The performance of the classifier was validated in comparison with state-of-the-art approaches. The MLPNN-BMMV has resulted in impressive performance measures (%) using a 10-fold cross-validation-accuracy = 99.87 ± 0.25, sensitivity (normal) = 99.97 ± 0.13, sensitivity (myopathy) = 99.68 ± 0.95, sensitivity (neuropathy) = 99.76 ± 0.66, specificity (normal) = 99.72 ± 0.61, specificity (myopathy) = 99.98 ± 0.10, and specificity (neuropathy) = 99.96 ± 0.14-surpassing the existing approaches. Conclusions: A future research direction is to validate the
Techniques of EMG signal analysis and classification of Neuromuscular diseases
Artificial intelligence techniques are being used effectively in medical diagnostic tools to increase the diagnostic accuracy and provide additional knowledge. Electromyography (EMG) signals are becoming increasingly important in clinical and biomedical applications. Detection, processing and classification of EMG signals are very desirable because it allows a more standardized evaluation to discriminate between different neuromus-cular diseases. This paper reviews a brief explanation of the different features extraction and classification techniques for classifying EMG signals used in literatures. Wavelet Transform (WT), Principle Component Analysis (PCA), and Independent Component Analysis (ICA) are different feature extraction techniques. Literature presents different techniques to classify EMG data such as probabilistic neural network (PNN), Support Vector Machine (SVM), Artificial Neural Networks (ANN), etc. In this paper neuromuscular disease classification from electromyography (EMG) signals are proposed based on different combination of features extraction methods and types of classifiers. Combination of WT and SVM improved the classification accuracy than other combinations such as DWT with ANN, ICA with MLPN, PCA with ANN and DWT with PNN. Keywords: Electromyogram (EMG), Wavelet Transform (WT), Principle Component Analysis (PCA), Support Vector Machine (SVM), Multilayer Perceptron Neural Network (MLPNN), Probabilistic Neural Network (PNN).
Journal of biomedical physics & engineering, 2013
The time and frequency features of motor unit action potentials (MUAPs) extracted from electromyographic (EMG) signal provide discriminative information for diagnosis and treatment of neuromuscular disorders. However, the results of conventional automatic diagnosis methods using MUAP features is not convincing yet. The main goal in designing a MUAP characterization system is obtaining high classification accuracy to be used in clinical decision system. For this aim, in this study, a robust classifier is proposed to improve MUAP classification performance in estimating the class label (myopathic, neuropathic and normal) of a given MUAP. The proposed scheme employs both time and time-frequency features of a MUAP along with an ensemble of support vector machines (SVMs) classifiers in hybrid serial/parallel architecture. Time domain features includes phase, turn, peak to peak amplitude, area, and duration of the MUAP. Time-frequency features are discrete wavelet transform coefficients o...
A novel method for automated EMG decomposition an MUAP classification
Objective: This paper proposes a novel method for the extraction and classification of individual motor unit action potentials (MUAPs) from intramuscular electromyographic signals. Methodology: The proposed method automatically detects the number of template MUAP clusters and classifies them into normal, neuropathic or myopathic. It consists of three steps: (i) preprocessing of electromyogram (EMG) recordings, (ii) MUAP detection and clustering and (iii) MUAP classification. Results: The approach has been validated using a dataset of EMG recordings and an annotated collection of MUAPs. The correct identification rate for MUAP clustering is 93, 95 and 92% for normal, myopathic and neuropathic, respectively. Ninety-one percent of the superimposed MUAPs were correctly identified. The obtained accuracy for MUAP classification is about 86%. Conclusion: The proposed method, apart from efficient EMG decomposition addresses automatic MUAP classification to neuropathic, myopathic or normal classes directly from raw EMG signals. #
Classification and Diagnosis of Myopathy from EMG Signals
We present a methodology to predict the presence of myopathy (muscle disease) from intramuscular electromyography (EMG) signals. By evaluating the shape and frequency of electrical action potentials produced by muscular fibers and captured in EMG measurements, a physician can often detect both the presence and the severity of such disorders. However, EMG measurements can vary significantly across different subjects, different muscles, and according to session-specific characteristics such as muscle fatigue and degree of contraction. By considering fixed-duration (0.5-2 sec) frequency-domain samples of diagnostic regions in EMG signals measured at full muscle contraction, we can automatically detect the presence of myopathies across different subjects and muscles with ~90% accuracy. We argue that our methodology is more generally applicable than existing methods that depend upon accurate segmentation of individual motor unit action potential (MUAP) waveforms. We present a rigorous evaluation of our technique across several different subjects and muscles.