Muscle categorization using quantitative needle electromyography: A 2-stage Gaussian mixture model based approach

Meena Abdelmaseeh, Pascal Poupart, Benn Smith, Daniel Stashuk

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Needle Electromyography, in combination with nerve conduction studies, is the gold standard methodology for assessing the neurophysiologic effects of neuromuscular diseases. Muscle categorization is typically based on visual and auditory assessment of the morphology and activation patterns of its constituent motor units. A procedure which is highly dependent on the skills and level of experience of the examiner. This motivates the development of automated or semi-automated categorization techniques. This paper describes a 2-stage Gaussian mixture model based approach. In the first stage, a muscle is classified as neurogenic or myopathic. The second stage uses a classifier specific to each disease category to confirm or refute the disease involvement. A total of 2556 motor unit potentials sampled from 48 normal, 30 neurogenic and 20 myopathic tibialis anterior muscles were utilized for this study. The proposed approach showed an average accuracy of 91.25%, which is higher than the compared linear and non-linear multi-class schemas. In addition to improved accuracy, the 2-stage approach is more suitable for the muscle categorization, because it has a hierarchical decision structure similar to current clinical practice, and its output can be interpreted as a measure of confidence.

Original languageEnglish (US)
Title of host publicationProceedings - 2012 11th International Conference on Machine Learning and Applications, ICMLA 2012
Pages548-553
Number of pages6
Volume1
DOIs
StatePublished - 2012
Event11th IEEE International Conference on Machine Learning and Applications, ICMLA 2012 - Boca Raton, FL, United States
Duration: Dec 12 2012Dec 15 2012

Other

Other11th IEEE International Conference on Machine Learning and Applications, ICMLA 2012
CountryUnited States
CityBoca Raton, FL
Period12/12/1212/15/12

Fingerprint

Electromyography
Needles
Muscle
Disease
decision structure
gold standard
examiner
activation
confidence
Classifiers
Chemical activation
methodology
experience

Keywords

  • 2-stage approach
  • Decomposition based quantitative EMG
  • Gaussian Mixture Model
  • Muscle categorization
  • Needle EMG

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Education

Cite this

Abdelmaseeh, M., Poupart, P., Smith, B., & Stashuk, D. (2012). Muscle categorization using quantitative needle electromyography: A 2-stage Gaussian mixture model based approach. In Proceedings - 2012 11th International Conference on Machine Learning and Applications, ICMLA 2012 (Vol. 1, pp. 548-553). [6406621] https://doi.org/10.1109/ICMLA.2012.100

Muscle categorization using quantitative needle electromyography : A 2-stage Gaussian mixture model based approach. / Abdelmaseeh, Meena; Poupart, Pascal; Smith, Benn; Stashuk, Daniel.

Proceedings - 2012 11th International Conference on Machine Learning and Applications, ICMLA 2012. Vol. 1 2012. p. 548-553 6406621.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abdelmaseeh, M, Poupart, P, Smith, B & Stashuk, D 2012, Muscle categorization using quantitative needle electromyography: A 2-stage Gaussian mixture model based approach. in Proceedings - 2012 11th International Conference on Machine Learning and Applications, ICMLA 2012. vol. 1, 6406621, pp. 548-553, 11th IEEE International Conference on Machine Learning and Applications, ICMLA 2012, Boca Raton, FL, United States, 12/12/12. https://doi.org/10.1109/ICMLA.2012.100
Abdelmaseeh M, Poupart P, Smith B, Stashuk D. Muscle categorization using quantitative needle electromyography: A 2-stage Gaussian mixture model based approach. In Proceedings - 2012 11th International Conference on Machine Learning and Applications, ICMLA 2012. Vol. 1. 2012. p. 548-553. 6406621 https://doi.org/10.1109/ICMLA.2012.100
Abdelmaseeh, Meena ; Poupart, Pascal ; Smith, Benn ; Stashuk, Daniel. / Muscle categorization using quantitative needle electromyography : A 2-stage Gaussian mixture model based approach. Proceedings - 2012 11th International Conference on Machine Learning and Applications, ICMLA 2012. Vol. 1 2012. pp. 548-553
@inproceedings{bf9ab69d95cd4c2cab6cde9ea50f57a3,
title = "Muscle categorization using quantitative needle electromyography: A 2-stage Gaussian mixture model based approach",
abstract = "Needle Electromyography, in combination with nerve conduction studies, is the gold standard methodology for assessing the neurophysiologic effects of neuromuscular diseases. Muscle categorization is typically based on visual and auditory assessment of the morphology and activation patterns of its constituent motor units. A procedure which is highly dependent on the skills and level of experience of the examiner. This motivates the development of automated or semi-automated categorization techniques. This paper describes a 2-stage Gaussian mixture model based approach. In the first stage, a muscle is classified as neurogenic or myopathic. The second stage uses a classifier specific to each disease category to confirm or refute the disease involvement. A total of 2556 motor unit potentials sampled from 48 normal, 30 neurogenic and 20 myopathic tibialis anterior muscles were utilized for this study. The proposed approach showed an average accuracy of 91.25{\%}, which is higher than the compared linear and non-linear multi-class schemas. In addition to improved accuracy, the 2-stage approach is more suitable for the muscle categorization, because it has a hierarchical decision structure similar to current clinical practice, and its output can be interpreted as a measure of confidence.",
keywords = "2-stage approach, Decomposition based quantitative EMG, Gaussian Mixture Model, Muscle categorization, Needle EMG",
author = "Meena Abdelmaseeh and Pascal Poupart and Benn Smith and Daniel Stashuk",
year = "2012",
doi = "10.1109/ICMLA.2012.100",
language = "English (US)",
isbn = "9780769549132",
volume = "1",
pages = "548--553",
booktitle = "Proceedings - 2012 11th International Conference on Machine Learning and Applications, ICMLA 2012",

}

TY - GEN

T1 - Muscle categorization using quantitative needle electromyography

T2 - A 2-stage Gaussian mixture model based approach

AU - Abdelmaseeh, Meena

AU - Poupart, Pascal

AU - Smith, Benn

AU - Stashuk, Daniel

PY - 2012

Y1 - 2012

N2 - Needle Electromyography, in combination with nerve conduction studies, is the gold standard methodology for assessing the neurophysiologic effects of neuromuscular diseases. Muscle categorization is typically based on visual and auditory assessment of the morphology and activation patterns of its constituent motor units. A procedure which is highly dependent on the skills and level of experience of the examiner. This motivates the development of automated or semi-automated categorization techniques. This paper describes a 2-stage Gaussian mixture model based approach. In the first stage, a muscle is classified as neurogenic or myopathic. The second stage uses a classifier specific to each disease category to confirm or refute the disease involvement. A total of 2556 motor unit potentials sampled from 48 normal, 30 neurogenic and 20 myopathic tibialis anterior muscles were utilized for this study. The proposed approach showed an average accuracy of 91.25%, which is higher than the compared linear and non-linear multi-class schemas. In addition to improved accuracy, the 2-stage approach is more suitable for the muscle categorization, because it has a hierarchical decision structure similar to current clinical practice, and its output can be interpreted as a measure of confidence.

AB - Needle Electromyography, in combination with nerve conduction studies, is the gold standard methodology for assessing the neurophysiologic effects of neuromuscular diseases. Muscle categorization is typically based on visual and auditory assessment of the morphology and activation patterns of its constituent motor units. A procedure which is highly dependent on the skills and level of experience of the examiner. This motivates the development of automated or semi-automated categorization techniques. This paper describes a 2-stage Gaussian mixture model based approach. In the first stage, a muscle is classified as neurogenic or myopathic. The second stage uses a classifier specific to each disease category to confirm or refute the disease involvement. A total of 2556 motor unit potentials sampled from 48 normal, 30 neurogenic and 20 myopathic tibialis anterior muscles were utilized for this study. The proposed approach showed an average accuracy of 91.25%, which is higher than the compared linear and non-linear multi-class schemas. In addition to improved accuracy, the 2-stage approach is more suitable for the muscle categorization, because it has a hierarchical decision structure similar to current clinical practice, and its output can be interpreted as a measure of confidence.

KW - 2-stage approach

KW - Decomposition based quantitative EMG

KW - Gaussian Mixture Model

KW - Muscle categorization

KW - Needle EMG

UR - http://www.scopus.com/inward/record.url?scp=84873589331&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873589331&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2012.100

DO - 10.1109/ICMLA.2012.100

M3 - Conference contribution

AN - SCOPUS:84873589331

SN - 9780769549132

VL - 1

SP - 548

EP - 553

BT - Proceedings - 2012 11th International Conference on Machine Learning and Applications, ICMLA 2012

ER -