Neuromuscular electrical stimulation induced brain patterns to decode motor imagery

C. Vidaurre; J. Pascual; A. Ramos-Murguialday; R. Lorenz; B. Blankertz; N. Birbaumer; K. R. Müller

doi:10.1016/j.clinph.2013.03.009

Neuromuscular electrical stimulation induced brain patterns to decode motor imagery

C. Vidaurre, J. Pascual, A. Ramos-Murguialday, R. Lorenz, B. Blankertz, N. Birbaumer, K. R. Müller

Research output: Contribution to journal › Article › peer-review

27 Citations (Scopus)

Abstract

Objective: Regardless of the paradigm used to implement a brain-computer interface (BCI), all systems suffer from BCI-inefficiency. In the case of patients the inefficiency can be high. Some solutions have been proposed to overcome this problem, however they have not been completely successful yet. Methods: EEG from 10 healthy users was recorded during neuromuscular electrical stimulation (NMES) of hands and feet and during motor imagery (MI) of the same limbs. Features and classifiers were computed using part of these data to decode MI. Results: Offline analyses showed that it was possible to decode MI using a classifier based on afferent patterns induced by NMES and even infer a better model than with MI data. Conclusion: Afferent NMES motor patterns can support the calibration of BCI systems and be used to decode MI. Significance: This finding might be a new way to train sensorimotor rhythm (SMR) based BCI systems for healthy users having difficulties to attain BCI control. It might also be an alternative to train MI-based BCIs for users who cannot perform real movements but have remaining afferents (ALS, stroke patients).

Original language	English
Pages (from-to)	1824-1834
Number of pages	11
Journal	Clinical Neurophysiology
Volume	124
Issue number	9
DOIs	https://doi.org/10.1016/j.clinph.2013.03.009
Publication status	Published - 2013 Sept

Bibliographical note

Funding Information:
We gratefully acknowledge Christian Klauer and Thomas Schauer for letting us use part of their NMES hardware and software and a room to perform the experiments. We thank Stefan Haufe for the production of Fig. 6 . The research leading to these results has received funding from the European Community’s Seventh Framework Program under grant MUNDUS and HUMOUR-ICT-2008-231724, the European Union’s PASCAL 2 Network of Excellence (ICT-216886), the German Government under grants MU 987/3-2, the Bernstein Focus: Neurotechnology BMBF 01GQ0831 and BMBF 01GQ0850, the German Research Foundation DFG project KU 1453-1 and the World Class University Program through the National Research Foundation of Korea funded by the Ministry of Education, Science, and Technology , under Grant R31-10008. This publication only reflects the authors’ views.

Keywords

Afferent patterns
BCI-inefficency
Efferent pattern classification
Motor imagery
Neuromuscular electrical stimulation

ASJC Scopus subject areas

Sensory Systems
Neurology
Clinical Neurology
Physiology (medical)

Access to Document

10.1016/j.clinph.2013.03.009

Cite this

@article{b9a332374d6d4f7bb04873f89f1b61ec,

title = "Neuromuscular electrical stimulation induced brain patterns to decode motor imagery",

abstract = "Objective: Regardless of the paradigm used to implement a brain-computer interface (BCI), all systems suffer from BCI-inefficiency. In the case of patients the inefficiency can be high. Some solutions have been proposed to overcome this problem, however they have not been completely successful yet. Methods: EEG from 10 healthy users was recorded during neuromuscular electrical stimulation (NMES) of hands and feet and during motor imagery (MI) of the same limbs. Features and classifiers were computed using part of these data to decode MI. Results: Offline analyses showed that it was possible to decode MI using a classifier based on afferent patterns induced by NMES and even infer a better model than with MI data. Conclusion: Afferent NMES motor patterns can support the calibration of BCI systems and be used to decode MI. Significance: This finding might be a new way to train sensorimotor rhythm (SMR) based BCI systems for healthy users having difficulties to attain BCI control. It might also be an alternative to train MI-based BCIs for users who cannot perform real movements but have remaining afferents (ALS, stroke patients).",

keywords = "Afferent patterns, BCI-inefficency, Efferent pattern classification, Motor imagery, Neuromuscular electrical stimulation",

author = "C. Vidaurre and J. Pascual and A. Ramos-Murguialday and R. Lorenz and B. Blankertz and N. Birbaumer and M{\"u}ller, {K. R.}",

note = "Funding Information: We gratefully acknowledge Christian Klauer and Thomas Schauer for letting us use part of their NMES hardware and software and a room to perform the experiments. We thank Stefan Haufe for the production of Fig. 6 . The research leading to these results has received funding from the European Community{\textquoteright}s Seventh Framework Program under grant MUNDUS and HUMOUR-ICT-2008-231724, the European Union{\textquoteright}s PASCAL 2 Network of Excellence (ICT-216886), the German Government under grants MU 987/3-2, the Bernstein Focus: Neurotechnology BMBF 01GQ0831 and BMBF 01GQ0850, the German Research Foundation DFG project KU 1453-1 and the World Class University Program through the National Research Foundation of Korea funded by the Ministry of Education, Science, and Technology , under Grant R31-10008. This publication only reflects the authors{\textquoteright} views. ",

year = "2013",

month = sep,

doi = "10.1016/j.clinph.2013.03.009",

language = "English",

volume = "124",

pages = "1824--1834",

journal = "Clinical Neurophysiology",

issn = "1388-2457",

publisher = "Elsevier Ireland Ltd",

number = "9",

}

TY - JOUR

T1 - Neuromuscular electrical stimulation induced brain patterns to decode motor imagery

AU - Vidaurre, C.

AU - Pascual, J.

AU - Ramos-Murguialday, A.

AU - Lorenz, R.

AU - Blankertz, B.

AU - Birbaumer, N.

AU - Müller, K. R.

N1 - Funding Information: We gratefully acknowledge Christian Klauer and Thomas Schauer for letting us use part of their NMES hardware and software and a room to perform the experiments. We thank Stefan Haufe for the production of Fig. 6 . The research leading to these results has received funding from the European Community’s Seventh Framework Program under grant MUNDUS and HUMOUR-ICT-2008-231724, the European Union’s PASCAL 2 Network of Excellence (ICT-216886), the German Government under grants MU 987/3-2, the Bernstein Focus: Neurotechnology BMBF 01GQ0831 and BMBF 01GQ0850, the German Research Foundation DFG project KU 1453-1 and the World Class University Program through the National Research Foundation of Korea funded by the Ministry of Education, Science, and Technology , under Grant R31-10008. This publication only reflects the authors’ views.

PY - 2013/9

Y1 - 2013/9

N2 - Objective: Regardless of the paradigm used to implement a brain-computer interface (BCI), all systems suffer from BCI-inefficiency. In the case of patients the inefficiency can be high. Some solutions have been proposed to overcome this problem, however they have not been completely successful yet. Methods: EEG from 10 healthy users was recorded during neuromuscular electrical stimulation (NMES) of hands and feet and during motor imagery (MI) of the same limbs. Features and classifiers were computed using part of these data to decode MI. Results: Offline analyses showed that it was possible to decode MI using a classifier based on afferent patterns induced by NMES and even infer a better model than with MI data. Conclusion: Afferent NMES motor patterns can support the calibration of BCI systems and be used to decode MI. Significance: This finding might be a new way to train sensorimotor rhythm (SMR) based BCI systems for healthy users having difficulties to attain BCI control. It might also be an alternative to train MI-based BCIs for users who cannot perform real movements but have remaining afferents (ALS, stroke patients).

AB - Objective: Regardless of the paradigm used to implement a brain-computer interface (BCI), all systems suffer from BCI-inefficiency. In the case of patients the inefficiency can be high. Some solutions have been proposed to overcome this problem, however they have not been completely successful yet. Methods: EEG from 10 healthy users was recorded during neuromuscular electrical stimulation (NMES) of hands and feet and during motor imagery (MI) of the same limbs. Features and classifiers were computed using part of these data to decode MI. Results: Offline analyses showed that it was possible to decode MI using a classifier based on afferent patterns induced by NMES and even infer a better model than with MI data. Conclusion: Afferent NMES motor patterns can support the calibration of BCI systems and be used to decode MI. Significance: This finding might be a new way to train sensorimotor rhythm (SMR) based BCI systems for healthy users having difficulties to attain BCI control. It might also be an alternative to train MI-based BCIs for users who cannot perform real movements but have remaining afferents (ALS, stroke patients).

KW - Afferent patterns

KW - BCI-inefficency

KW - Efferent pattern classification

KW - Motor imagery

KW - Neuromuscular electrical stimulation

UR - http://www.scopus.com/inward/record.url?scp=84881113245&partnerID=8YFLogxK

U2 - 10.1016/j.clinph.2013.03.009

DO - 10.1016/j.clinph.2013.03.009

M3 - Article

C2 - 23642833

AN - SCOPUS:84881113245

SN - 1388-2457

VL - 124

SP - 1824

EP - 1834

JO - Clinical Neurophysiology

JF - Clinical Neurophysiology

IS - 9

ER -

Neuromuscular electrical stimulation induced brain patterns to decode motor imagery

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this