Decoding of motor intentions from epidural ECoG recordings in severely paralyzed chronic stroke patients

M. Spüler, A. Walter, A. Ramos-Murguialday, G. Naros, N. Birbaumer, A. Gharabaghi, W. Rosenstiel, M. Bogdan

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

Objective. Recently, there have been several approaches to utilize a brain-computer interface (BCI) for rehabilitation with stroke patients or as an assistive device for the paralyzed. In this study we investigated whether up to seven different hand movement intentions can be decoded from epidural electrocorticography (ECoG) in chronic stroke patients.

Approach. In a screening session we recorded epidural ECoG data over the ipsilesional motor cortex from four chronic stroke patients who had no residual hand movement. Data was analyzed offline using a support vector machine (SVM) to decode different movement intentions.

Main results. We showed that up to seven hand movement intentions can be decoded with an average accuracy of 61% (chance level 15.6%). When reducing the number of classes, average accuracies up to 88% can be achieved for decoding three different movement intentions.

Significance. The findings suggest that ipsilesional epidural ECoG can be used as a viable control signal for BCI-driven neuroprosthesis. Although patients showed no sign of residual hand movement, brain activity at the ipsilesional motor cortex still shows enough intention-related activity to decode different movement intentions with sufficient accuracy.

Original languageEnglish
Article number066008
JournalJournal of Neural Engineering
Volume11
Issue number6
DOIs
Publication statusPublished - Dec 1 2014

Fingerprint

Brain computer interface
Decoding
Stroke
Hand
Patient rehabilitation
Brain-Computer Interfaces
Support vector machines
Brain
Screening
Motor Cortex
Self-Help Devices
Electrocorticography

Keywords

  • electrocorticography (ECOG)
  • stroke, brain-computer interface (BCI)

ASJC Scopus subject areas

  • Biomedical Engineering
  • Cellular and Molecular Neuroscience
  • Medicine(all)

Cite this

Spüler, M., Walter, A., Ramos-Murguialday, A., Naros, G., Birbaumer, N., Gharabaghi, A., ... Bogdan, M. (2014). Decoding of motor intentions from epidural ECoG recordings in severely paralyzed chronic stroke patients. Journal of Neural Engineering, 11(6), [066008]. https://doi.org/10.1088/1741-2560/11/6/066008

Decoding of motor intentions from epidural ECoG recordings in severely paralyzed chronic stroke patients. / Spüler, M.; Walter, A.; Ramos-Murguialday, A.; Naros, G.; Birbaumer, N.; Gharabaghi, A.; Rosenstiel, W.; Bogdan, M.

In: Journal of Neural Engineering, Vol. 11, No. 6, 066008, 01.12.2014.

Research output: Contribution to journalArticle

Spüler, M, Walter, A, Ramos-Murguialday, A, Naros, G, Birbaumer, N, Gharabaghi, A, Rosenstiel, W & Bogdan, M 2014, 'Decoding of motor intentions from epidural ECoG recordings in severely paralyzed chronic stroke patients', Journal of Neural Engineering, vol. 11, no. 6, 066008. https://doi.org/10.1088/1741-2560/11/6/066008
Spüler, M. ; Walter, A. ; Ramos-Murguialday, A. ; Naros, G. ; Birbaumer, N. ; Gharabaghi, A. ; Rosenstiel, W. ; Bogdan, M. / Decoding of motor intentions from epidural ECoG recordings in severely paralyzed chronic stroke patients. In: Journal of Neural Engineering. 2014 ; Vol. 11, No. 6.
@article{1ce7bcd50c31427fb0be8d3257ebb13b,
title = "Decoding of motor intentions from epidural ECoG recordings in severely paralyzed chronic stroke patients",
abstract = "Objective. Recently, there have been several approaches to utilize a brain-computer interface (BCI) for rehabilitation with stroke patients or as an assistive device for the paralyzed. In this study we investigated whether up to seven different hand movement intentions can be decoded from epidural electrocorticography (ECoG) in chronic stroke patients.Approach. In a screening session we recorded epidural ECoG data over the ipsilesional motor cortex from four chronic stroke patients who had no residual hand movement. Data was analyzed offline using a support vector machine (SVM) to decode different movement intentions.Main results. We showed that up to seven hand movement intentions can be decoded with an average accuracy of 61{\%} (chance level 15.6{\%}). When reducing the number of classes, average accuracies up to 88{\%} can be achieved for decoding three different movement intentions.Significance. The findings suggest that ipsilesional epidural ECoG can be used as a viable control signal for BCI-driven neuroprosthesis. Although patients showed no sign of residual hand movement, brain activity at the ipsilesional motor cortex still shows enough intention-related activity to decode different movement intentions with sufficient accuracy.",
keywords = "electrocorticography (ECOG), stroke, brain-computer interface (BCI)",
author = "M. Sp{\"u}ler and A. Walter and A. Ramos-Murguialday and G. Naros and N. Birbaumer and A. Gharabaghi and W. Rosenstiel and M. Bogdan",
year = "2014",
month = "12",
day = "1",
doi = "10.1088/1741-2560/11/6/066008",
language = "English",
volume = "11",
journal = "Journal of Neural Engineering",
issn = "1741-2560",
publisher = "IOP Publishing Ltd.",
number = "6",

}

TY - JOUR

T1 - Decoding of motor intentions from epidural ECoG recordings in severely paralyzed chronic stroke patients

AU - Spüler, M.

AU - Walter, A.

AU - Ramos-Murguialday, A.

AU - Naros, G.

AU - Birbaumer, N.

AU - Gharabaghi, A.

AU - Rosenstiel, W.

AU - Bogdan, M.

PY - 2014/12/1

Y1 - 2014/12/1

N2 - Objective. Recently, there have been several approaches to utilize a brain-computer interface (BCI) for rehabilitation with stroke patients or as an assistive device for the paralyzed. In this study we investigated whether up to seven different hand movement intentions can be decoded from epidural electrocorticography (ECoG) in chronic stroke patients.Approach. In a screening session we recorded epidural ECoG data over the ipsilesional motor cortex from four chronic stroke patients who had no residual hand movement. Data was analyzed offline using a support vector machine (SVM) to decode different movement intentions.Main results. We showed that up to seven hand movement intentions can be decoded with an average accuracy of 61% (chance level 15.6%). When reducing the number of classes, average accuracies up to 88% can be achieved for decoding three different movement intentions.Significance. The findings suggest that ipsilesional epidural ECoG can be used as a viable control signal for BCI-driven neuroprosthesis. Although patients showed no sign of residual hand movement, brain activity at the ipsilesional motor cortex still shows enough intention-related activity to decode different movement intentions with sufficient accuracy.

AB - Objective. Recently, there have been several approaches to utilize a brain-computer interface (BCI) for rehabilitation with stroke patients or as an assistive device for the paralyzed. In this study we investigated whether up to seven different hand movement intentions can be decoded from epidural electrocorticography (ECoG) in chronic stroke patients.Approach. In a screening session we recorded epidural ECoG data over the ipsilesional motor cortex from four chronic stroke patients who had no residual hand movement. Data was analyzed offline using a support vector machine (SVM) to decode different movement intentions.Main results. We showed that up to seven hand movement intentions can be decoded with an average accuracy of 61% (chance level 15.6%). When reducing the number of classes, average accuracies up to 88% can be achieved for decoding three different movement intentions.Significance. The findings suggest that ipsilesional epidural ECoG can be used as a viable control signal for BCI-driven neuroprosthesis. Although patients showed no sign of residual hand movement, brain activity at the ipsilesional motor cortex still shows enough intention-related activity to decode different movement intentions with sufficient accuracy.

KW - electrocorticography (ECOG)

KW - stroke, brain-computer interface (BCI)

UR - http://www.scopus.com/inward/record.url?scp=84913593905&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84913593905&partnerID=8YFLogxK

U2 - 10.1088/1741-2560/11/6/066008

DO - 10.1088/1741-2560/11/6/066008

M3 - Article

VL - 11

JO - Journal of Neural Engineering

JF - Journal of Neural Engineering

SN - 1741-2560

IS - 6

M1 - 066008

ER -