Closed-loop control of a neuroprosthetic hand by magnetoencephalographic signals

Ryohei Fukuma, Takufumi Yanagisawa, Shiro Yorifuji, Ryu Kato, Hiroshi Yokoi, Masayuki Hirata, Youichi Saitoh, Haruhiko Kishima, Yukiyasu Kamitani, Toshiki Yoshimine

    • 5 Citations

    Abstract

    Objective: A neuroprosthesis using a brain-machine interface (BMI) is a promising therapeutic option for severely paralyzed patients, but the ability to control it may vary among individual patients and needs to be evaluated before any invasive procedure is undertaken. We have developed a neuroprosthetic hand that can be controlled by magnetoencephalographic (MEG) signals to noninvasively evaluate subjects' ability to control a neuroprosthesis. Method: Six nonparalyzed subjects performed grasping or opening movements of their right hand while the slow components of the MEG signals (SMFs) were recorded in an open-loop condition. The SMFs were used to train two decoders to infer the timing and types of movement by support vector machine and Gaussian process regression. The SMFs were also used to calculate estimated slow cortical potentials (eSCPs) to identify the origin of motor information. Finally, using the trained decoders, the subjects controlled a neuroprosthetic hand in a closed-loop condition. Results: The SMFs in the open-loop condition revealed movement-related cortical field characteristics and successfully inferred the movement type with an accuracy of 75.0 ± 12.9% (mean ± SD). In particular, the eSCPs in the sensorimotor cortex contralateral to the moved hand varied significantly enough among the movement types to be decoded with an accuracy of 76.5 ± 10.6%, which was significantly higher than the accuracy associated with eSCPs in the ipsilateral sensorimotor cortex (58.1 ± 13.7%; p = 0.0072, paired two-tailed Student's t-test). Moreover, another decoder using SMFs successfully inferred when the accuracy was the greatest. Combining these two decoders allowed the neuroprosthetic hand to be controlled in a closed-loop condition. Conclusions: Use of real-time MEG signals was shown to successfully control the neuroprosthetic hand. The developed system may be useful for evaluating movement-related slow cortical potentials of severely paralyzed patients to predict the efficacy of invasive BMI.

    Original languageEnglish
    Article numbere0131547
    JournalPLoS One
    Volume10
    Issue number7
    DOIs
    StatePublished - 2015 Jul 2

    Fingerprint

    Brain-Computer Interfaces
    Sensorimotor Cortex
    Support Vector Machines
    Students

    ASJC Scopus subject areas

    • Agricultural and Biological Sciences(all)
    • Biochemistry, Genetics and Molecular Biology(all)
    • Medicine(all)

    Cite this

    Fukuma, R., Yanagisawa, T., Yorifuji, S., Kato, R., Yokoi, H., Hirata, M., ... Yoshimine, T. (2015). Closed-loop control of a neuroprosthetic hand by magnetoencephalographic signals. PLoS One, 10(7), [e0131547]. DOI: 10.1371/journal.pone.0131547

    Closed-loop control of a neuroprosthetic hand by magnetoencephalographic signals. / Fukuma, Ryohei; Yanagisawa, Takufumi; Yorifuji, Shiro; Kato, Ryu; Yokoi, Hiroshi; Hirata, Masayuki; Saitoh, Youichi; Kishima, Haruhiko; Kamitani, Yukiyasu; Yoshimine, Toshiki.

    In: PLoS One, Vol. 10, No. 7, e0131547, 02.07.2015.

    Research output: Contribution to journalArticle

    Fukuma, R, Yanagisawa, T, Yorifuji, S, Kato, R, Yokoi, H, Hirata, M, Saitoh, Y, Kishima, H, Kamitani, Y & Yoshimine, T 2015, 'Closed-loop control of a neuroprosthetic hand by magnetoencephalographic signals' PLoS One, vol 10, no. 7, e0131547. DOI: 10.1371/journal.pone.0131547
    Fukuma R, Yanagisawa T, Yorifuji S, Kato R, Yokoi H, Hirata M et al. Closed-loop control of a neuroprosthetic hand by magnetoencephalographic signals. PLoS One. 2015 Jul 2;10(7). e0131547. Available from, DOI: 10.1371/journal.pone.0131547

    Fukuma, Ryohei; Yanagisawa, Takufumi; Yorifuji, Shiro; Kato, Ryu; Yokoi, Hiroshi; Hirata, Masayuki; Saitoh, Youichi; Kishima, Haruhiko; Kamitani, Yukiyasu; Yoshimine, Toshiki / Closed-loop control of a neuroprosthetic hand by magnetoencephalographic signals.

    In: PLoS One, Vol. 10, No. 7, e0131547, 02.07.2015.

    Research output: Contribution to journalArticle

    @article{8d8b343a2041490eae807f187bb14051,
    title = "Closed-loop control of a neuroprosthetic hand by magnetoencephalographic signals",
    author = "Ryohei Fukuma and Takufumi Yanagisawa and Shiro Yorifuji and Ryu Kato and Hiroshi Yokoi and Masayuki Hirata and Youichi Saitoh and Haruhiko Kishima and Yukiyasu Kamitani and Toshiki Yoshimine",
    year = "2015",
    month = "7",
    doi = "10.1371/journal.pone.0131547",
    volume = "10",
    journal = "PLoS One",
    issn = "1932-6203",
    publisher = "Public Library of Science",
    number = "7",

    }

    TY - JOUR

    T1 - Closed-loop control of a neuroprosthetic hand by magnetoencephalographic signals

    AU - Fukuma,Ryohei

    AU - Yanagisawa,Takufumi

    AU - Yorifuji,Shiro

    AU - Kato,Ryu

    AU - Yokoi,Hiroshi

    AU - Hirata,Masayuki

    AU - Saitoh,Youichi

    AU - Kishima,Haruhiko

    AU - Kamitani,Yukiyasu

    AU - Yoshimine,Toshiki

    PY - 2015/7/2

    Y1 - 2015/7/2

    N2 - Objective: A neuroprosthesis using a brain-machine interface (BMI) is a promising therapeutic option for severely paralyzed patients, but the ability to control it may vary among individual patients and needs to be evaluated before any invasive procedure is undertaken. We have developed a neuroprosthetic hand that can be controlled by magnetoencephalographic (MEG) signals to noninvasively evaluate subjects' ability to control a neuroprosthesis. Method: Six nonparalyzed subjects performed grasping or opening movements of their right hand while the slow components of the MEG signals (SMFs) were recorded in an open-loop condition. The SMFs were used to train two decoders to infer the timing and types of movement by support vector machine and Gaussian process regression. The SMFs were also used to calculate estimated slow cortical potentials (eSCPs) to identify the origin of motor information. Finally, using the trained decoders, the subjects controlled a neuroprosthetic hand in a closed-loop condition. Results: The SMFs in the open-loop condition revealed movement-related cortical field characteristics and successfully inferred the movement type with an accuracy of 75.0 ± 12.9% (mean ± SD). In particular, the eSCPs in the sensorimotor cortex contralateral to the moved hand varied significantly enough among the movement types to be decoded with an accuracy of 76.5 ± 10.6%, which was significantly higher than the accuracy associated with eSCPs in the ipsilateral sensorimotor cortex (58.1 ± 13.7%; p = 0.0072, paired two-tailed Student's t-test). Moreover, another decoder using SMFs successfully inferred when the accuracy was the greatest. Combining these two decoders allowed the neuroprosthetic hand to be controlled in a closed-loop condition. Conclusions: Use of real-time MEG signals was shown to successfully control the neuroprosthetic hand. The developed system may be useful for evaluating movement-related slow cortical potentials of severely paralyzed patients to predict the efficacy of invasive BMI.

    AB - Objective: A neuroprosthesis using a brain-machine interface (BMI) is a promising therapeutic option for severely paralyzed patients, but the ability to control it may vary among individual patients and needs to be evaluated before any invasive procedure is undertaken. We have developed a neuroprosthetic hand that can be controlled by magnetoencephalographic (MEG) signals to noninvasively evaluate subjects' ability to control a neuroprosthesis. Method: Six nonparalyzed subjects performed grasping or opening movements of their right hand while the slow components of the MEG signals (SMFs) were recorded in an open-loop condition. The SMFs were used to train two decoders to infer the timing and types of movement by support vector machine and Gaussian process regression. The SMFs were also used to calculate estimated slow cortical potentials (eSCPs) to identify the origin of motor information. Finally, using the trained decoders, the subjects controlled a neuroprosthetic hand in a closed-loop condition. Results: The SMFs in the open-loop condition revealed movement-related cortical field characteristics and successfully inferred the movement type with an accuracy of 75.0 ± 12.9% (mean ± SD). In particular, the eSCPs in the sensorimotor cortex contralateral to the moved hand varied significantly enough among the movement types to be decoded with an accuracy of 76.5 ± 10.6%, which was significantly higher than the accuracy associated with eSCPs in the ipsilateral sensorimotor cortex (58.1 ± 13.7%; p = 0.0072, paired two-tailed Student's t-test). Moreover, another decoder using SMFs successfully inferred when the accuracy was the greatest. Combining these two decoders allowed the neuroprosthetic hand to be controlled in a closed-loop condition. Conclusions: Use of real-time MEG signals was shown to successfully control the neuroprosthetic hand. The developed system may be useful for evaluating movement-related slow cortical potentials of severely paralyzed patients to predict the efficacy of invasive BMI.

    UR - http://www.scopus.com/inward/record.url?scp=84940038072&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84940038072&partnerID=8YFLogxK

    U2 - 10.1371/journal.pone.0131547

    DO - 10.1371/journal.pone.0131547

    M3 - Article

    VL - 10

    JO - PLoS One

    T2 - PLoS One

    JF - PLoS One

    SN - 1932-6203

    IS - 7

    M1 - e0131547

    ER -