Multiscale decoding for reliable brain-machine interface performance over time

Han Lin Hsieh, Yan T. Wong, Bijan Pesaran, Maryam M. Shanechi

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

4 Citations (Scopus)

Abstract

Recordings from invasive implants can degrade over time, resulting in a loss of spiking activity for some electrodes. For brain-machine interfaces (BMI), such a signal degradation lowers control performance. Achieving reliable performance over time is critical for BMI clinical viability. One approach to improve BMI longevity is to simultaneously use spikes and other recording modalities such as local field potentials (LFP), which are more robust to signal degradation over time. We have developed a multiscale decoder that can simultaneously model the different statistical profiles of multi-scale spike/LFP activity (discrete spikes vs. continuous LFP). This decoder can also run at multiple time-scales (millisecond for spikes vs. tens of milliseconds for LFP). Here, we validate the multiscale decoder for estimating the movement of 7 major upper-arm joint angles in a non-human primate (NHP) during a 3D reach-to-grasp task. The multiscale decoder uses motor cortical spike/LFP recordings as its input. We show that the multiscale decoder can improve decoding accuracy by adding information from LFP to spikes, while running at the fast millisecond time-scale of the spiking activity. Moreover, this improvement is achieved using relatively few LFP channels, demonstrating the robustness of the approach. These results suggest that using multiscale decoders has the potential to improve the reliability and longevity of BMIs.

Original languageEnglish
Title of host publication2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2017)
EditorsEung Je Woo, Yuan-ting Zhang, Thomas Penzel
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages197-200
Number of pages4
ISBN (Electronic)9781509028092
ISBN (Print)9781509028108
DOIs
Publication statusPublished - 13 Sep 2017
EventInternational Conference of the IEEE Engineering in Medicine and Biology Society 2017 - Jeju Island, Korea, Republic of (South)
Duration: 11 Jul 201715 Jul 2017
Conference number: 39th
https://embc.embs.org/2017/

Conference

ConferenceInternational Conference of the IEEE Engineering in Medicine and Biology Society 2017
Abbreviated titleEMBC 2017
CountryKorea, Republic of (South)
CityJeju Island
Period11/07/1715/07/17
Internet address

Cite this

Hsieh, H. L., Wong, Y. T., Pesaran, B., & Shanechi, M. M. (2017). Multiscale decoding for reliable brain-machine interface performance over time. In E. J. Woo, Y. Zhang, & T. Penzel (Eds.), 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2017) (pp. 197-200). [8036796] Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/EMBC.2017.8036796
Hsieh, Han Lin ; Wong, Yan T. ; Pesaran, Bijan ; Shanechi, Maryam M. / Multiscale decoding for reliable brain-machine interface performance over time. 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2017). editor / Eung Je Woo ; Yuan-ting Zhang ; Thomas Penzel. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2017. pp. 197-200
@inproceedings{94a32c27b0de40ff85a6b211200daa0e,
title = "Multiscale decoding for reliable brain-machine interface performance over time",
abstract = "Recordings from invasive implants can degrade over time, resulting in a loss of spiking activity for some electrodes. For brain-machine interfaces (BMI), such a signal degradation lowers control performance. Achieving reliable performance over time is critical for BMI clinical viability. One approach to improve BMI longevity is to simultaneously use spikes and other recording modalities such as local field potentials (LFP), which are more robust to signal degradation over time. We have developed a multiscale decoder that can simultaneously model the different statistical profiles of multi-scale spike/LFP activity (discrete spikes vs. continuous LFP). This decoder can also run at multiple time-scales (millisecond for spikes vs. tens of milliseconds for LFP). Here, we validate the multiscale decoder for estimating the movement of 7 major upper-arm joint angles in a non-human primate (NHP) during a 3D reach-to-grasp task. The multiscale decoder uses motor cortical spike/LFP recordings as its input. We show that the multiscale decoder can improve decoding accuracy by adding information from LFP to spikes, while running at the fast millisecond time-scale of the spiking activity. Moreover, this improvement is achieved using relatively few LFP channels, demonstrating the robustness of the approach. These results suggest that using multiscale decoders has the potential to improve the reliability and longevity of BMIs.",
author = "Hsieh, {Han Lin} and Wong, {Yan T.} and Bijan Pesaran and Shanechi, {Maryam M.}",
year = "2017",
month = "9",
day = "13",
doi = "10.1109/EMBC.2017.8036796",
language = "English",
isbn = "9781509028108",
pages = "197--200",
editor = "Woo, {Eung Je} and Yuan-ting Zhang and Thomas Penzel",
booktitle = "2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2017)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States of America",

}

Hsieh, HL, Wong, YT, Pesaran, B & Shanechi, MM 2017, Multiscale decoding for reliable brain-machine interface performance over time. in EJ Woo, Y Zhang & T Penzel (eds), 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2017)., 8036796, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 197-200, International Conference of the IEEE Engineering in Medicine and Biology Society 2017, Jeju Island, Korea, Republic of (South), 11/07/17. https://doi.org/10.1109/EMBC.2017.8036796

Multiscale decoding for reliable brain-machine interface performance over time. / Hsieh, Han Lin; Wong, Yan T.; Pesaran, Bijan; Shanechi, Maryam M.

2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2017). ed. / Eung Je Woo; Yuan-ting Zhang; Thomas Penzel. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2017. p. 197-200 8036796.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - Multiscale decoding for reliable brain-machine interface performance over time

AU - Hsieh, Han Lin

AU - Wong, Yan T.

AU - Pesaran, Bijan

AU - Shanechi, Maryam M.

PY - 2017/9/13

Y1 - 2017/9/13

N2 - Recordings from invasive implants can degrade over time, resulting in a loss of spiking activity for some electrodes. For brain-machine interfaces (BMI), such a signal degradation lowers control performance. Achieving reliable performance over time is critical for BMI clinical viability. One approach to improve BMI longevity is to simultaneously use spikes and other recording modalities such as local field potentials (LFP), which are more robust to signal degradation over time. We have developed a multiscale decoder that can simultaneously model the different statistical profiles of multi-scale spike/LFP activity (discrete spikes vs. continuous LFP). This decoder can also run at multiple time-scales (millisecond for spikes vs. tens of milliseconds for LFP). Here, we validate the multiscale decoder for estimating the movement of 7 major upper-arm joint angles in a non-human primate (NHP) during a 3D reach-to-grasp task. The multiscale decoder uses motor cortical spike/LFP recordings as its input. We show that the multiscale decoder can improve decoding accuracy by adding information from LFP to spikes, while running at the fast millisecond time-scale of the spiking activity. Moreover, this improvement is achieved using relatively few LFP channels, demonstrating the robustness of the approach. These results suggest that using multiscale decoders has the potential to improve the reliability and longevity of BMIs.

AB - Recordings from invasive implants can degrade over time, resulting in a loss of spiking activity for some electrodes. For brain-machine interfaces (BMI), such a signal degradation lowers control performance. Achieving reliable performance over time is critical for BMI clinical viability. One approach to improve BMI longevity is to simultaneously use spikes and other recording modalities such as local field potentials (LFP), which are more robust to signal degradation over time. We have developed a multiscale decoder that can simultaneously model the different statistical profiles of multi-scale spike/LFP activity (discrete spikes vs. continuous LFP). This decoder can also run at multiple time-scales (millisecond for spikes vs. tens of milliseconds for LFP). Here, we validate the multiscale decoder for estimating the movement of 7 major upper-arm joint angles in a non-human primate (NHP) during a 3D reach-to-grasp task. The multiscale decoder uses motor cortical spike/LFP recordings as its input. We show that the multiscale decoder can improve decoding accuracy by adding information from LFP to spikes, while running at the fast millisecond time-scale of the spiking activity. Moreover, this improvement is achieved using relatively few LFP channels, demonstrating the robustness of the approach. These results suggest that using multiscale decoders has the potential to improve the reliability and longevity of BMIs.

UR - http://www.scopus.com/inward/record.url?scp=85032213821&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2017.8036796

DO - 10.1109/EMBC.2017.8036796

M3 - Conference Paper

SN - 9781509028108

SP - 197

EP - 200

BT - 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2017)

A2 - Woo, Eung Je

A2 - Zhang, Yuan-ting

A2 - Penzel, Thomas

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

ER -

Hsieh HL, Wong YT, Pesaran B, Shanechi MM. Multiscale decoding for reliable brain-machine interface performance over time. In Woo EJ, Zhang Y, Penzel T, editors, 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2017). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2017. p. 197-200. 8036796 https://doi.org/10.1109/EMBC.2017.8036796