Retrospectively supervised click decoder calibration for self-calibrating point-and-click brain–computer interfaces
Journal of Physiology-Paris · 2016-11 · 110 (4) · 382-391
DOI: 10.1016/j.jphysparis.2017.03.001 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Physiology-Paris, 2016-11. Verfasst von Beata Jarosiewicz und 6 weiteren Autor:innen. Beteiligte Einrichtung: Neuroscience, Brown University, Providence, RI 02912, United States; Center for Neurorestoration and Neurotechnology, Rehabilitation R&D Service, Vet…. Hauptthemen laut MEDLINE: Brain-Computer Interfaces. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIDCD NIH HHS, Office of Research and Development, Rehabilitation R&D Service, Department of Veterans Affairs, NIH: NIDCD.
Abstract (Originalsprache)
Brain-computer interfaces (BCIs) aim to restore independence to people with severe motor disabilities by allowing control of acursor on a computer screen or other effectors with neural activity. However, physiological and/or recording-related nonstationarities in neural signals can limit long-term decoding stability, and it would be tedious for users to pause use of the BCI whenever neural control degrades to perform decoder recalibration routines. We recently demonstrated that a kinematic decoder (i.e. a decoder that controls cursor movement) can be recalibrated using data acquired during practical point-and-click control of the BCI by retrospectively inferring users' intended movement directions based on their subsequent selections. Here, we extend these methods to allow the click decoder to also be recalibrated using data acquired during practical BCI use. We retrospectively labeled neural data patterns as corresponding to "click" during all time bins in which the click log-likelihood (decoded using linear discriminant analysis, or LDA) had been above the click threshold that was used during real-time neural control. We labeled as "non-click" those periods that the kinematic decoder's retrospective target inference (RTI) heuristics determined to be consistent with intended cursor movement. Once these neural activity patterns were labeled, the click decoder was calibrated using standard supervised classifier training methods. Combined with real-time bias correction and baseline firing rate tracking, this set of "retrospectively labeled" decoder calibration methods enabled a BrainGate participant with amyotrophic lateral sclerosis (T9) to type freely across 11 research sessions spanning 29days, maintaining high-performance neural control over cursor movement and click without needing to interrupt virtual keyboard use for explicit calibration tasks. By eliminating the need for tedious calibration tasks with prescribed targets and pre-specified click times, this approach advances the potential clinical utility of intracortical BCIs for individuals with severe motor disability.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Neuroscience, Brown University, Providence, RI 02912, United States; Center for Neurorestoration and Neurotechnology, Rehabilitation R&D Service, Veterans Affairs Medical Center, Providence, RI 02908, United States; Bro…
- Center for Neurorestoration and Neurotechnology, Rehabilitation R&D Service, Veterans Affairs Medical Center, Providence, RI 02908, United States; Brown Institute for Brain Science, Brown University, Providence, RI 0291…
- School of Engineering, Brown University, Providence, RI 02912, United States; Center for Neurorestoration and Neurotechnology, Rehabilitation R&D Service, Veterans Affairs Medical Center, Providence, RI 02908, United St…
- Neurology, Massachusetts General Hospital, Boston, MA 02114, United States.
- Neurology, Massachusetts General Hospital, Boston, MA 02114, United States; Neurology, Harvard Medical School, Boston, MA 02115, United States.
- Neurosurgery, Massachusetts General Hospital, Boston, MA 02114, United States; Neuroscience, Harvard Medical School, Boston, MA 02115, United States.
Förderung
- NIDCD NIH HHS
- Office of Research and Development, Rehabilitation R&D Service, Department of Veterans Affairs
- NIH: NIDCD
- MGH-Deane Institute for Integrated Research on Atrial Fibrillation and Stroke
- Executive Committee on Research
Zitieren
APA
Jarosiewicz, B., Sarma, A. A., Saab, J., Franco, B., Cash, S. S., Eskandar, E. N., & Hochberg, L. R. (2016). Retrospectively supervised click decoder calibration for self-calibrating point-and-click brain–computer interfaces. Journal of Physiology-Paris, 110(4), 382-391. https://doi.org/10.1016/j.jphysparis.2017.03.001
Vancouver
Jarosiewicz B, Sarma AA, Saab J, Franco B, Cash SS, Eskandar EN, et al. Retrospectively supervised click decoder calibration for self-calibrating point-and-click brain–computer interfaces. Journal of Physiology-Paris. 2016;110(4):382-391. doi:10.1016/j.jphysparis.2017.03.001
BibTeX
@article{Jarosiewicz2016,
author = {Jarosiewicz, Beata and Sarma, Anish A and Saab, Jad and Franco, Brian and Cash, Sydney S and Eskandar, Emad N and Hochberg, Leigh R},
title = {Retrospectively supervised click decoder calibration for self-calibrating point-and-click brain–computer interfaces},
journal = {Journal of Physiology-Paris},
year = {2016},
volume = {110},
number = {4},
pages = {382--391},
doi = {10.1016/j.jphysparis.2017.03.001}
}
EUVIMED