CoChat

Classification of Articulator Movements and Movement Direction from Sensorimotor Cortex Activity

Open access

The DOI matches its Crossref record; 50 of the 51 references it cites were found in a registry or an index.

Abstract

For people suffering from severe paralysis, communication can be difficult or nearly impossible. Technology systems called brain-computer interfaces (BCIs) are being developed to assist these people with communication by using their brain activity to control a computer without any muscle activity. To benefit the development of BCIs that employ neural activity related to speech, we investigated if neural activity patterns related to different articulator movements can be distinguished from each other. We recorded with electrocorticography (ECoG), the neural activity related to different articulator movements in 4 epilepsy patients and classified which articulator participants moved based on the sensorimotor cortex activity patterns. The same was done for different movement directions of a single articulator, the tongue. In both experiments highly accurate classification was obtained, on average 92% for different articulators and 85% for different tongue directions. Furthermore, the data show that only a small part of the sensorimotor cortex is needed for classification (ca. 1 cm 2 ). We show that recordings from small parts of the sensorimotor cortex contain information about different articulator movements which might be used for BCI control. Our results are of interest for BCI systems that aim to decode neural activity related to (actual or attempted) movements from a contained cortical area.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-019-50834-5

Cites

50 of 50 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Classification accuracies. The mean classification accuracies (over cross-validation iterations) and standard deviations are shown for each subject (A–D, in different colors), per run. Classification was based on all electrodes that showed a significant relation to the task. Runs are indicated on the x-axis and the classification accuracy is indicated on the y-axis. In the upper panel, the spatial classification accuracies are shown. In the lower panel, the accuracies for spatio-temporal classification are given. The red line indicates the chance level of 25%. Note that not all subjects performed two runs and subject (C) only performed the articulator movement task.
Figure 1 Classification accuracies. The mean classification accuracies (over cross-validation iterations) and standard deviations are shown for each subject (A–D, in different colors), per run. Classification was based on all electrodes that showed a significant relation to the task. Runs are indicated on the x-axis and the classification accuracy is indicated on the y-axis. In the upper panel, the spatial classification accuracies are shown. In the lower panel, the accuracies for spatio-temporal classification are given. The red line indicates the chance level of 25%. Note that not all subjects performed two runs and subject (C) only performed the articulator movement task.CC BY · PubMed Central
Figure 2 Most informative electrodes. The most informative electrodes are shown for each subject (A–D) and for each task. Informative electrodes were determined by a random search procedure. Colors indicate the normalized average accuracy score of this procedure. The warmer the color the higher the classification was on average if that electrode was included. Results are based on the first run of each task, per participant. See Supplementary Material for the data of the other runs.
Figure 2 Most informative electrodes. The most informative electrodes are shown for each subject (A–D) and for each task. Informative electrodes were determined by a random search procedure. Colors indicate the normalized average accuracy score of this procedure. The warmer the color the higher the classification was on average if that electrode was included. Results are based on the first run of each task, per participant. See Supplementary Material for the data of the other runs.CC BY · PubMed Central
Figure 3 Size of cortical area required for accurate classification. The maximum classification accuracy (y-axis) is shown for different sizes of cortical surface area (x-axis), for each subject. This was calculated by using a search light approach in which we increased the sampled area of the search light and for each size computed the highest accuracy.
Figure 3 Size of cortical area required for accurate classification. The maximum classification accuracy (y-axis) is shown for different sizes of cortical surface area (x-axis), for each subject. This was calculated by using a search light approach in which we increased the sampled area of the search light and for each size computed the highest accuracy.CC BY · PubMed Central
Figure 4 Search light results. The most informative areas are shown for each subject (A–D) and for each task. Informative areas were determined by a search light procedure (a 3 × 3 grid size was used for the current figure). For this plot, we chose a search light of three electrode rows and columns, corresponding to approximately 12 × 12 mm for subject (A,B) and 9 × 9 mm for subjects (C,D). Colors indicate the average accuracy score of this procedure. The warmer the color the higher the classification was on average. Results are based on the first run of each task and participant. See Supplementary Material for the data of the other runs.
Figure 4 Search light results. The most informative areas are shown for each subject (A–D) and for each task. Informative areas were determined by a search light procedure (a 3 × 3 grid size was used for the current figure). For this plot, we chose a search light of three electrode rows and columns, corresponding to approximately 12 × 12 mm for subject (A,B) and 9 × 9 mm for subjects (C,D). Colors indicate the average accuracy score of this procedure. The warmer the color the higher the classification was on average. Results are based on the first run of each task and participant. See Supplementary Material for the data of the other runs.CC BY · PubMed Central
Figure 5 Representations of neural responses during different movements. In the top panels (a,b), the average representation of different articulator and tongue movements is shown on an inflated and normalized brain surface with darker colors indicating the sulcus and lighter colors indicating the surface (for anatomical reference of these matrices see Bruurmijn et al.36,37). Each colored square indicates one electrode. The left side of each plot indicates the precentral gyrus (M1) and the right side the postcentral gyrus (S1), also for subject D in whom the right hemisphere was recorded. The dashed line indicates the central sulcus. Colors indicate for each electrode which movement had the highest r2-value in a winner takes all fashion. For the top panel plots (a,b), electrodes with an r2-value less than 0.2 are not shown as they were not included in the winner-takes-all analysis. The coordinates on the x-axis and y-axis indicate the number of ‘tiles’ in the anterior-posterior and ventral-dorsal direction, respectively. Each tile represents about 1 mm of inflated cortex. In the lower panels (c,d), the average of the r2-values per movement are shown. Results are based on the first run of each participant and task. See Supplementary Fig. S6 for the data per participant for all runs.
Figure 5 Representations of neural responses during different movements. In the top panels (a,b), the average representation of different articulator and tongue movements is shown on an inflated and normalized brain surface with darker colors indicating the sulcus and lighter colors indicating the surface (for anatomical reference of these matrices see Bruurmijn et al.36,37). Each colored square indicates one electrode. The left side of each plot indicates the precentral gyrus (M1) and the right side the postcentral gyrus (S1), also for subject D in whom the right hemisphere was recorded. The dashed line indicates the central sulcus. Colors indicate for each electrode which movement had the highest r2-value in a winner takes all fashion. For the top panel plots (a,b), electrodes with an r2-value less than 0.2 are not shown as they were not included in the winner-takes-all analysis. The coordinates on the x-axis and y-axis indicate the number of ‘tiles’ in the anterior-posterior and ventral-dorsal direction, respectively. Each tile represents about 1 mm of inflated cortex. In the lower panels (c,d), the average of the r2-values per movement are shown. Results are based on the first run of each participant and task. See Supplementary Fig. S6 for the data per participant for all runs.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 50 references

Cited by

See all 26

Metadata

Authors
Salari, E., Freudenburg, Z. V., Branco, M. P., Aarnoutse, E. J., Vansteensel, M. J., & Ramsey, N. F.
Affiliations
University Medical Center Utrecht (NL)
Corresponding author
Ramsey, N. F.
Venue
Scientific Reports
Published
2019-10-02
Volume
9
Issue
1
Pages
14165-14165
ISSN
2045-2322 (ISSN-L)
OpenAlex
W2977914667
Cited by
26
References
51
Citations by year
2026: 2 · 2025: 3 · 2024: 3 · 2023: 4 · 2022: 4 · 2021: 5 · 2020: 5
FWCI
2.04
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
  • Utrecht University Repository (Utrecht University) (submittedVersion, other-oa)
Funders
European Commission (320708)
Topics
  • Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
  • Physical Sciences › Engineering › Biomedical Engineering › Muscle activation and electromyography studies
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Tactile and Sensory Interactions
Keywords
articulator movement, sensorimotor cortex, brain-computer interface, electrocorticography, epilepsy patients, movement classification, severe paralysis, communication aids
MeSH terms
Electrocorticography, Adult, Articulation Disorders, Epilepsy, Female, Humans, Male, Movement, Tongue, Voice, Brain-Computer Interfaces, Sensorimotor Cortex

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Classification of Articulator Movements and Movement Direction from Sensorimotor Cortex Activity. https://app.cochat.ai/papers/10.1038/s41598-019-50834-5
The paper
Salari, E., Freudenburg, Z. V., Branco, M. P., Aarnoutse, E. J., Vansteensel, M. J., & Ramsey, N. F. (2019). Classification of Articulator Movements and Movement Direction from Sensorimotor Cortex Activity. Scientific Reports. https://doi.org/10.1038/s41598-019-50834-5

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.