Related Experiment Video
Updated: Jun 26, 2026
08:15
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
Published on: March 28, 2025
Decoding hand and cursor kinematics from magnetoencephalographic signals during tool use
Trent J Bradberry1, Jose L Contreras-Vidal, Feng Rong
1Fischell Department of Bioengineering, University of Maryland, College Park, MD 20742, USA. trentb@umd.edu
Summary
This study shows that non-invasive brain signals can decode intended movement, paving the way for advanced prosthetic devices. Researchers decoded hand position and velocity using magnetoencephalography, offering hope for motor-disabled individuals.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Rehabilitation Technology
Background:
- Decoding neural activity is crucial for developing advanced prosthetic limbs.
- Current neuromotor prostheses rely heavily on invasive methods like microelectrode arrays.
- Non-invasive techniques are sought to improve accessibility and reduce risks.
Purpose of the Study:
- To investigate the feasibility of decoding hand kinematics from non-invasive magnetoencephalographic (MEG) signals.
- To assess the accuracy of decoding hand position and velocity during a drawing task.
- To explore the potential of non-invasive neuroimaging for controlling neuromotor prostheses.
Main Methods:
- Participants performed a center-out drawing task in both familiar and novel environments.
- Magnetoencephalography (MEG) was used to record neural activity non-invasively.
- Decoding algorithms were applied to MEG signals to estimate hand position and velocity.
Main Results:
- Successful decoding of hand position and velocity was achieved using non-invasive MEG signals.
- Mean correlation coefficients for decoded kinematics ranged from 0.27-0.61 (horizontal) and 0.06-0.58 (vertical).
- Results demonstrate that non-invasive signals contain significant kinematic information.
Conclusions:
- Non-invasive magnetoencephalography signals hold promise for controlling neuromotor prostheses.
- This approach could lead to more accessible and less invasive brain-computer interfaces for motor rehabilitation.
- Further research can refine decoding algorithms for improved prosthetic control.
