Enhanced Motor Imagery Based Brain- Computer Interface via FES and VR for Lower Limbs

Area of Science:

• Neuroscience
• Rehabilitation Engineering
• Human-Computer Interaction

Background:

• Motor imagery based brain-computer interfaces (MI-BCI) show promise for neurorehabilitation and motor assistance.
• Challenges in performing motor imagery tasks limit the widespread application of current MI-BCI systems.
• Enhancing motor imagery (MI) abilities is crucial for improving BCI performance.

Purpose of the Study:

• To develop and validate an enhanced MI-BCI system integrating functional electrical stimulation (FES) and virtual reality (VR).
• To investigate the potential of FES and VR to reduce the difficulty of MI tasks and boost classification accuracy.
• To improve motor function and assistance for patients through more effective brain-computer interfaces.

Main Methods:

• An enhanced MI-BCI was developed, combining FES for lower limb muscle stimulation with VR for visual guidance.
• FES was applied before motor imagery to enhance muscle contraction experience and attention.
• A first-person perspective virtual reality ball-kicking scenario was designed to aid MI task performance.

Main Results:

• The enhanced MI-BCI system demonstrated significant improvements in classification performance.
• Key metrics including accuracy (ACC), area under the curve (AUC), and F1 score were significantly enhanced.
• Experiments conducted on twelve healthy subjects validated the effectiveness of the proposed MI-BCI approach.

Conclusions:

• The integration of FES and VR offers a promising strategy to overcome limitations in current MI-BCI systems.
• The enhanced MI-BCI significantly improves classification accuracy, paving the way for more effective neurorehabilitation.
• This novel approach holds potential for advancing motor assistance technologies and improving patient outcomes.