Embodied Virtual Reality Feedback Reshapes Neural Representations to Support Continuous Three-Dimensional Motor Imagery Decoding

2026-05-28

AI Summary

This study addresses the unclear impact of feedback modality and longitudinal training on neural representations and motor imagery decoding performance in continuous brain–computer interfaces. Through ten longitudinal sessions, it systematically compares embodied virtual reality (VR) feedback against conventional screen-based feedback during real-time control of a three-dimensional virtual limb. Employing a CNN-LSTM decoder, linear mixed-effects modeling, and EEG-based neurophysiological analyses, the work evaluates decoding efficacy across three training strategies. Results demonstrate for the first time that embodied VR feedback fosters more decodable and generalizable neural representations, yielding sustained performance improvements without model retraining. The VR condition achieved a significantly higher decoding correlation coefficient (r = 0.762) than screen feedback and enhanced event-related desynchronization over sensorimotor–parietal regions alongside broadband activation in the anterior insula.

Abstract

Continuous brain-computer interfaces (BCIs) that decode motion trajectories from imagined movement offer intuitive motor control, yet how feedback modality and longitudinal training shape neural representations and decoding performance remains poorly understood. We present the first systematic investigation of embodied virtual reality (VR) feedback during real-time 3D virtual limb control driven by motor imagery, across ten longitudinal sessions in ten participants. Performance was evaluated using three strategies: actual online performance (Fixed Decoder Generalisation, FDG), periodic retraining (Sequential Adaptive Training, SAT), and within-session upper-bound estimation (Within-Session Reconstruction, WSR). A CNN-LSTM decoder achieved within-session imagined movement correlations of r = 0.762 under VR and r = 0.672 under screen feedback. VR significantly outperformed screen feedback across all strategies and movement dimensions (improvements of 8.9-13.0%, all p <= 0.002, d = 1.42-2.05). This advantage persisted under fixed decoders without retraining, demonstrating that embodied VR feedback elicits inherently more decodable and generalisable neural representations. Linear mixed-effects modelling confirmed robust main effects of feedback modality and movement axis with no interaction. Neurophysiologically, VR produced stronger sensorimotor-parietal desynchronisation and enhanced motor-frontal functional connectivity, with pervasive anterior insula engagement across all frequency bands and increased superior parietal lobule coupling, paralleling patterns associated with real movement execution. These findings establish embodied spatial feedback as a key design principle for next-generation continuous BCIs targeting intuitive motor control and neurorehabilitation.

Problem

• continuous brain-computer interfaces
• motor imagery decoding
• feedback modality
• neural representations
• embodied virtual reality

Innovation

• embodied virtual reality
• continuous BCI
• motor imagery decoding
• neural representation
• CNN-LSTM