BiND: A Neural Discriminator-Decoder for Accurate Bimanual Trajectory Prediction in Brain-Computer Interfaces
This work addresses a critical problem for tetraplegic patients using BCIs by improving bimanual movement decoding, though it is incremental as it builds on existing neural decoding methods.
The paper tackled the challenge of decoding bimanual hand movements from intracortical recordings in brain-computer interfaces by introducing BiND, a two-stage model that achieved a mean R² of 0.76 for unimanual and 0.69 for bimanual trajectory prediction, surpassing the next-best model by 2% in both tasks.
Decoding bimanual hand movements from intracortical recordings remains a critical challenge for brain-computer interfaces (BCIs), due to overlapping neural representations and nonlinear interlimb interactions. We introduce BiND (Bimanual Neural Discriminator-Decoder), a two-stage model that first classifies motion type (unimanual left, unimanual right, or bimanual) and then uses specialized GRU-based decoders, augmented with a trial-relative time index, to predict continuous 2D hand velocities. We benchmark BiND against six state-of-the-art models (SVR, XGBoost, FNN, CNN, Transformer, GRU) on a publicly available 13-session intracortical dataset from a tetraplegic patient. BiND achieves a mean $R^2$ of 0.76 ($\pm$0.01) for unimanual and 0.69 ($\pm$0.03) for bimanual trajectory prediction, surpassing the next-best model (GRU) by 2% in both tasks. It also demonstrates greater robustness to session variability than all other benchmarked models, with accuracy improvements of up to 4% compared to GRU in cross-session analyses. This highlights the effectiveness of task-aware discrimination and temporal modeling in enhancing bimanual decoding.