Decoding trajectories of imagined hand movement using electrocorticograms for brain-machine interface

Abstract

Reaching hand movement is an important motor skill investigated in brain-computer interface (BCI). Among the various components of movement analyzed is the hand's trajectory, which describes the hand's continuous position in three-dimensional space. While many studies have investigated the decoding of real movements and the possibility of reconstructing real hand movement trajectories from neural signals, fewer studies have attempted to decode the trajectory of imagined hand movement. In order to develop BCI systems for patients with motor dysfunction, systems need to achieve movement-free control of external devices, and this may only be possible through successful decoding of purely imagined hand movement. To make a thorough investigation on this issue, we analyzed electrocorticograms (ECoG) of eighteen epilepsy patients who performed imaginations of hand movement. We tested two experimental paradigms to induce imaginations of reach-and-grasp action and evaluated the performances of decoding models on their ability to make continuous predictions on the trajectory of imagined hand movement.