Connectivity Analysis as a Novel Approach to Motor Decoding for Prosthesis Control

Abstract

The use of neural signals for prosthesis control is an emerging frontier of research to restore lost function to amputees and the paralyzed. Electrocorticography (ECoG) brain-machine interfaces (BMI) are an alternative to EEG and neural spiking and local field potential BMI approaches. Conventional ECoG BMIs rely on spectral analysis at specific electrode sites to extract signals for controlling prostheses. We compare traditional features with information about the connectivity of an ECoG electrode network. We use time-varying dynamic Bayesian networks (TV-DBN) to determine connectivity between ECoG channels in humans during a motor task. We show that, on average, TV-DBN connectivity decreases from baseline preceding movement and then becomes negative, indicating an alteration in the phase relationship between electrode pairs. In some subjects, this change occurs preceding and during movement, before changes in low or high frequency power. We tested TV-DBN output in a hand kinematic decoder and obtained an average correlation coefficient (r2) between actual and predicted joint angle of 0.40, and as high as 0.66 in one subject. This result compares favorably with spectral feature decoders, for which the average correlation coefficient was 0.13. This work introduces a new feature set based on connectivity and demonstrates its potential to improve ECoG BMI accuracy.

Discriminant brain connectivity patterns of performance monitoring at average and single-trial levels

“…Connectivity-based features have also been used for continuous decoding of arm trajectories from electrocorticography signals showing increased estimation accuracy with respect to spectral features (Benz et al, 2012). However, most of these classification or regression models are mainly data driven, extracting features through optimization algorithms, without providing an explicit interpretation about the selected features.…”

Joint Spatial-Spectral Feature Space Clustering for Speech Activity Detection from ECoG Signals

“…Over the past two decades, rapid advances in electrophysiological recording technology [1]-[2] and novel signal processing techniques have led to the dawn of brain machine interfaces (BMIs) for neurorestoration [3]-[5]. In addition to the rehabilitation of motor deficits [6]-[8], BMI systems could permit silent communication with disabled patients [9]-[27].…”

“…Moreover, we propose a data-driven unsupervised scheme for clustering the feature space to sub-spaces. With this approach we aim to extract the most discriminative features, rather than setting a threshold as in previous studies [3][4][9][26]. Furthermore, the speech activity is jointly studied in the spatial and spectral domains to reveal how the speech activity is organized within different cortical areas and frequency bands.…”

Real-time voice activity detection for ECoG-based speech brain machine interfaces

“…Several studies have made advances toward the development of effective motor [1]- [4] and speech prostheses [5]- [8] based on biological signals. These speech prostheses aim to completely replace the vocal mechanism of a locked-in individual [9] and enable the articulation of words directly or indirectly from neural activity.…”