Detection of Movement Related Cortical Potentials from EEG Using Constrained ICA for Brain-Computer Interface Applications.

Fatemeh Karimi,Dario Farina,Jonathan Kofman,Ning Jiang,Natalie Mrachacz-Kersting

doi:10.3389/fnins.2017.00356

Abstract

The movement related cortical potential (MRCP), a slow cortical potential from the scalp electroencephalogram (EEG), has been used in real-time brain-computer-interface (BCI) systems designed for neurorehabilitation. Detecting MPCPs in real time with high accuracy and low latency is essential in these applications. In this study, we propose a new MRCP detection method based on constrained independent component analysis (cICA). The method was tested for MRCP detection during executed and imagined ankle dorsiflexion of 24 healthy participants, and compared with four commonly used spatial filters for MRCP detection in an offline experiment. The effect of cICA and the compared spatial filters on the morphology of the extracted MRCP was evaluated by two indices quantifying the signal-to-noise ratio and variability of the extracted MRCP. The performance of the filters for detection was then directly compared for accuracy and latency. The latency obtained with cICA (−34 ± 29 ms motor execution (ME) and 28 ± 16 ms for motor imagery (MI) dataset) was significantly smaller than with all other spatial filters. Moreover, cICA resulted in greater true positive rates (87.11 ± 11.73 for ME and 86.66 ± 6.96 for MI dataset) and lower false positive rates (20.69 ± 13.68 for ME and 19.31 ± 12.60 for MI dataset) compared to the other methods. These results confirm the superiority of cICA in MRCP detection with respect to previously proposed EEG filtering approaches.

Highlights

The movement-related cortical potential (MRCP) is a low frequency (0–5 Hz) negative shift in the electroencephalogram (EEG) signal, which has recently been used as an EEG modality for real-time brain computer interface (BCI) applications, in neuromodulation systems (MrachaczKersting et al, 2016)
We have proposed a new spatial filter for MRCP detection
The results indicated that constrained independent component analysis (cICA) did not enhance the extracted MRCP from multi-channel EEG significantly better than several commonly used spatial filters, including Common Spatial Pattern (CSP), Laplacian spatial filter (LAP), and Independent Component Analysis (ICA)

Summary

Introduction

The movement-related cortical potential (MRCP) is a low frequency (0–5 Hz) negative shift in the electroencephalogram (EEG) signal, which has recently been used as an EEG modality for real-time brain computer interface (BCI) applications, in neuromodulation systems (MrachaczKersting et al, 2016). The ability to detect MRCPs with high accuracy and short latency (usually shorter than 300 ms) on a single trial basis is crucial for these applications. Improvement in accuracy and Constrained ICA for Movement Related latency of single-trial MRCP detection is a relevant challenge. The amplitude of the MRCP is typically between 5 and 30 μV and masked by other brain activities (Wright et al, 2011). Extracting a single trial MRCP from an EEG signal with high accuracy and minimal latency in real-time is a challenging task

Results

Discussion

Conclusion