Decoding two-dimensional movement trajectories using electrocorticographic signals in humans

Abstract

Signals from the brain could provide a non-muscular communication and control system, a brain-computer interface (BCI), for people who are severely paralyzed. A common BCI research strategy begins by decoding kinematic parameters from brain signals recorded during actual arm movement. It has been assumed that these parameters can be derived accurately only from signals recorded by intracortical microelectrodes, but the long-term stability of such electrodes is uncertain. The present study disproves this widespread assumption by showing in humans that kinematic parameters can also be decoded from signals recorded by subdural electrodes on the cortical surface (ECoG) with an accuracy comparable to that achieved in monkey studies using intracortical microelectrodes. A new ECoG feature labeled the local motor potential (LMP) provided the most information about movement. Furthermore, features displayed cosine tuning that has previously been described only for signals recorded within the brain. These results suggest that ECoG could be a more stable and less invasive alternative to intracortical electrodes for BCI systems, and could also prove useful in studies of motor function.

Decoding finger movements from ECoG signals using Empirical Mode Decomposition

“…The general-purpose BCI system BCI2000 provided visual stimuli to the patient, acquired brain signals from the Synamps2 system, and also recorded the flexion of individual fingers (on the hand contralateral to the implanted grid) using a data glove (Fifth Dimension Technologies, Irvine, CA) [6]. BCI2000 stored the brain signals, the timing of stimulus presentation, and the flexion of each of the fingers in a data file.…”

“…Data files were converted to MATLAB format for this competition. The subjects were cued to move a particular finger by displaying the corresponding word (e.g., "thumb") on a computer monitor placed at the bedside [6]. Each cue lasted two seconds and was followed by a two-second rest period with a blank screen.…”

“…The idea of linking the human brain to a machine and transforming the pure thinking power into mechanical or virtual actions attracted the attention of several research groups worldwide afterwards [3 , 6, 8]. The authors in [6] have successfully demonstrated a brain computer interface that uses an electrode implanted into the motor cortex of the brain. In [7] authors describe the early stage development and initial human application of neural interface systems (NISs) for paralyzed humans based on an intra-cortical microelectrode sensor that derives control signals from the motor cortex.…”

“…For the fourth round of the BCI Competition, new challenging problems were introduced which are highly relevant for practical BCI. Dataset 4 was recorded with exactly the paradigm found in [6] from band-specific ECoG and pair-wise feature selection in combination with linear regression with the performance of 0.46 [11]. The performance measure is defined by the correlation coefficient r between the actual and the predicted finger flexions, averaged across all subjects and fingers (except for finger 4).…”

Brain-Computer Interfaces in Medicine

“…Gamma activity is important because it exhibits very precise functional localization; is highly correlated with specific aspects of motor, language, and cognitive function; and is linked to the firing rates of individual neurons and to blood-oxygen level-dependent signals detected by fMRI. [74][75][76][77][78][79] Individual finger, [80][81][82][83] hand, 84,85 and arm 86 movements have been decoded successfully from ECoG. ECoG-based BCIs have controlled 1-or 2-dimensional cursor movements using motor or sensory imagery or working memory (dorsolateral prefrontal cortex).…”