Comparison of spatial filters and features for the detection and classification of movement-related cortical potentials in healthy individuals and stroke patients

OBJECTIVE The possibility of detecting movement-related cortical potentials (MRCPs) at the single trial level has been explored for closing the motor control loop with brain-computer interfaces (BCIs) for neurorehabilitation. A distinct feature of MRCPs is that the movement kinetic information is encoded in the brain potential prior to the onset of the movement, which makes it possible to timely drive external devices to provide sensory feedback according to the efferent activity from the brain. The aim of this study was to compare methods for the detection (different spatial filters) and classification (features extracted from various domains) of MRCPs from continuous electroencephalography recordings from executed and imagined movements from healthy subjects (n = 24) and attempted movements from stroke patients (n = 6) to optimize the performance of MRCP-based BCIs for neurorehabilitation. APPROACH The MRCPs from four cue-based tasks were detected with a template matching approach and a set of spatial filters, and classified with a linear support vector machine using the combination of temporal, spectral, time-scale, or entropy-based features. MAIN RESULTS The best spatial filter (large Laplacian spatial filter (LLSF)) resulted in a true positive rate of 82 ± 9%, 78 ± 12% and 72 ± 9% (with detections occurring ∼ 200 ms before the onset of the movement) for executed, imagined and attempted movements (stroke patients). The best feature combination (temporal and spectral) led to pairwise classification of 73 ± 9%, 64 ± 10% and 80 ± 12%. When the detection was combined with classification, 60 ± 10%, 49 ± 10% and 58 ± 10% of the movements were both correctly detected and classified for executed, imagined and attempted movements. A similar performance for detection and classification was obtained with optimized spatial filtering. SIGNIFICANCE A simple setup with an LLSF is useful for detecting cued movements while the combination of features from the time and frequency domain can optimize the decoding of kinetic information from MRCPs; this may be used in neuromodulatory BCIs.

[1]  W. Walter,et al.  Contingent Negative Variation : An Electric Sign of Sensori-Motor Association and Expectancy in the Human Brain , 1964, Nature.

[2]  G. Ouyang,et al.  Predictability analysis of absence seizures with permutation entropy , 2007, Epilepsy Research.

[3]  Moritz Grosse-Wentrup,et al.  Using brain–computer interfaces to induce neural plasticity and restore function , 2011, Journal of neural engineering.

[4]  S M Pincus,et al.  Approximate entropy as a measure of system complexity. , 1991, Proceedings of the National Academy of Sciences of the United States of America.

[5]  Dario Farina,et al.  Detection of movement-related cortical potentials based on subject-independent training , 2013, Medical & Biological Engineering & Computing.

[6]  J. Colebatch,et al.  Movement-related potentials associated with self-paced, cued and imagined arm movements , 2002, Experimental Brain Research.

[7]  Marie-Françoise Lucas,et al.  Identification of task parameters from movement-related cortical potentials , 2009, Medical & Biological Engineering & Computing.

[8]  Dario Farina,et al.  Offline Identification of Imagined Speed of Wrist Movements in Paralyzed ALS Patients from Single-Trial EEG , 2009, Front. Neuropro..

[9]  Motoaki Kawanabe,et al.  A Maxmin Approach to Optimize Spatial Filters for EEG Single-Trial Classification , 2009, IWANN.

[10]  Yunfa Fu,et al.  Reactive Rhythm Activities and Offline Classification of Imagined Speeds of Finger Movements , 2011, 2011 5th International Conference on Bioinformatics and Biomedical Engineering.

[11]  C. Tsai,et al.  Movement related cortical potentials of cued versus self‐initiated movements: Double dissociated modulation by dorsal premotor cortex versus supplementary motor area rTMS , 2012, Human brain mapping.

[12]  Mads Jochumsen,et al.  Detection and classification of movement-related cortical potentials associated with task force and speed , 2013, Journal of neural engineering.

[13]  Marie-Françoise Lucas,et al.  Optimization of wavelets for classification of movement-related cortical potentials generated by variation of force-related parameters , 2007, Journal of Neuroscience Methods.

[14]  Peter Feys,et al.  Facilitation of motor imagery through movement-related cueing , 2009, Brain Research.

[15]  B. Pompe,et al.  Permutation entropy: a natural complexity measure for time series. , 2002, Physical review letters.

[16]  Ning Jiang,et al.  Peripheral Electrical Stimulation Triggered by Self-Paced Detection of Motor Intention Enhances Motor Evoked Potentials , 2012, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[17]  J R Wolpaw,et al.  Spatial filter selection for EEG-based communication. , 1997, Electroencephalography and clinical neurophysiology.

[18]  J. Wolpaw,et al.  Brain–computer interfaces in neurological rehabilitation , 2008, The Lancet Neurology.

[19]  Michael Voigt,et al.  Movement-related parameters modulate cortical activity during imaginary isometric plantar-flexions , 2006, Experimental Brain Research.

[20]  Guang H. Yue,et al.  Relationship between motor activity-related cortical potential and voluntary muscle activation , 2000, Experimental Brain Research.

[21]  H. Kornhuber,et al.  Hirnpotentialänderungen bei Willkürbewegungen und passiven Bewegungen des Menschen: Bereitschaftspotential und reafferente Potentiale , 1965, Pflüger's Archiv für die gesamte Physiologie des Menschen und der Tiere.

[22]  Dario Farina,et al.  Classifying speed and force from movement intentions using entropy and a support vector machine , 2013 .

[23]  José Luis Pons Rovira,et al.  A Closed-Loop Brain–Computer Interface Triggering an Active Ankle–Foot Orthosis for Inducing Cortical Neural Plasticity , 2014, IEEE Transactions on Biomedical Engineering.

[24]  M. Hallett,et al.  Modulation of muscle responses evoked by transcranial magnetic stimulation during the acquisition of new fine motor skills. , 1995, Journal of neurophysiology.

[25]  Dario Farina,et al.  Single-trial discrimination of type and speed of wrist movements from EEG recordings , 2009, Clinical Neurophysiology.

[26]  M. Hallett,et al.  What is the Bereitschaftspotential? , 2006, Clinical Neurophysiology.

[27]  J. Richman,et al.  Physiological time-series analysis using approximate entropy and sample entropy. , 2000, American journal of physiology. Heart and circulatory physiology.

[28]  Hongyi Li,et al.  Time Domain Features for Relationship between Speed and Slow Potentials Activity during Periodic Movement and Motor Imagery at Fast and Slow for BCRI , 2011 .

[29]  D. Farina,et al.  Detection of movement intention from single-trial movement-related cortical potentials , 2011, Journal of neural engineering.

[30]  Yunfa Fu,et al.  Event-related perturbation in spectral power and in potentials during periodic fast and slow motor imagination for brain-controlled robots interface , 2010, 2010 IEEE International Conference on Robotics and Biomimetics.

[31]  Winnie Jensen,et al.  Estimation of Grasping Force from Features of Intramuscular EMG Signals with Mirrored Bilateral Training , 2011, Annals of Biomedical Engineering.

[32]  J. Krakauer Motor learning: its relevance to stroke recovery and neurorehabilitation. , 2006, Current opinion in neurology.

[33]  Michael Voigt,et al.  Relationship between plantar-flexor torque generation and the magnitude of the movement-related potentials , 2004, Experimental Brain Research.

[34]  Ning Jiang,et al.  Enhanced Low-Latency Detection of Motor Intention From EEG for Closed-Loop Brain-Computer Interface Applications , 2014, IEEE Transactions on Biomedical Engineering.

[35]  M. Hallett,et al.  Prediction of human voluntary movement before it occurs , 2011, Clinical Neurophysiology.

[36]  Clemens Brunner,et al.  Better than random? A closer look on BCI results , 2008 .

[37]  Dario Farina,et al.  Movement-Related Cortical Potentials Allow Discrimination of Rate of Torque Development in Imaginary Isometric Plantar Flexion , 2008, IEEE Transactions on Biomedical Engineering.

[38]  Byung Chun Park,et al.  Carousel system performance , 2003, Journal of Applied Probability.

[39]  J. Millán,et al.  Detection of self-paced reaching movement intention from EEG signals , 2012, Front. Neuroeng..

[40]  G. Pfurtscheller,et al.  Brain-Computer Interfaces for Communication and Control. , 2011, Communications of the ACM.

[41]  D. Farina,et al.  Precise temporal association between cortical potentials evoked by motor imagination and afference induces cortical plasticity , 2012, The Journal of physiology.