Hand posture classification using electrocorticography signals in the gamma band over human sensorimotor brain areas

被引:97
作者
Chestek, Cynthia A. [1 ]
Gilja, Vikash [1 ]
Blabe, Christine H. [1 ]
Foster, Brett L. [2 ]
Shenoy, Krishna V. [3 ]
Parvizi, Josef [2 ]
Henderson, Jaimie M. [4 ]
机构
[1] Stanford Univ, James H Clark Ctr, Stanford Inst Neuroinnovat & Translat Neurosci, Stanford, CA 94305 USA
[2] Stanford Comprehens Epilepsy Ctr, Dept Neurol & Neurol Sci, Stanford, CA 94305 USA
[3] Stanford Univ, Dept Elect Engn, James H Clark Ctr, Stanford, CA 94305 USA
[4] Stanford Univ, Sch Med, Dept Neurosurg, Stanford, CA 94305 USA
关键词
COMPUTER-INTERFACE; FINGER MOVEMENTS; MOTOR; CORTEX; REPRESENTATION; PERFORMANCE; SINGLE; ROBOT;
D O I
10.1088/1741-2560/10/2/026002
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Objective. Brain-machine interface systems translate recorded neural signals into command signals for assistive technology. In individuals with upper limb amputation or cervical spinal cord injury, the restoration of a useful hand grasp could significantly improve daily function. We sought to determine if electrocorticographic (ECoG) signals contain sufficient information to select among multiple hand postures for a prosthetic hand, orthotic, or functional electrical stimulation system. Approach. We recorded ECoG signals from subdural macro-and microelectrodes implanted in motor areas of three participants who were undergoing inpatient monitoring for diagnosis and treatment of intractable epilepsy. Participants performed five distinct isometric hand postures, as well as four distinct finger movements. Several control experiments were attempted in order to remove sensory information from the classification results. Online experiments were performed with two participants. Main results. Classification rates were 68%, 84% and 81% for correct identification of 5 isometric hand postures offline. Using 3 potential controls for removing sensory signals, error rates were approximately doubled on average (2.1x). A similar increase in errors (2.6x) was noted when the participant was asked to make simultaneous wrist movements along with the hand postures. In online experiments, fist versus rest was successfully classified on 97% of trials; the classification output drove a prosthetic hand. Online classification performance for a larger number of hand postures remained above chance, but substantially below offline performance. In addition, the long integration windows used would preclude the use of decoded signals for control of a BCI system. Significance. These results suggest that ECoG is a plausible source of command signals for prosthetic grasp selection. Overall, avenues remain for improvement through better electrode designs and placement, better participant training, and characterization of non-stationarities such that ECoG could be a viable signal source for grasp control for amputees or individuals with paralysis.
引用
收藏
页数:11
相关论文
共 48 条
[1]  
Acharya S, 2010, J NEURAL ENG, V7, DOI [10.1088/1741-2560/7/4/046002, 10.2202/1553-3840.1324]
[2]   Asynchronous decoding of dexterous finger movements using M1 neurons [J].
Aggarwal, Vikram ;
Acharya, Soumyadipta ;
Tenore, Francesco ;
Shin, Hyun-Chool ;
Etienne-Cummings, Ralph ;
Schieber, Marc H. ;
Thakor, Nitish V. .
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2008, 16 (01) :3-14
[3]   Muscle synergies as a predictive framework for the EMG patterns of new hand postures [J].
Ajiboye, A. B. ;
Weir, R. F. .
JOURNAL OF NEURAL ENGINEERING, 2009, 6 (03) :036004
[4]   Control of a humanoid robot by a noninvasive brain-computer interface in humans [J].
Bell, Christian J. ;
Shenoy, Pradeep ;
Chalodhorn, Rawichote ;
Rao, Rajesh P. N. .
JOURNAL OF NEURAL ENGINEERING, 2008, 5 (02) :214-220
[5]   Decoding M1 neurons during multiple finger movements [J].
Ben Hamed, S. ;
Schieber, M. H. ;
Pouget, A. .
JOURNAL OF NEUROPHYSIOLOGY, 2007, 98 (01) :327-333
[6]   Robust, long-term control of an electrocorticographic brain-computer interface with fixed parameters [J].
Blakely, Tim ;
Miller, Kai J. ;
Zanos, Stavros P. ;
Rao, Rajesh P. N. ;
Ojemann, Jeffrey G. .
NEUROSURGICAL FOCUS, 2009, 27 (01)
[7]   The origin of extracellular fields and currents - EEG, ECoG, LFP and spikes [J].
Buzsaki, Gyoergy ;
Anastassiou, Costas A. ;
Koch, Christof .
NATURE REVIEWS NEUROSCIENCE, 2012, 13 (06) :407-420
[8]  
Chao Zenas C, 2010, Front Neuroeng, V3, P3, DOI 10.3389/fneng.2010.00003
[9]  
Christopher Reeve Spinal Cord Injury and Paralysis Foundation, 2009, ON DEGR SEP PAR SPIN
[10]   A supervised feature-projection-based real-time EMG pattern recognition for multifunction myoelectric hand control [J].
Chu, Jun-Uk ;
Moon, Inhyuk ;
Lee, Yun-Jung ;
Kim, Shin-Ki ;
Mun, Mu-Seong .
IEEE-ASME TRANSACTIONS ON MECHATRONICS, 2007, 12 (03) :282-290