Asynchronous Decoding of Dexterous Finger Movements Using M1 Neurons

Abstract

While previous efforts in Brain-Machine Interfaces (BMI) have looked at decoding movement intent or hand and arm trajectory, current neural control strategies have not focused on the decoding of dexterous actions such as finger movements. The present work demonstrates the asynchronous deciphering of the neural coding associated with the movement of individual and combined fingers. Single-unit activities were recorded sequentially from a population of neurons in the M1 hand area of trained rhesus monkeys during flexion and extension movements of each finger and the wrist. Non-linear filters were used to decode both movement intent and movement type from randomly selected neuronal ensembles. Average asynchronous decoding accuracies as high as 99.8% ± 0.1%, 96.2% ± 1.8%, and 90.5% ± 2.1%, were achieved for individuated finger and wrist movements with three monkeys. Average decoding accuracy was still 92.5% ± 1.1% when combined movements of two fingers were included. These results demonstrate that it is possible to asynchronously decode dexterous finger movements from a neuronal ensemble with high accuracy. This is an important step towards the development of a BMI for direct neural control of a state-of-the-art, multi-fingered hand prosthesis.

Decoding grasp movement from monkey premotor cortex for real-time prosthetic hand control

“…In fact, we do not need control every single joint separately, because natural grasp works in a synergic way, which is also the way brain adopted [14,23]. Although studies have decoded categorized grasp types [15][16][17]23], we realized the decoding in real time and asynchronous mode, which is critical in practical applications [22,24]. The present study demonstrated the asynchronously real time grasp type decoding, in which both the onset of movement and movement type were decoded.…”

“…The online control module was integrated into the training system described above, with additional sub-modules including real-time data reading from Cerebus, online decoding, prosthetic hand controller and graphic user interface. Online control of a prosthetic hand required asynchronous classification in real-time without priori knowledge of the movement events, i.e., the decoder not only can predict the right grasp types, but also the timing of grasp [22]. Therefore, we employed a two-stage decoding strategy.…”

“…Recently, there are some reports that can decode a large number of joint kinematics from hand. Aggarwal et al tried to decode the individual and two combined fingers flexion and extension movement from neurons in M1, and got high accuracies [11]. Vargas-Irwin et al demonstrated that the full arm joint kinematics (including arm, wrist and hand) can be reconstructed from local ensembles of M1 [12].…”

“…Vargas-Irwin et al demonstrated that the full arm joint kinematics (including arm, wrist and hand) can be reconstructed from local ensembles of M1 [12]. However, none of them can reconstruct the functional grasp gesture, which is crucial for grasping different objects [11,12]. Alternatively, current studies often resolve the problem by transferring continuous grasp movement into discrete classification.…”

Designing Closed-Loop Brain-Machine Interfaces Using Model Predictive Control

“…In the past, several linear and nonlinear decoders have been developed in BMI studies. Among them, the most popular are based on the Wiener filter [22], the Kalman filter and its variations [23][24][25][26][27][28], artificial neural networks [29] and recurrent neural networks [30].…”