Adaptive neuron-to-EMG decoder training for FES neuroprostheses

Abstract

Objective We have previously demonstrated a brain-machine interface (BMI) neuroprosthetic system that provided continuous control of functional electrical stimulation (FES) and restoration of grasp in a primate model of spinal cord injury (SCI). Predicting intended EMG directly from cortical recordings provides a flexible high-dimensional control signal for FES. However, no peripheral signal such as force or EMG is available for training EMG decoders in paralyzed individuals. Approach Here we present a method for training an EMG decoder in the absence of muscle activity recordings; the decoder relies on mapping behaviorally-relevant cortical activity to the inferred EMG activity underlying an intended action. Monkeys were trained at a 2D isometric wrist force task to control a computer cursor by applying force in the flexion, extension, ulnar, and radial directions and execute a center-out task. We used a generic muscle-to-force model based on muscle pulling directions to relate each target force to an optimal EMG pattern that attained the target force while minimizing overall muscle activity. We trained EMG decoders during the target hold periods using a gradient descent algorithm that compared EMG predictions to optimal EMG patterns. Main results We tested this method both offline and online. We quantified both the accuracy of offline force predictions and the ability of a monkey to use these real-time force predictions for closed-loop brain-control. We compared both offline and online results to those obtained with several other force decoders, including an optimal decoder computed from concurrently measured neural and force signals. Significance This novel approach to training an adaptive EMG decoder could make a brain-control FES neuroprosthesis an effective tool to restore the hand function of paralyzed individuals. Clinical implementation would make use of individualized muscle-to-force models. Broad generalization could be achieved by including data from multiple grasping tasks in the training of the neuron-to-muscle decoder. Our approach would make it possible for persons with SCI to grasp objects with their own hands, using near-normal motor intent.

Neuroprosthetic-enabled control of graded arm muscle contraction in a paralyzed human

“…Research in the field of brain computer interfaces (BCIs) has consistently demonstrated that brain activity in the intact motor cortex can be leveraged to establish a direct, functional connection to assistive devices that can restore motor and sensory functions 1 – 4 . More recent work has shown that signals recorded from the brain can be used to directly activate paralyzed muscles via functional electrical stimulation (FES) 5 – 11 . In humans, BCI control of FES (BCI-FES) has enabled control of hand movements in paralyzed participants 8 , 9 .…”

Investigation of the Relationship Between Electrical Stimulation Frequency and Muscle Frequency Response Under Submaximal Contractions

“…For the mean values, 95% confidence intervals were presented, and the hypothesis test for a mean based on the distribution of the t-value was performed to evaluate if the mean response of the individual differs from the applied stimulus. For each electrical stimulus frequency (20,25,30,35,40,45,50,75, and 100 Hz) the null hypothesis was tested for and stated that the mean response of the MMG signal of the individual was equal to the value of the stimulus frequency. In comparison, the alternative hypothesis stated that the mean response is different from the stimulus frequency.…”

“…Nine NMES profiles were applied to the neuromuscular tissue to activate the femoral nerve. They consisted of a bipolar rectangular carrier frequency set at 1 kHz (100 ms-on and 900 ms-off), randomly modulated at 20,25,30,35,40,45,50,75, and 100 Hz. The load cell feedback allowed monitoring of force production in which the tension should sustain 5% MVIC during 10 s. An interval of 2 min between each session was allowed for muscle recovery (42).…”

“…Thirteen male participants performed three maximal voluntary isometric contractions (MVIC) recorded in isometric conditions to determine the maximal force of knee extensors. This was followed by the application of nine modulated NMES frequencies (20,25,30,35,40,45,50, 75, and 100 Hz) to evoke 5% MVIC. Muscle behavior was monitored by the analysis of MMG signals, which were decomposed into frequency bands by using a Cauchy wavelet transform.…”

Functional Electrical Stimulation (FES): Clinical successes and failures to date

“…Iterative algorisms depend on input signals typically obtained using non-invasive electromyography (EMG) or motion sensors [42][43][44][45][46]. Less common is the use of electroencephalography (EEG) derived signals to control the FES [47,48]. Both EMG and motion sensing inputs can be obtained from the paretic limb or remotely from non-paretic locations.…”