Hwang, Y.-C. E. | Search bioRxiv

bioRxiv2023

Closed-loop control of functional electrical stimulation using a selectively recording and bidirectional nerve cuff interface

BackgroundDiscriminating recorded afferent neural information can provide sensory feedback for closed-loop control of functional electrical stimulation, which restores movement to paralyzed limbs. Previous work achieved state-of-the-art off-line classification of electrical activity in different neural pathways recorded by a multi-contact nerve cuff electrode, by applying deep learning to spatiotemporal neural patterns. ObjectiveTo incorporate this approach into closed-loop stimulation. MethodsAcute in vivo experiments were conducted on 11 Long Evans rats to demonstrate closed-loop stimulation. A 64-channel (8 x 8) nerve cuff electrode was implanted on each rats sciatic nerve for recording and stimulation. A convolutional neural network (CNN) was trained with spatiotemporal signal recordings associated with 3 different states of the hindpaw (dorsiflexion, plantarflexion, and pricking of the heel). After training, firing rates were reconstructed from the classifier outputs for each of the three target classes. A rule-based closed-loop controller was implemented to produce ankle movement trajectories using neural stimulation, based on the classified nerve recordings. Closed-loop stimulation was initiated by the detection of a heel prick, and induced dorsiflexion. The detection of dorsiflexion triggered stimulation to induce plantarflexion, and vice versa. A single trial began with a heel prick and ended when an incorrect state transition occurred or when a second heel prick was detected. ResultsClosed-loop stimulation was successfully demonstrated in 6 subjects. Number of successful trials per subject ranged from 1-17 and number of correct state transitions per trial ranged from 3-53. ConclusionThis work demonstrates that a CNN applied to multi-contact nerve cuff recordings can be used for closed-loop control of functional electrical stimulation.

neuroscience↗

bioRxiv2022

Resource-efficient Neural Network Architectures forClassifying Nerve Cuff Recordings on Implantable Devices

BackgroundClosed-loop control of functional electrical stimulation involves using recorded nerve signals to make decisions regarding nerve stimulation in real-time. Surgically implanted devices that can implement this strategy have significant potential to restore natural movement after paralysis. Previous work demonstrated the use of convolutional neural networks (CNNs) to discriminate between activity from different neural pathways recorded by a high-density multi-contact nerve cuff electrode. Despite state-of-the-art performance, that approach required too much data storage, power and computation time for a practical implementation on surgically implanted hardware. ObjectiveTo reduce resource utilization for an implantable implementation, with a minimal performance loss for CNNs that can discriminate between neural pathways in multi-contact nerve cuff electrode recordings. MethodsNeural network (NN) architectures were evaluated on a dataset of rat sciatic nerve recordings previously collected using 56-channel (7 x 8) spiral nerve cuff electrodes to capture spatiotemporal neural activity patterns. The NNs were trained to classify individual, natural compound action potentials (nCAPs) elicited by sensory stimuli. Three architecture types were explored: the previously reported ESCAPE-NET, a fully convolutional network, and a recurrent neural network. Variations of each architecture yielded NNs with a range in the number of weights and required floating-point operations (FLOPs). Each NN was evaluated based on F1-score and resource requirements. ResultsNNs were identified that, when compared to ESCAPE-NET, required 1,132-1,787x fewer weights, 389-995x less memory, and 6-11,073x fewer FLOPs, while maintaining macro F1-scores of 0.70-0.71 compared to a baseline of 0.75. Memory requirements range from 22.69 KB to 58.11 KB, falling within the range of on-chip memory sizes from several published deep learning accelerators fabricated in 65nm ASIC technology. ConclusionReduced versions of ESCAPE-NET require significantly fewer resources without significant accuracy loss, thus can be more easily incorporated into a surgically implantable device that performs closed-loop real-time responsive neural stimulation.

neuroscience↗