Toward a generalizable deep CNN for neural drive estimation across muscles and participants.

Objective.High-density electromyography (HD-EMG) decomposition algorithms are used to identify individual motor unit (MU) spike trains, which collectively constitute the neural code of movements, to predict motor intent. This approach has advanced from offline to online decomposition, from isometric to dynamic contractions, leading to a wide range of neural-machine interface applications. However, current online methods need offline retraining when applied to the same muscle on a different day or to a different person, which limits their applications in a real-time neural-machine interface. We proposed a deep convolutional neural network (CNN) framework for neural drive estimation, which takes in frames of HD-EMG signals as input, extracts general spatiotemporal properties of MU action potentials, and outputs the number of spikes in each frame. The deep CNN can generalize its application without retraining to HD-EMG data recorded in separate sessions, muscles, or participants.Approach.We recorded HD-EMG signals from the vastus medialis and vastus lateralis muscles from five participants while they performed isometric contractions during two sessions separated by ∼20 months. We identified MU spike trains from HD-EMG signals using a convolutive blind source separation (BSS) method, and then used the cumulative spike train (CST) of these MUs and the HD-EMG signals to train and validate the deep CNN.Main results.On average, the correlation coefficients between CST from the BSS and that from deep CNN were0.983±0.006for leave-one-out across-sessions-and-muscles validation and0.989±0.002for leave-one-out across-participants validation. When trained with more than four datasets, the performance of deep CNN saturated at0.984±0.001for cross validations across muscles, sessions, and participants.Significance.We can conclude that the deep CNN is generalizable across the aforementioned conditions without retraining. We could potentially generate a robust deep CNN to estimate neural drive to muscles for neural-machine interfaces.

A Deep CNN Framework for Neural Drive Estimation From HD-EMG Across Contraction Intensities and Joint Angles.

OBJECTIVE: Previous studies have demonstrated promising results in estimating the neural drive to muscles, the net output of all motoneurons that innervate the muscle, using high-density electromyography (HD-EMG) for the purpose of interfacing with assistive technologies. Despite the high estimation accuracy, current methods based on neural networks need to be trained with specific motor unit action potential (MUAP) shapes updated for each condition (i.e., varying muscle contraction intensities or joint angles). This preliminary step dramatically limits the potential generalization of these algorithms across tasks. We propose a novel approach to estimate the neural drive using a deep convolutional neural network (CNN), which can identify the cumulative spike train (CST) through general features of MUAPs from a pool of motor units. METHODS: We recorded HD-EMG signals from the gastrocnemius medialis muscle under three isometric contraction scenarios: 1) trapezoidal contraction tasks with different intensities, 2) contraction tasks with a trapezoidal or sinusoidal torque target, and 3) trapezoidal contraction tasks at different ankle angles. We applied a convolutive blind source separation (BSS) method to decompose HD-EMG signals to CST and segmented both signals into windows to train and validate the deep CNN. Then, we optimized the structure of the deep CNN and validated its generalizability across contraction tasks within each scenario. RESULTS: With the optimal configuration for the HD-EMG data window (overlap of 20 data points and window length of 40 data points), the deep CNN estimated the CST close to that from BSS, with a correlation coefficient higher than 0.96 and normalized root-mean-square-error lower than 7% with respect to the BSS (golden standard) within each scenario. CONCLUSION: The proposed deep CNN framework can utilize data from different contraction tasks (e.g., different intensities), learn general features of MUAP variants, and estimate the neural drive for other contraction tasks. SIGNIFICANCE: With the proposed deep CNN, we could potentially build a neural-drive-based human-machine interface that is generalizable to different contraction tasks without retraining.

Characteristic behaviors associated with gait of individuals with Rett syndrome.

BACKGROUND: Individuals with Rett syndrome (RTT) exhibit impaired motor performance and gait performance, leading to decreased quality of life. Currently, there is no robust observational instrument to identify gait characteristics in RTT. Current scales are limited as individuals with intellectual disorders may be unable to understand instructions. Our primary purpose was to utilize video analysis to characterize the behaviors associated with walking in individuals with RTT and explore the relationship between behaviors during overground and during treadmill walking. METHODS: Fourteen independently ambulatory females with RTT were video-taped and observed during overground and treadmill walking. Their gait was codified into an observational checklist to reveal prominent features associated with gait in this population. RESULTS: Participants exhibited similar rates of freezing, veering, and hand stereotypies between overground and treadmill walking; however, freeze duration was shortened during treadmill walking. Toe walking was prominently exhibited during overground, but not treadmill walking. During both walking modes, participants required extensive external motivation to maintain their walking patterns. CONCLUSIONS: Results identify several gait characteristics observable during overground and treadmill walking. In general, participants behaved similarly during overground and treadmill walking. We conclude that both overground and treadmill walking are appropriate tools to evaluate gait in this population.Implications for rehabilitationLocomotor rehabilitation may increase the quantity of walking performed by the patients, which can alleviate negative effects of the sedentary lifestyle commonly observed in patients with Rett syndrome (RTT).Video analysis of natural walking can be an effective tool to characterize gait in patients with RTT which does not require particular instructions which may not be fully understood.Both overground and treadmill walking are appropriate means of evaluating gait in individuals with RTT.

The effects of muscle vibration on gait control: a review.

Background: The purpose of the review is to summarize the literature surrounding the use of muscle vibration as it relates to modifying human gait. Methods: After a brief introduction concerning historical uses and early research identifying the effect of vibration on muscle activation, we reviewed 32 articles that used muscle vibration during walking. The review is structured to address the literature within four broad categories: the effect of vibration to 'trigger' gait-like lower limb motions, the effect of vibration on gait control of healthy individuals and individuals with clinical conditions in which gait disorders are a prominent feature, and the effect of vibration training protocols on gait. Results: The acute effects of vibration during gait involving healthy participants is varied. Some authors reported differences in segmental kinematic and spatiotemporal measures while other authors reported no differences in these outcome measures. The literature involving participants with clinical conditions revealed that vibration consistently had a significant impact on gait, suggesting vibration may be an effective rehabilitation tool. All of the studies that used vibration therapy over time reported significant improvement in gait performance. Conclusions: This review highlights the difficulties in drawing definitive conclusions as to the impact of vibration on gait control, partly because of differences in walking protocols, site of vibration application, and outcome measures used across different investigative teams. It is suggested that the development of common investigative methodologies and outcome measures would accelerate the identification of techniques that may provide optimal rehabilitation protocols for individuals experiencing disordered gait control.