Analysis of crosstalk in the mechanomyographic signals generated by forearm muscles during different wrist postures

BiLSTM-Based Joint Torque Prediction From Mechanomyogram During Isometric Contractions: A Proof of Concept Study

Quantifying muscle strength is an important measure in clinical settings; however, there is a lack of practical tools that can be deployed for routine assessment. The purpose of this study is to propose a deep learning model for ankle plantar flexion torque prediction from time-series mechanomyogram (MMG) signals recorded during isometric contractions (i.e., a similar form to manual muscle testing procedure in clinical practice) and to evaluate its performance. Four different deep learning models in terms of model architecture (based on a stacked bidirectional long short-term memory and dense layers) were designed with different combinations of the number of units (from 32 to 512) and dropout ratio (from 0.0 to 0.8), and then evaluated for prediction performance by conducting the leave-one-subject-out cross-validation method from the 10-subject dataset. As a result, the models explained more variance in the untrained test dataset as the error metrics (e.g., root-mean-square error) decreased and as the slope of the relationship between the measured and predicted joint torques became closer to 1.0. Although the slope estimates appear to be sensitive to an individual dataset, >70% of the variance in nine out of 10 datasets was explained by the optimal model. These results demonstrated the feasibility of the proposed model as a potential tool to quantify average joint torque during a sustained isometric contraction.

MMG-Based Knee Dynamic Extension Force Estimation Using Cross-Talk and IGWO-LSTM

Mechanomyography (MMG) is an important muscle physiological activity signal that can reflect the amount of motor units recruited as well as the contraction frequency. As a result, MMG can be utilized to estimate the force produced by skeletal muscle. However, cross-talk and time-series correlation severely affect MMG signal recognition in the real world. These restrict the accuracy of dynamic muscle force estimation and their interaction ability in wearable devices. To address these issues, a hypothesis that the accuracy of knee dynamic extension force estimation can be improved by using MMG signals from a single muscle with less cross-talk is first proposed. The hypothesis is then confirmed using the estimation results from different muscle signal feature combinations. Finally, a novel model (improved grey wolf optimizer optimized long short-term memory networks, i.e., IGWO-LSTM) is proposed for further improving the performance of knee dynamic extension force estimation. The experimental results demonstrate that MMG signals from a single muscle with less cross-talk have a superior ability to estimate dynamic knee extension force. In addition, the proposed IGWO-LSTM provides the best performance metrics in comparison to other state-of-the-art models. Our research is expected to not only improve the understanding of the mechanisms of quadriceps contraction but also enhance the flexibility and interaction capabilities of future rehabilitation and assistive devices.

Crosstalk in Mechanomyographic Signals From Elbow Flexor Muscles During Submaximal to Maximal Isometric Flexion, Pronation, and Supination Torque Tasks

This study analyzed the crosstalk in mechanomyographic (MMG) signals from elbow flexors during isometric muscle actions from 20% to 100% maximum voluntary isometric contraction (MVIC). Twenty-five young, healthy, male participants performed the isometric elbow flexion, forearm pronation, and supination tasks at an elbow joint angle of 90 deg. The MMG signals from the biceps brachii (BB), brachialis (BRA), and brachioradialis (BRD) muscles were recorded using accelerometers. The cross-correlation coefficient was used to quantify the crosstalk in MMG signals, recorded in a direction transverse to muscle fiber axis, among the muscle pairs (P1: BB and BRA, P2: BRA and BRD, and P3: BB and BRD). In addition, the MMG RMS and MPF were quantified. The mean normalized RMS and mean MPF exhibited increasing (r > 0.900) and decreasing (r < -0.900) trends, respectively, with increases in the effort levels in all three tasks. The magnitude of crosstalk ranged from 0.915% to 21.565% in all three muscle pairs. The crosstalk was found to exhibit high positive correlations with submaximal to maximal flexion [P1 (r = 0.970), P2 (r = 0.951), and P3 (r = 0.824)], pronation [P1 (r = 0.811), P2 (r = 0.763), and P3 (r = 0.901)] and supination [P1 (r = 0.898), P2 (r = 0.838), and P3 (r = 0.852)] torque levels (eight out of nine p-values were < 0.05). Regardless of the high positive correlation between crosstalk and level of effort, the crosstalk remained at a low range (0.915-21.565%) with increases in the torque levels.

Association of anthropometric parameters with amplitude and crosstalk of mechanomyographic signals during forearm flexion, pronation and supination torque tasks

This study aimed to quantify the association of four anthropometric parameters of the human arm, namely, the arm circumference (CA), arm length (LA), skinfold thickness (ST) and inter-sensor distance (ISD), with amplitude (RMS) and crosstalk (CT) of mechanomyography (MMG) signals. Twenty-five young, healthy, male participants were recruited to perform forearm flexion, pronation and supination torque tasks. Three accelerometers were employed to record the MMG signals from the biceps brachii (BB), brachialis (BRA) and brachioradialis (BRD) at 80% maximal voluntary contraction (MVC). Signal RMS was used to quantify the amplitude of the MMG signals from a muscle, and cross-correlation coefficients were used to quantify the magnitude of the CT among muscle pairs (BB & BRA, BRA & BRD, and BB & BRD). For all investigated muscles and pairs, RMS and CT showed negligible to low negative correlations with CA, LA and ISD (r = −0.0001–−0.4611), and negligible to moderate positive correlations with ST (r = 0.004–0.511). However, almost all of these correlations were statistically insignificant (p > 0.05). These findings suggest that RMS and CT values for the elbow flexor muscles recorded and quantified using accelerometers appear invariant to anthropometric parameters.

A review on crosstalk in myographic signals

PURPOSE

Crosstalk in myographic signals is a major hindrance to the understanding of local information related to individual muscle function. This review aims to analyse the problem of crosstalk in electromyography and mechanomyography.

METHODS

An initial search of the SCOPUS database using an appropriate set of keywords yielded 290 studies, and 59 potential studies were selected after all the records were screened using the eligibility criteria. This review on crosstalk revealed that signal contamination due to crosstalk remains a major challenge in the application of surface myography techniques. Various methods have been employed in previous studies to identify, quantify and reduce crosstalk in surface myographic signals.

RESULTS

Although correlation-based methods for crosstalk quantification are easy to use, there is a possibility that co-contraction could be interpreted as crosstalk. High-definition EMG has emerged as a new technique that has been successfully applied to reduce crosstalk.

CONCLUSIONS

The phenomenon of crosstalk needs to be investigated carefully because it depends on many factors related to muscle task and physiology. This review article not only provides a good summary of the literature on crosstalk in myographic signals but also discusses new directions related to techniques for crosstalk identification, quantification and reduction. The review also provides insights into muscle-related issues that impact crosstalk in myographic signals.