Task-Oriented Muscle Synergy Extraction Using An Autoencoder-Based Neural Model

Transferring Sensor-Based Assessments to Clinical Practice: The Case of Muscle Synergies

Sensor-based assessments in medical practice and rehabilitation include the measurement of physiological signals such as EEG, EMG, ECG, heart rate, and NIRS, and the recording of movement kinematics and interaction forces. Such measurements are commonly employed in clinics with the aim of assessing patients' pathologies, but so far some of them have found full exploitation mainly for research purposes. In fact, even though the data they allow to gather may shed light on physiopathology and mechanisms underlying motor recovery in rehabilitation, their practical use in the clinical environment is mainly devoted to research studies, with a very reduced impact on clinical practice. This is especially the case for muscle synergies, a well-known method for the evaluation of motor control in neuroscience based on multichannel EMG recordings. In this paper, considering neuromotor rehabilitation as one of the most important scenarios for exploiting novel methods to assess motor control, the main challenges and future perspectives for the standard clinical adoption of muscle synergy analysis are reported and critically discussed.

Dissecting muscle synergies in the task space

The muscle synergy is a guiding concept in motor control research that relies on the general notion of muscles 'working together' towards task performance. However, although the synergy concept has provided valuable insights into motor coordination, muscle interactions have not been fully characterised with respect to task performance. Here, we address this research gap by proposing a novel perspective to the muscle synergy that assigns specific functional roles to muscle couplings by characterising their task-relevance. Our novel perspective provides nuance to the muscle synergy concept, demonstrating how muscular interactions can 'work together' in different ways: (1) irrespective of the task at hand but also (2) redundantly or (3) complementarily towards common task-goals. To establish this perspective, we leverage information- and network-theory and dimensionality reduction methods to include discrete and continuous task parameters directly during muscle synergy extraction. Specifically, we introduce co-information as a measure of the task-relevance of muscle interactions and use it to categorise such interactions as task-irrelevant (present across tasks), redundant (shared task information), or synergistic (different task information). To demonstrate these types of interactions in real data, we firstly apply the framework in a simple way, revealing its added functional and physiological relevance with respect to current approaches. We then apply the framework to large-scale datasets and extract generalizable and scale-invariant representations consisting of subnetworks of synchronised muscle couplings and distinct temporal patterns. The representations effectively capture the functional interplay between task end-goals and biomechanical affordances and the concurrent processing of functionally similar and complementary task information. The proposed framework unifies the capabilities of current approaches in capturing distinct motor features while providing novel insights and research opportunities through a nuanced perspective to the muscle synergy.

Characteristics of muscle synergy extracted using an autoencoder in patients with stroke during the curved walking in comparison with healthy controls

BACKGROUND AND OBJECTIVE

This study investigated the spatial and temporal features of muscle synergy during two types of curved walking (CW), according to whether the analyzed legs were located on the outside (OCW) or inside (ICW) on the basis of the curve direction during CW, in patients with stroke.

METHODS

Thirteen patients with stroke and seven age-matched healthy controls participated in this study. Using the autoencoder technique, four muscle synergies were extracted from eight muscles of the paretic legs in patients with stroke and the dominant legs in healthy controls. Walking speed, variance accounted for (VAF) of the four synergies, and each synergy with the same number were compared. Pearson's correlation and activation peak timing calculation were used to identify spatial and temporal features, respectively.

RESULTS

Regarding walking speed in patients with stroke, ICW was significantly faster than OCW (P = 0.027). Regarding spatial features, muscle weighting values of patients with stroke in synergy 3 that were mainly involved in the early swing phase had the lowest similarity [r = 0.30] during OCW, and synergy 4 that was mainly involved in the late swing phase had the lowest similarity [r = 0.39] during ICW compared to the healthy group. Meanwhile, in terms of temporal features, activation peak timings of patients with stroke in synergy 1, which was mainly involved in the early stance phase, and synergy 2, which was mainly involved in the mid-late stance phase, were significantly delayed during OCW (P < .001, P = 0.003), while peak timings of synergy 1 and synergy 3 were delayed during ICW (P = .004, P = .002).

SIGNIFICANCE

Based on distinctive features of spatial synergy during the swing phase of CW and temporal synergy during the swing-stance transition phase of CW in patients with stroke in gait rehabilitation, specific approaches need to be considered depending on the curve direction and each gait phase.

A Serious Game for the Assessment of Visuomotor Adaptation Capabilities during Locomotion Tasks Employing an Embodied Avatar in Virtual Reality

The study of visuomotor adaptation (VMA) capabilities has been encompassed in various experimental protocols aimed at investigating human motor control strategies and/or cognitive functions. VMA-oriented frameworks can have clinical applications, primarily in the investigation and assessment of neuromotor impairments caused by conditions such as Parkinson's disease or post-stroke, which affect the lives of tens of thousands of people worldwide. Therefore, they can enhance the understanding of the specific mechanisms of such neuromotor disorders, thus being a potential biomarker for recovery, with the aim of being integrated with conventional rehabilitative programs. Virtual Reality (VR) can be entailed in a framework targeting VMA since it allows the development of visual perturbations in a more customizable and realistic way. Moreover, as has been demonstrated in previous works, a serious game (SG) can further increase engagement thanks to the use of full-body embodied avatars. Most studies implementing VMA frameworks have focused on upper limb tasks and have utilized a cursor as visual feedback for the user. Hence, there is a paucity in the literature about VMA-oriented frameworks targeting locomotion tasks. In this article, the authors present the design, development, and testing of an SG-based framework that addresses VMA in a locomotion activity by controlling a full-body moving avatar in a custom VR environment. This workflow includes a set of metrics to quantitatively assess the participants' performance. Thirteen healthy children were recruited to evaluate the framework. Several quantitative comparisons and analyses were run to validate the different types of introduced visuomotor perturbations and to evaluate the ability of the proposed metrics to describe the difficulty caused by such perturbations. During the experimental sessions, it emerged that the system is safe, easy to use, and practical in a clinical setting. Despite the limited sample size, which represents the main limitation of the study and can be compensated for with future recruitment, the authors claim the potential of this framework as a useful instrument for quantitatively assessing either motor or cognitive impairments. The proposed feature-based approach gives several objective parameters as additional biomarkers that can integrate the conventional clinical scores. Future studies might investigate the relation between the proposed biomarkers and the clinical scores for specific disorders such as Parkinson's disease and cerebral palsy.

Evaluation of Methods for the Extraction of Spatial Muscle Synergies

Muscle synergies have been largely used in many application fields, including motor control studies, prosthesis control, movement classification, rehabilitation, and clinical studies. Due to the complexity of the motor control system, the full repertoire of the underlying synergies has been identified only for some classes of movements and scenarios. Several extraction methods have been used to extract muscle synergies. However, some of these methods may not effectively capture the nonlinear relationship between muscles and impose constraints on input signals or extracted synergies. Moreover, other approaches such as autoencoders (AEs), an unsupervised neural network, were recently introduced to study bioinspired control and movement classification. In this study, we evaluated the performance of five methods for the extraction of spatial muscle synergy, namely, principal component analysis (PCA), independent component analysis (ICA), factor analysis (FA), nonnegative matrix factorization (NMF), and AEs using simulated data and a publicly available database. To analyze the performance of the considered extraction methods with respect to several factors, we generated a comprehensive set of simulated data (ground truth), including spatial synergies and temporal coefficients. The signal-to-noise ratio (SNR) and the number of channels (NoC) varied when generating simulated data to evaluate their effects on ground truth reconstruction. This study also tested the efficacy of each synergy extraction method when coupled with standard classification methods, including K-nearest neighbors (KNN), linear discriminant analysis (LDA), support vector machines (SVM), and Random Forest (RF). The results showed that both SNR and NoC affected the outputs of the muscle synergy analysis. Although AEs showed better performance than FA in variance accounted for and PCA in synergy vector similarity and activation coefficient similarity, NMF and ICA outperformed the other three methods. Classification tasks showed that classification algorithms were sensitive to synergy extraction methods, while KNN and RF outperformed the other two methods for all extraction methods; in general, the classification accuracy of NMF and PCA was higher. Overall, the results suggest selecting suitable methods when performing muscle synergy-related analysis.

CardioVR-ReTone—Robotic Exoskeleton for Upper Limb Rehabilitation following Open Heart Surgery: Design, Modelling, and Control

Following cardiac surgery, patients experience difficulties with the rehabilitation process, often finding it difficult, and therefore lack the motivation for rehabilitation activities. As the number of people aged 65 and over will rise by 207 percent globally by 2050, the need for cardiac rehabilitation will significantly increase, as this is the main population to experience heart problems. To address this challenge, this paper proposes a new robotic exoskeleton concept with 12 DoFs (6 DoFs on each arm), with a symmetrical structure for the upper limbs, to be used in the early rehabilitation of cardiac patients after open-heart surgery. The electromechanical design (geometric, kinematic, and dynamic model), the control architecture, and the VR-based operating module of the robotic exoskeleton are presented. To solve the problem of the high degree of complexity regarding the CardioVR-ReTone kinematic and dynamic model, the iterative algorithm, kinetic energy, and generalized forces were used. The results serve as a complete model of the exoskeleton, from a kinematic and dynamic point of view as well as to the selection of the electric motors, control system, and VR motivation model. The validation of the concept was achieved by evaluating the exoskeleton structure from an ergonomic point of view, emphasizing the movements that will be part of the cardiac rehabilitation.

How Many Muscles? Optimal Muscles Set Search for Optimizing Myocontrol Performance

In myo-control, for computational and setup constraints, the measurement of a high number of muscles is not always possible: the choice of the muscle set to use in a myo-control strategy depends on the desired application scope and a search for a reduced muscle set, tailored to the application, has never been performed. The identification of such set would involve finding the minimum set of muscles whose difference in terms of intention detection performance is not statistically significant when compared to the original set. Also, given the intrinsic sensitivity of muscle synergies to variations of EMG signals matrix, the reduced set should not alter synergies that come from the initial input, since they provide physiological information on motor coordination. The advantages of such reduced set, in a rehabilitation context, would be the reduction of the inputs processing time, the reduction of the setup bulk and a higher sensitivity to synergy changes after training, which can eventually lead to modifications of the ongoing therapy. In this work, the existence of a minimum muscle set, called optimal set, for an upper-limb myoelectric application, that preserves performance of motor activity prediction and the physiological meaning of synergies, has been investigated. Analyzing isometric contractions during planar reaching tasks, two types of optimal muscle sets were examined: a subject-specific one and a global one. The former relies on the subject-specific movement strategy, the latter is composed by the most recurrent muscles among subjects specific optimal sets and shared by all the subjects. Results confirmed that the muscle set can be reduced to achieve comparable hand force estimation performances. Moreover, two types of muscle synergies namely "Pose-Shared" (extracted from a single multi-arm-poses dataset) and "Pose-Related" (clustering pose-specific synergies), extracted from the global optimal muscle set, have shown a significant similarity with full-set related ones meaning a high consistency of the motor primitives. Pearson correlation coefficients assessed the similarity of each synergy. The discovering of dominant muscles by means of the optimization of both muscle set size and force estimation error may reveal a clue on the link between synergistic patterns and the force task.