Neuromuscular electrical stimulation (NMES) combined with blood flow restriction (BFR) has garnered attention in rehabilitation for its ability to enhance muscle strength, despite the potential to accelerate training-related fatigue. This study examined changes in force scaling capacity immediately following combined NMES and BFR, focusing on motor unit synergy between agonist pairs. Fifteen participants ($23.3~pm ~1.8$ years) trained with combined BFR and NMES on the extensor carpi radialis longus (ECRL) muscle, with maximal voluntary contraction (MVC) of wrist extension, along with force and EMG in the ECRL and extensor carpi radialis brevis (ECRB), measured during a designate force-tracking before and after training. Factor analysis identified latent modes influencing motor unit coordination between the ECRB and ECRL. The results showed a significant decrease in MVC after training ($text {p}lt 0.001$ ). Post-test force fluctuations increased (p =0.031), along with a decrease in the mean inter-spike interval (M_ISI) in the ECRL (p =0.022). Factor analysis revealed an increase in the proportion of motor units (MUs) jointly regulated by the neural mode for both ECRB and ECRL, coupled with a decline in independently regulated MUs. Specifically, the proportion of MUs governed by the ECRL mode decreased, while those regulated by the ECRB mode increased. In conclusion, force generation capacity and force scaling are impaired after receiving combined NMES and BFR treatment. It involves redistribution of the common drive to MUs within two agonists, affecting the flexible coordination of muscle synergy and necessitating compensatory recruitment of MUs from the less fatigable agonist.
{"title":"Adaptive Modification in Agonist Common Drive After Combined Blood Flow Restriction and Neuromuscular Electrical Stimulation","authors":"Yi-Ching Chen;Chia-Chan Wu;Yeng-Ting Lin;Yueh Chen;Ing-Shiou Hwang","doi":"10.1109/TNSRE.2025.3525517","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3525517","url":null,"abstract":"Neuromuscular electrical stimulation (NMES) combined with blood flow restriction (BFR) has garnered attention in rehabilitation for its ability to enhance muscle strength, despite the potential to accelerate training-related fatigue. This study examined changes in force scaling capacity immediately following combined NMES and BFR, focusing on motor unit synergy between agonist pairs. Fifteen participants (<inline-formula> <tex-math>$23.3~pm ~1.8$ </tex-math></inline-formula> years) trained with combined BFR and NMES on the extensor carpi radialis longus (ECRL) muscle, with maximal voluntary contraction (MVC) of wrist extension, along with force and EMG in the ECRL and extensor carpi radialis brevis (ECRB), measured during a designate force-tracking before and after training. Factor analysis identified latent modes influencing motor unit coordination between the ECRB and ECRL. The results showed a significant decrease in MVC after training (<inline-formula> <tex-math>$text {p}lt 0.001$ </tex-math></inline-formula>). Post-test force fluctuations increased (p =0.031), along with a decrease in the mean inter-spike interval (M_ISI) in the ECRL (p =0.022). Factor analysis revealed an increase in the proportion of motor units (MUs) jointly regulated by the neural mode for both ECRB and ECRL, coupled with a decline in independently regulated MUs. Specifically, the proportion of MUs governed by the ECRL mode decreased, while those regulated by the ECRB mode increased. In conclusion, force generation capacity and force scaling are impaired after receiving combined NMES and BFR treatment. It involves redistribution of the common drive to MUs within two agonists, affecting the flexible coordination of muscle synergy and necessitating compensatory recruitment of MUs from the less fatigable agonist.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"372-379"},"PeriodicalIF":4.8,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10821494","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142992970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Intermuscular coupling analysis (IMC) provides important clues for understanding human muscle motion control and serves as a valuable reference for the rehabilitation assessment of stroke patients. However, the higher-order interactions and microscopic characteristics implied in IMC are not fully understood. This study introduced a multiscale intermuscular coupling analysis framework based on complex networks with O-Information (Information About Organizational Structure). In addition, to introduce microscopic neural information, sEMG signals were decomposed to obtain motor units (MU). We applied this framework to data collected from experiments on three different upper limb movements. Graph theory-based analysis revealed significant differences in muscle network connectivity across the various upper limb movement tasks. Furthermore, the community division based on MU showed a mismatch between the distribution of muscle and motor neuron inputs, with a reduction in the dimension of motor unit control during multi-joint activity tasks. O-Information was used to explore higher-order interactions in the network. The analysis of redundant and synergistic information within the network indicated that numerous low-order synergistic subsystems were present while sEMG networks and MU networks were predominantly characterized by redundant information. Moreover, the graph features of macroscopic and microscopic network exhibit promising classification accuracy under KNN, showing the potential for engineering applications of the proposed framework.
肌间耦合分析（Intermuscular coupling analysis， IMC）为理解人体肌肉运动控制提供了重要线索，为脑卒中患者的康复评估提供了有价值的参考。然而，高阶相互作用和微观特征所隐含的IMC尚未完全了解。提出了一种基于O-Information （Information About Organizational Structure）复杂网络的多尺度肌肉间耦合分析框架。此外，为了引入微观神经信息，对表面肌电信号进行分解，得到运动单元（MU）。我们将这一框架应用于从三种不同上肢运动的实验中收集的数据。基于图论的分析揭示了不同上肢运动任务中肌肉网络连通性的显著差异。此外，基于MU的社区划分显示肌肉和运动神经元输入分布不匹配，在多关节活动任务中运动单元控制维度降低。O-Information用于探索网络中的高阶交互。对网络内部冗余信息和协同信息的分析表明，在表面肌电信号网络和单元神经网络中存在大量的低阶协同子系统，而冗余信息则占主导地位。此外，宏观和微观网络的图特征在KNN下表现出良好的分类精度，显示了所提出框架的工程应用潜力。
{"title":"Multiscale Intermuscular Coupling Analysis via Complex Network-Based High-Order O-Information","authors":"Chang Yu;Qingshan She;Michael Houston;Tongcai Tan;Yingchun Zhang","doi":"10.1109/TNSRE.2025.3525467","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3525467","url":null,"abstract":"Intermuscular coupling analysis (IMC) provides important clues for understanding human muscle motion control and serves as a valuable reference for the rehabilitation assessment of stroke patients. However, the higher-order interactions and microscopic characteristics implied in IMC are not fully understood. This study introduced a multiscale intermuscular coupling analysis framework based on complex networks with O-Information (Information About Organizational Structure). In addition, to introduce microscopic neural information, sEMG signals were decomposed to obtain motor units (MU). We applied this framework to data collected from experiments on three different upper limb movements. Graph theory-based analysis revealed significant differences in muscle network connectivity across the various upper limb movement tasks. Furthermore, the community division based on MU showed a mismatch between the distribution of muscle and motor neuron inputs, with a reduction in the dimension of motor unit control during multi-joint activity tasks. O-Information was used to explore higher-order interactions in the network. The analysis of redundant and synergistic information within the network indicated that numerous low-order synergistic subsystems were present while sEMG networks and MU networks were predominantly characterized by redundant information. Moreover, the graph features of macroscopic and microscopic network exhibit promising classification accuracy under KNN, showing the potential for engineering applications of the proposed framework.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"310-320"},"PeriodicalIF":4.8,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10821496","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-31DOI: 10.1109/TNSRE.2024.3524791
M. Controzzi;L. Angelini;P. Randi;P. Mucci;A. Mazzeo;R. Ferrari;E. Gruppioni;C. Cipriani
The evaluation of hand function is of great importance to both clinical practice and biomedical research and is frequently evaluated by manual dexterity. Most of the assessment procedures evaluate the gross or the fine dexterity of the hand, but few of them are devoted to the assessment of both. We developed the Virtual Eggs Test (VET): it resembles the task of transporting fragile and robust objects, thus requiring both gross and fine dexterity. The test is composed of 11 Virtual Eggs that collapse if the grasping force exceeds their breaking thresholds, ranging from 0.4 N to 11.5 N. The test aims to transport each Virtual Egg over the barrier in the centre of the test platform without breaking it and as fast as possible. The metrics measured during the test are combined and provide two indexes that evaluate, respectively, gross and fine dexterity. We verify the concurrent validity and the construct validity of the VET with a target population of 30 trans-radial amputees wearing a myoelectric hand and the test-retest reliability on a control population of 35 healthy individuals. The results suggest the ability of the VET to assess hand function specifically in handling breakable objects, using both gross and fine dexterity over time. However, further research is needed to verify its correlation with other tests and the ability of amputees to perform activities of daily living.
{"title":"Assessing Hand Function in Trans-Radial Amputees Wearing Myoelectric Hands: The Virtual Eggs Test (VET)","authors":"M. Controzzi;L. Angelini;P. Randi;P. Mucci;A. Mazzeo;R. Ferrari;E. Gruppioni;C. Cipriani","doi":"10.1109/TNSRE.2024.3524791","DOIUrl":"https://doi.org/10.1109/TNSRE.2024.3524791","url":null,"abstract":"The evaluation of hand function is of great importance to both clinical practice and biomedical research and is frequently evaluated by manual dexterity. Most of the assessment procedures evaluate the gross or the fine dexterity of the hand, but few of them are devoted to the assessment of both. We developed the Virtual Eggs Test (VET): it resembles the task of transporting fragile and robust objects, thus requiring both gross and fine dexterity. The test is composed of 11 Virtual Eggs that collapse if the grasping force exceeds their breaking thresholds, ranging from 0.4 N to 11.5 N. The test aims to transport each Virtual Egg over the barrier in the centre of the test platform without breaking it and as fast as possible. The metrics measured during the test are combined and provide two indexes that evaluate, respectively, gross and fine dexterity. We verify the concurrent validity and the construct validity of the VET with a target population of 30 trans-radial amputees wearing a myoelectric hand and the test-retest reliability on a control population of 35 healthy individuals. The results suggest the ability of the VET to assess hand function specifically in handling breakable objects, using both gross and fine dexterity over time. However, further research is needed to verify its correlation with other tests and the ability of amputees to perform activities of daily living.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"286-297"},"PeriodicalIF":4.8,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10819437","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938186","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rehabilitation training is essential for the recovery of patients with conditions such as stroke and Parkinson’s disease. However, traditional skeletal-based assessments often fail to capture the subtle movement qualities necessary for personalized care and are not optimized for scoring tasks. To address these limitations, we propose a hierarchical contrastive learning framework that integrates multi-view skeletal data, combining both positional and angular joint information. This integration enhances the framework’s ability to detect subtle variations in movement during rehabilitation exercises. In addition, we introduce a novel contrastive loss function specifically designed for regression tasks. This new approach yields substantial improvements over existing state-of-the-art models, achieving over a 30% reduction in mean absolute deviation on both the KIMORE and UIPRMD datasets. The framework demonstrates robustness in capturing both global and local movement characteristics, which are critical for accurate clinical evaluations. By precisely quantifying action quality, the framework supports the development of more targeted, personalized rehabilitation plans and shows strong potential for broad application in rehabilitation practices as well as in a wider range of motion assessment tasks.
{"title":"Hierarchical Contrastive Representation for Accurate Evaluation of Rehabilitation Exercises via Multi-View Skeletal Representations","authors":"Zhejun Kuang;Jingrui Wang;Dawen Sun;Jian Zhao;Lijuan Shi;Yusheng Zhu","doi":"10.1109/TNSRE.2024.3523906","DOIUrl":"https://doi.org/10.1109/TNSRE.2024.3523906","url":null,"abstract":"Rehabilitation training is essential for the recovery of patients with conditions such as stroke and Parkinson’s disease. However, traditional skeletal-based assessments often fail to capture the subtle movement qualities necessary for personalized care and are not optimized for scoring tasks. To address these limitations, we propose a hierarchical contrastive learning framework that integrates multi-view skeletal data, combining both positional and angular joint information. This integration enhances the framework’s ability to detect subtle variations in movement during rehabilitation exercises. In addition, we introduce a novel contrastive loss function specifically designed for regression tasks. This new approach yields substantial improvements over existing state-of-the-art models, achieving over a 30% reduction in mean absolute deviation on both the KIMORE and UIPRMD datasets. The framework demonstrates robustness in capturing both global and local movement characteristics, which are critical for accurate clinical evaluations. By precisely quantifying action quality, the framework supports the development of more targeted, personalized rehabilitation plans and shows strong potential for broad application in rehabilitation practices as well as in a wider range of motion assessment tasks.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"201-211"},"PeriodicalIF":4.8,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10818452","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, significant strides in deep learning have propelled the advancement of electromyography (EMG)-based upper-limb gesture recognition systems, yielding notable successes across a spectrum of domains, including rehabilitation, orthopedics, robotics, and human-computer interaction. Despite these achievements, prevailing methodologies often overlook the intrinsic physical configurations and interconnectivity of multi-channel sensory inputs, resulting in a failure to adequately capture relational information embedded within the connections of deployed EMG sensor network topology. This oversight poses a significant challenge, impeding the extraction of crucial features from collaborative multi-channel EMG inputs and subsequently constraining model performance, generalizability, and interpretability. To address these limitations, we introduce novel graph structures meticulously crafted to encapsulate the spatial proximity of distributed EMG sensors and the temporal adjacency of EMG signals. Harnessing these tailored graph structures, we present Graph Convolution Network (GCN)-based classification models adept at effectively extracting and aggregating key features associated with various gestures. Our methodology exhibits remarkable efficacy, achieving state-of-the-art performance across five publicly available datasets, thus underscoring its prowess in gesture recognition tasks. Furthermore, our approach provides interpretable insights into muscular activation patterns, thereby reaffirming the practical effectiveness of our GCN model. Moreover, we show the effectiveness of our graph-based input structure and GCN-based classifier in maintaining high accuracy even with reduced sensor configurations, suggesting their potential for seamless integration into AI-powered rehabilitation strategies utilizing EMG-based gesture classification systems.
{"title":"Decoding Gestures in Electromyography: Spatiotemporal Graph Neural Networks for Generalizable and Interpretable Classification","authors":"Hunmin Lee;Ming Jiang;Jinhui Yang;Zhi Yang;Qi Zhao","doi":"10.1109/TNSRE.2024.3523943","DOIUrl":"https://doi.org/10.1109/TNSRE.2024.3523943","url":null,"abstract":"In recent years, significant strides in deep learning have propelled the advancement of electromyography (EMG)-based upper-limb gesture recognition systems, yielding notable successes across a spectrum of domains, including rehabilitation, orthopedics, robotics, and human-computer interaction. Despite these achievements, prevailing methodologies often overlook the intrinsic physical configurations and interconnectivity of multi-channel sensory inputs, resulting in a failure to adequately capture relational information embedded within the connections of deployed EMG sensor network topology. This oversight poses a significant challenge, impeding the extraction of crucial features from collaborative multi-channel EMG inputs and subsequently constraining model performance, generalizability, and interpretability. To address these limitations, we introduce novel graph structures meticulously crafted to encapsulate the spatial proximity of distributed EMG sensors and the temporal adjacency of EMG signals. Harnessing these tailored graph structures, we present Graph Convolution Network (GCN)-based classification models adept at effectively extracting and aggregating key features associated with various gestures. Our methodology exhibits remarkable efficacy, achieving state-of-the-art performance across five publicly available datasets, thus underscoring its prowess in gesture recognition tasks. Furthermore, our approach provides interpretable insights into muscular activation patterns, thereby reaffirming the practical effectiveness of our GCN model. Moreover, we show the effectiveness of our graph-based input structure and GCN-based classifier in maintaining high accuracy even with reduced sensor configurations, suggesting their potential for seamless integration into AI-powered rehabilitation strategies utilizing EMG-based gesture classification systems.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"404-419"},"PeriodicalIF":4.8,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10818442","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142992968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-27DOI: 10.1109/TNSRE.2024.3521923
Shivani Guptasarma;Monroe D. Kennedy
Upper-limb amputees face tremendous difficulty in operating dexterous powered prostheses. Previous work has shown that aspects of prosthetic hand, wrist, or elbow control can be improved through “intelligent” control, by combining movement-based or gaze-based intent estimation with low-level robotic autonomy. However, no such solutions exist for whole-arm control. Moreover, hardware platforms for advanced prosthetic control are expensive, and existing simulation platforms are not well-designed for integration with robotics software frameworks. We present the Prosthetic Arm Control Testbed (ProACT), a platform for evaluating intelligent control methods for prosthetic arms in an immersive (Augmented Reality) simulation setting. We demonstrate the use of ProACT through preliminary studies, with non-amputee participants performing an adapted Box-and-Blocks task with and without intent estimation. We further discuss how our observations may inform the design of prosthesis control methods, as well as the design of future studies using the platform. To the best of our knowledge, this constitutes the first study of semi-autonomous control for complex whole-arm prostheses, the first study including sequential task modeling in the context of wearable prosthetic arms, and the first testbed of its kind. Towards the goal of supporting future research in intelligent prosthetics, the system is built upon existing open-source frameworks for robotics, and is available at https://arm.stanford.edu/proact.
{"title":"ProACT: An Augmented Reality Testbed for Intelligent Prosthetic Arms","authors":"Shivani Guptasarma;Monroe D. Kennedy","doi":"10.1109/TNSRE.2024.3521923","DOIUrl":"https://doi.org/10.1109/TNSRE.2024.3521923","url":null,"abstract":"Upper-limb amputees face tremendous difficulty in operating dexterous powered prostheses. Previous work has shown that aspects of prosthetic hand, wrist, or elbow control can be improved through “intelligent” control, by combining movement-based or gaze-based intent estimation with low-level robotic autonomy. However, no such solutions exist for whole-arm control. Moreover, hardware platforms for advanced prosthetic control are expensive, and existing simulation platforms are not well-designed for integration with robotics software frameworks. We present the Prosthetic Arm Control Testbed (ProACT), a platform for evaluating intelligent control methods for prosthetic arms in an immersive (Augmented Reality) simulation setting. We demonstrate the use of ProACT through preliminary studies, with non-amputee participants performing an adapted Box-and-Blocks task with and without intent estimation. We further discuss how our observations may inform the design of prosthesis control methods, as well as the design of future studies using the platform. To the best of our knowledge, this constitutes the first study of semi-autonomous control for complex whole-arm prostheses, the first study including sequential task modeling in the context of wearable prosthetic arms, and the first testbed of its kind. Towards the goal of supporting future research in intelligent prosthetics, the system is built upon existing open-source frameworks for robotics, and is available at <uri>https://arm.stanford.edu/proact</uri>.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"354-365"},"PeriodicalIF":4.8,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10817583","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142975938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-26DOI: 10.1109/TNSRE.2024.3523332
Guofu Zhang;Banghua Yang;Peng Zan;Dingguo Zhang
Background: Assessment of exercise fatigue is crucial for enhancing work capacity and minimizing the risk of injury. Surface electromyography (sEMG) has been used to quantitatively assess exercise fatigue as a new technology in recent years. However, the currently available research primarily distinguishes between fatigue and non-fatigue states, offering limited and less robust findings in multilevel evaluations. Methods: This study proposes a multiple attention and convolution network (MACNet) for a three-level assessment of muscle fatigue based on sEMG. Under the designed 50% maximum voluntary contraction experimental paradigm, sEMG signals and rate of perceived exertion scale are collected from 48 subjects. MACNet is developed to assess sEMG fatigue, incorporating improved temporal attention based on sliding window, multiscale convolution, and channel-spatial attention. Finally, GradCAM visualization is used to verify the developed model’s interpretation, exploring the effects of sEMG channels and time-domain characteristics on exercise fatigue. Results: The average classification F1-Score and accuracy of MACNet are 83.95% and 84.11% for subject-wise and 82.83% and 82.43% for cross-subject, respectively. The GradCAM visualization highlights the greater contribution of the flexor digitorum superficialis and flexor digitorum profundus in evaluating high fatigue, along with the varied impact of time-domain features on exercise fatigue assessment. Conclusion: MACNet achieves the highest average classification accuracy and F1-Score, significantly higher than other state-of-the-art methods like SVM, RF, MFFNet, TSCNN, LMDANet, Conformer and MSFEnet, enhancing the extraction of exercise fatigue insights from sEMG channels and time-domain features. The codes are available at: https://github.com/ZhangGf94/MACNet
{"title":"Multilevel Assessment of Exercise Fatigue Utilizing Multiple Attention and Convolution Network (MACNet) Based on Surface Electromyography","authors":"Guofu Zhang;Banghua Yang;Peng Zan;Dingguo Zhang","doi":"10.1109/TNSRE.2024.3523332","DOIUrl":"https://doi.org/10.1109/TNSRE.2024.3523332","url":null,"abstract":"Background: Assessment of exercise fatigue is crucial for enhancing work capacity and minimizing the risk of injury. Surface electromyography (sEMG) has been used to quantitatively assess exercise fatigue as a new technology in recent years. However, the currently available research primarily distinguishes between fatigue and non-fatigue states, offering limited and less robust findings in multilevel evaluations. Methods: This study proposes a multiple attention and convolution network (MACNet) for a three-level assessment of muscle fatigue based on sEMG. Under the designed 50% maximum voluntary contraction experimental paradigm, sEMG signals and rate of perceived exertion scale are collected from 48 subjects. MACNet is developed to assess sEMG fatigue, incorporating improved temporal attention based on sliding window, multiscale convolution, and channel-spatial attention. Finally, GradCAM visualization is used to verify the developed model’s interpretation, exploring the effects of sEMG channels and time-domain characteristics on exercise fatigue. Results: The average classification F1-Score and accuracy of MACNet are 83.95% and 84.11% for subject-wise and 82.83% and 82.43% for cross-subject, respectively. The GradCAM visualization highlights the greater contribution of the flexor digitorum superficialis and flexor digitorum profundus in evaluating high fatigue, along with the varied impact of time-domain features on exercise fatigue assessment. Conclusion: MACNet achieves the highest average classification accuracy and F1-Score, significantly higher than other state-of-the-art methods like SVM, RF, MFFNet, TSCNN, LMDANet, Conformer and MSFEnet, enhancing the extraction of exercise fatigue insights from sEMG channels and time-domain features. The codes are available at: \u0000<uri>https://github.com/ZhangGf94/MACNet</uri>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"243-254"},"PeriodicalIF":4.8,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10816640","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Amyotrophic lateral sclerosis (ALS) is a multisystem neurodegenerative disorder characterized by progressive motor decline. Studies of electroencephalographic (EEG) activity during rest and motor execution have captured network changes in ALS. However, the nature of network-level impairment in the pre-motor activity in ALS remains unclear. Assessing the (dys)function of motor networks engaged prior to motor output is essential for understanding the motor pathophysiology in ALS. We recorded EEG in 22 people with ALS (PwALS) and 16 age-matched healthy controls during rest and isometric pincer-grip tasks. EEG spectral power and coherence were calculated during rest, pre-motor stage, and motor execution. In PwALS, significantly higher event-related spectral perturbations were observed compared to controls over electrodes representing a) contralateral prefrontal and parietal regions in theta band during pre-motor stage, b) contralateral parietal and ipsilateral motor regions in high-beta band during motor execution. Similarly, spectral coherence revealed abnormal EEG connectivity within 1) sensorimotor network during rest in theta band, 2) (pre)motor networks during pre-motor stage in low-alpha and high-beta bands, 3) Fronto-parietal networks during execution in high-beta band. Furthermore, the abnormal EEG connectivity during rest and execution (but not during pre-motor stage) showed significant negative correlation with clinical ALS-functional-rating-scale scores. Combining abnormal EEG connectivity from rest, pre-motor, and execution stages provided more powerful discrimination between patients and controls with a uniquely higher contribution of measures pertaining to the pre-motor stage. The results indicate that pre-motor functional activity reflects a different and unique aspect of network impairment, with potential for inclusion as biomarker candidates in ALS.
{"title":"Abnormal EEG Spectral Power and Coherence Measures During Pre-Motor Stage in Amyotrophic Lateral Sclerosis","authors":"Saroj Bista;Amina Coffey;Matthew Mitchell;Antonio Fasano;Stefan Dukic;Teresa Buxo;Eileen Giglia;Mark Heverin;Muthuraman Muthuraman;Richard G. Carson;Madeleine Lowery;Lara McManus;Orla Hardiman;Bahman Nasseroleslami","doi":"10.1109/TNSRE.2024.3523109","DOIUrl":"https://doi.org/10.1109/TNSRE.2024.3523109","url":null,"abstract":"Amyotrophic lateral sclerosis (ALS) is a multisystem neurodegenerative disorder characterized by progressive motor decline. Studies of electroencephalographic (EEG) activity during rest and motor execution have captured network changes in ALS. However, the nature of network-level impairment in the pre-motor activity in ALS remains unclear. Assessing the (dys)function of motor networks engaged prior to motor output is essential for understanding the motor pathophysiology in ALS. We recorded EEG in 22 people with ALS (PwALS) and 16 age-matched healthy controls during rest and isometric pincer-grip tasks. EEG spectral power and coherence were calculated during rest, pre-motor stage, and motor execution. In PwALS, significantly higher event-related spectral perturbations were observed compared to controls over electrodes representing a) contralateral prefrontal and parietal regions in theta band during pre-motor stage, b) contralateral parietal and ipsilateral motor regions in high-beta band during motor execution. Similarly, spectral coherence revealed abnormal EEG connectivity within 1) sensorimotor network during rest in theta band, 2) (pre)motor networks during pre-motor stage in low-alpha and high-beta bands, 3) Fronto-parietal networks during execution in high-beta band. Furthermore, the abnormal EEG connectivity during rest and execution (but not during pre-motor stage) showed significant negative correlation with clinical ALS-functional-rating-scale scores. Combining abnormal EEG connectivity from rest, pre-motor, and execution stages provided more powerful discrimination between patients and controls with a uniquely higher contribution of measures pertaining to the pre-motor stage. The results indicate that pre-motor functional activity reflects a different and unique aspect of network impairment, with potential for inclusion as biomarker candidates in ALS.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"232-242"},"PeriodicalIF":4.8,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10816442","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-25DOI: 10.1109/TNSRE.2024.3522681
Ke Ma, Siwei Liu, Mengjie Qin, Stephan M Goetz
Motor-evoked potentials (MEPs) are among the few directly observable responses to external brain stimulation and serve a variety of applications, often in the form of input-output (IO) curves. Previous statistical models with two variability sources inherently consider the small MEPs at the low-side plateau as part of the neural recruitment properties. However, recent studies demonstrated that small MEP responses under resting conditions are contaminated and over-shadowed by background noise of mostly technical quality, e.g., caused by the amplifier, and suggested that the neural recruitment curve should continue below this noise level. This work intends to separate physiological variability from background noise and improve the description of recruitment behaviour. We developed a triple-variability-source model around a logarithmic logistic function without a lower plateau and incorporated an additional source for background noise. Compared to models with two or fewer variability sources, our approach better described IO characteristics, evidenced by lower Bayesian Information Criterion scores across all subjects and pulse shapes. The model independently extracted hidden variability information across the stimulated neural system and isolated it from background noise, which led to an accurate estimation of the IO curve parameters. This new model offers a robust tool to analyse brain stimulation IO curves in clinical and experimental neuroscience and reduces the risk of spurious results from inappropriate statistical methods. The presented model together with the corresponding calibration method provides a more accurate representation of MEP responses and variability sources, advances our understanding of cortical excitability, and may improve the assessment of neuromodulation effects.
{"title":"Extraction of three mechanistically different variability and noise sources in the trial-to-trial variability of brain stimulation.","authors":"Ke Ma, Siwei Liu, Mengjie Qin, Stephan M Goetz","doi":"10.1109/TNSRE.2024.3522681","DOIUrl":"https://doi.org/10.1109/TNSRE.2024.3522681","url":null,"abstract":"<p><p>Motor-evoked potentials (MEPs) are among the few directly observable responses to external brain stimulation and serve a variety of applications, often in the form of input-output (IO) curves. Previous statistical models with two variability sources inherently consider the small MEPs at the low-side plateau as part of the neural recruitment properties. However, recent studies demonstrated that small MEP responses under resting conditions are contaminated and over-shadowed by background noise of mostly technical quality, e.g., caused by the amplifier, and suggested that the neural recruitment curve should continue below this noise level. This work intends to separate physiological variability from background noise and improve the description of recruitment behaviour. We developed a triple-variability-source model around a logarithmic logistic function without a lower plateau and incorporated an additional source for background noise. Compared to models with two or fewer variability sources, our approach better described IO characteristics, evidenced by lower Bayesian Information Criterion scores across all subjects and pulse shapes. The model independently extracted hidden variability information across the stimulated neural system and isolated it from background noise, which led to an accurate estimation of the IO curve parameters. This new model offers a robust tool to analyse brain stimulation IO curves in clinical and experimental neuroscience and reduces the risk of spurious results from inappropriate statistical methods. The presented model together with the corresponding calibration method provides a more accurate representation of MEP responses and variability sources, advances our understanding of cortical excitability, and may improve the assessment of neuromodulation effects.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143541913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Advancements in neuroscience and artificial intelligence are propelling rapid progress in brain-computer interfaces (BCIs). These developments hold significant potential for decoding motion intentions from brain signals, enabling direct control commands without reliance on conventional neural pathways. Growing interest exists in decoding bimanual motor tasks, crucial for activities of daily living. This stems from the need to restore motor function, especially in individuals with deficits. This review aims to summarize neurological advancements in bimanual BCIs, encompassing neuroimaging techniques, experimental paradigms, and analysis algorithms. Thirty-six articles were reviewed, adhering to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The literature search result revealed diverse experimental paradigms, protocols, and research directions, including enhancing the decoding accuracy, advancing versatile prosthesis robots, and enabling real-time applications. Notably, within BCI studies on bimanual movement coordination, a shared objective is to achieve naturalistic movement and practical applications with neurorehabilitation potential.
{"title":"A Systematic Review of Bimanual Motor Coordination in Brain-Computer Interface","authors":"Poraneepan Tantawanich;Chatrin Phunruangsakao;Shin-Ichi Izumi;Mitsuhiro Hayashibe","doi":"10.1109/TNSRE.2024.3522168","DOIUrl":"https://doi.org/10.1109/TNSRE.2024.3522168","url":null,"abstract":"Advancements in neuroscience and artificial intelligence are propelling rapid progress in brain-computer interfaces (BCIs). These developments hold significant potential for decoding motion intentions from brain signals, enabling direct control commands without reliance on conventional neural pathways. Growing interest exists in decoding bimanual motor tasks, crucial for activities of daily living. This stems from the need to restore motor function, especially in individuals with deficits. This review aims to summarize neurological advancements in bimanual BCIs, encompassing neuroimaging techniques, experimental paradigms, and analysis algorithms. Thirty-six articles were reviewed, adhering to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The literature search result revealed diverse experimental paradigms, protocols, and research directions, including enhancing the decoding accuracy, advancing versatile prosthesis robots, and enabling real-time applications. Notably, within BCI studies on bimanual movement coordination, a shared objective is to achieve naturalistic movement and practical applications with neurorehabilitation potential.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"266-285"},"PeriodicalIF":4.8,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10816155","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：