Pub Date : 2024-10-18DOI: 10.1109/TNSRE.2024.3483294
Kyriaki Kostoglou;Gernot R. Müller-Putz
This study introduces an alternative approach to electroencephalography (EEG) time-frequency analysis based on time-varying autoregressive (TV-AR) models in a cascade configuration to independently monitor key EEG spectral components. The method is evaluated for its neurophysiological interpretation and effectiveness in motor-related brain-computer interface (BCI) applications. Specifically, we assess the ability of the tracked EEG poles to discriminate between rest, movement execution (ME) and movement imagination (MI) in healthy subjects, as well as movement attempts (MA) in individuals with spinal cord injury (SCI). Our results show that pole tracking effectively captures broad changes in EEG dynamics, such as transitions between rest and movement-related states. It outperformed traditional EEG-based features, increasing detection accuracy for ME by an average of 4.1% (with individual improvements reaching as high as 15%) and MI by an average of 4.5% (up to 13.8%) compared to time-domain low-frequency EEG features. Similarly, compared to alpha/beta band power, the method improved ME detection by an average of 5.9% (up to 10.4%) and MI by an average of 4.3% (up to 10.2%), with results averaged across 15 healthy participants. In one participant with SCI, pole tracking improved MA detection by 12.9% over low-frequency EEG features and 4.8% over alpha/beta band power. However, its ability to distinguish finer movement details within specific movement types was limited. Additionally, the temporal evolution of the extracted pole tracking features revealed event-related desynchronization phenomena, typically observed during ME, MA and MI, as well as increases in frequency, which are of neurophysiological interest.
{"title":"Motor-Related EEG Analysis Using a Pole Tracking Approach","authors":"Kyriaki Kostoglou;Gernot R. Müller-Putz","doi":"10.1109/TNSRE.2024.3483294","DOIUrl":"10.1109/TNSRE.2024.3483294","url":null,"abstract":"This study introduces an alternative approach to electroencephalography (EEG) time-frequency analysis based on time-varying autoregressive (TV-AR) models in a cascade configuration to independently monitor key EEG spectral components. The method is evaluated for its neurophysiological interpretation and effectiveness in motor-related brain-computer interface (BCI) applications. Specifically, we assess the ability of the tracked EEG poles to discriminate between rest, movement execution (ME) and movement imagination (MI) in healthy subjects, as well as movement attempts (MA) in individuals with spinal cord injury (SCI). Our results show that pole tracking effectively captures broad changes in EEG dynamics, such as transitions between rest and movement-related states. It outperformed traditional EEG-based features, increasing detection accuracy for ME by an average of 4.1% (with individual improvements reaching as high as 15%) and MI by an average of 4.5% (up to 13.8%) compared to time-domain low-frequency EEG features. Similarly, compared to alpha/beta band power, the method improved ME detection by an average of 5.9% (up to 10.4%) and MI by an average of 4.3% (up to 10.2%), with results averaged across 15 healthy participants. In one participant with SCI, pole tracking improved MA detection by 12.9% over low-frequency EEG features and 4.8% over alpha/beta band power. However, its ability to distinguish finer movement details within specific movement types was limited. Additionally, the temporal evolution of the extracted pole tracking features revealed event-related desynchronization phenomena, typically observed during ME, MA and MI, as well as increases in frequency, which are of neurophysiological interest.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3837-3847"},"PeriodicalIF":4.8,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10721612","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142464257","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}
Mirror Therapy is a form of upper limb therapy in stroke, which consists on showing the mirrored symmetric movement of the unimpaired side using a mirror placed in the medial sagittal plane. The illusion of movement corresponding to the impaired extremity could facilitate neuroplasticity, and assists patients in regaining certain lost motor functions. Recent studies have shown the potential and benefit of translating this effective therapy in an immersive virtual reality (VR) environment, using head mounted display and hand tracking systems. This work investigates the feasibility to use myoelectric control in an immersive VR environment for the mirror therapy to accomplish a funtional task. Surface electromyography sensors were used to measure muscle activation and detect user intention to perform grasping actions in two visual feedback configurations: unimanual and bimanual. Even though in both conditions the virtual mirrored hand is controlled by the healthy hand, the latter creates the illusion that two functional hands cooperate for grasping. A total of 18 healthy subjects participated in the evaluation of the environment, control method and a comparison between the two configurations. This includes self-rating surveys and performance metrics. Results from the Simulator Sickness Questionnaire showed negligible adverse symptoms related to the use of the VR-application proposed. Positive outcomes from the System Usability Scale and Presence Questionnaire affirmed its feasible as a form of therapy for the rehabilitation of hemiparetic stroke patients. Although the adapted Box and Blocks Test proved immediate training-induced learning, performance measures revealed no significant distinctions between visual feedback configurations.
{"title":"Impact of Visual Feedback Configurations in a Task-Oriented Immersive Virtual Reality Mirror Therapy","authors":"Patricia Capsi-Morales;Thomas Geier;Joachim Hermsdörfer;Cristina Piazza","doi":"10.1109/TNSRE.2024.3482873","DOIUrl":"10.1109/TNSRE.2024.3482873","url":null,"abstract":"Mirror Therapy is a form of upper limb therapy in stroke, which consists on showing the mirrored symmetric movement of the unimpaired side using a mirror placed in the medial sagittal plane. The illusion of movement corresponding to the impaired extremity could facilitate neuroplasticity, and assists patients in regaining certain lost motor functions. Recent studies have shown the potential and benefit of translating this effective therapy in an immersive virtual reality (VR) environment, using head mounted display and hand tracking systems. This work investigates the feasibility to use myoelectric control in an immersive VR environment for the mirror therapy to accomplish a funtional task. Surface electromyography sensors were used to measure muscle activation and detect user intention to perform grasping actions in two visual feedback configurations: unimanual and bimanual. Even though in both conditions the virtual mirrored hand is controlled by the healthy hand, the latter creates the illusion that two functional hands cooperate for grasping. A total of 18 healthy subjects participated in the evaluation of the environment, control method and a comparison between the two configurations. This includes self-rating surveys and performance metrics. Results from the Simulator Sickness Questionnaire showed negligible adverse symptoms related to the use of the VR-application proposed. Positive outcomes from the System Usability Scale and Presence Questionnaire affirmed its feasible as a form of therapy for the rehabilitation of hemiparetic stroke patients. Although the adapted Box and Blocks Test proved immediate training-induced learning, performance measures revealed no significant distinctions between visual feedback configurations.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3923-3932"},"PeriodicalIF":4.8,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10721210","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142464255","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}
Combined exercise and cognitive training have been evidenced to be effective in cognitive and physical functions in post-stroke survivors. Recent interest has gradually shifted to technology-aided cognitive rehabilitation. However, clear neural makers or comprehensive behavioral indexes used for evaluating rehabilitation remain unexplored. The study aimed to examine the effects of two types of combined exercise-cognitive training on stroke patients with cognitive dysfunction, focusing on neural and behavioral markers. 39 patients were randomly assigned to sequential exercise-cognitive training, simultaneous exercise-cognitive training or active control groups and underwent 60 minutes/day training, 3 days/week, for 12 weeks. 29 patients ultimately completed the training. The markers/indexes included cognitive function, physical function, instrumental activities of daily living, and caregiver strain. Cognitive function included working memory task performance, neurophysiological markers, and cognitive indexes. The results indicated no d-prime difference between groups after the training. The simultaneous training demonstrated significant improvements in the neurophysiological marker of P300 and theta coherence compared to the other groups. Moreover, the simultaneous training also led to significant enhancements in physical function, as measured by the Rivermead Mobility Index, comparing to the other groups. Further analysis contrasting the two exercise-cognitive trainings revealed that improvements in cognition and multifaceted domains (i.e., instrumental activities of daily living and caregiver strain) were manifested in the simultaneous training. Together with the neural markers identified in the current interventions, the differential impacts of the two interventions indicates the potential of technology-driven and personalized rehabilitation in post-stroke patients.
{"title":"Characterizing Two Hybrid Exercise-Cognitive Training Interventions With Neurophysiological and Behavioral Indexes in Post-Stroke Patients With Cognitive Dysfunction: A Randomized Controlled Trial","authors":"Chia-Lun Liu;Shou-Hsien Huang;Wei-Chun Wang;Chih-Kuang Chen;Ken-Hsien Su;Ching-Yi Wu","doi":"10.1109/TNSRE.2024.3482328","DOIUrl":"10.1109/TNSRE.2024.3482328","url":null,"abstract":"Combined exercise and cognitive training have been evidenced to be effective in cognitive and physical functions in post-stroke survivors. Recent interest has gradually shifted to technology-aided cognitive rehabilitation. However, clear neural makers or comprehensive behavioral indexes used for evaluating rehabilitation remain unexplored. The study aimed to examine the effects of two types of combined exercise-cognitive training on stroke patients with cognitive dysfunction, focusing on neural and behavioral markers. 39 patients were randomly assigned to sequential exercise-cognitive training, simultaneous exercise-cognitive training or active control groups and underwent 60 minutes/day training, 3 days/week, for 12 weeks. 29 patients ultimately completed the training. The markers/indexes included cognitive function, physical function, instrumental activities of daily living, and caregiver strain. Cognitive function included working memory task performance, neurophysiological markers, and cognitive indexes. The results indicated no d-prime difference between groups after the training. The simultaneous training demonstrated significant improvements in the neurophysiological marker of P300 and theta coherence compared to the other groups. Moreover, the simultaneous training also led to significant enhancements in physical function, as measured by the Rivermead Mobility Index, comparing to the other groups. Further analysis contrasting the two exercise-cognitive trainings revealed that improvements in cognition and multifaceted domains (i.e., instrumental activities of daily living and caregiver strain) were manifested in the simultaneous training. Together with the neural markers identified in the current interventions, the differential impacts of the two interventions indicates the potential of technology-driven and personalized rehabilitation in post-stroke patients.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3913-3922"},"PeriodicalIF":4.8,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10720930","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142464254","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 : 2024-10-17DOI: 10.1109/TNSRE.2024.3482470
Pengju Liu;Xinyi Yang;Fenglin Han;Guangshuai Peng;Qiao Li;Liping Huang;Lizhen Wang;Yubo Fan
Clinical studies have proved significant improvements in hand motor function in stroke patients when assisted by robotic devices. However, there were few studies on neural activity changes in the brain during execution. This study aimed to investigate the brain activation pattern caused by soft rehabilitation glove and virtual reality scenes. Twenty healthy subjects and twenty stroke patients were recruited to complete three controlled trials: grasping passively with robotic glove assistance (RA), watching grasping movement video in virtual reality (VR), and the joint use of robotic glove and virtual reality (VRA). Neural activity in the prefrontal cortex, motor cortex and occipital lobe was synchronously collected by the functional near-infrared spectroscopy (fNIRS) device. Activation level and functional connectivity of these brain regions were subsequently calculated and statistically analyzed. For both groups, the VR and VRA tasks induced activation of larger cortical areas. Stroke group had higher average cortical activation in all three tasks compared to healthy group, especially in the prefrontal cortex ( ${P} lt 0.05$ ). Functional connectivity was weaker in the stroke group than in the healthy group across most regions, but was significantly stronger across some regions of the right hemisphere. These findings suggest significant differences in activation patterns across three tasks. In addition, multi-sensory stimulation can promote functional communication between more brain regions in patients. It has potential for neuromodulation in rehabilitation training by setting up different sensory stimulation modalities.
{"title":"Brain Activation Pattern Caused by Soft Rehabilitation Glove and Virtual Reality Scenes: A Pilot fNIRS Study","authors":"Pengju Liu;Xinyi Yang;Fenglin Han;Guangshuai Peng;Qiao Li;Liping Huang;Lizhen Wang;Yubo Fan","doi":"10.1109/TNSRE.2024.3482470","DOIUrl":"10.1109/TNSRE.2024.3482470","url":null,"abstract":"Clinical studies have proved significant improvements in hand motor function in stroke patients when assisted by robotic devices. However, there were few studies on neural activity changes in the brain during execution. This study aimed to investigate the brain activation pattern caused by soft rehabilitation glove and virtual reality scenes. Twenty healthy subjects and twenty stroke patients were recruited to complete three controlled trials: grasping passively with robotic glove assistance (RA), watching grasping movement video in virtual reality (VR), and the joint use of robotic glove and virtual reality (VRA). Neural activity in the prefrontal cortex, motor cortex and occipital lobe was synchronously collected by the functional near-infrared spectroscopy (fNIRS) device. Activation level and functional connectivity of these brain regions were subsequently calculated and statistically analyzed. For both groups, the VR and VRA tasks induced activation of larger cortical areas. Stroke group had higher average cortical activation in all three tasks compared to healthy group, especially in the prefrontal cortex (\u0000<inline-formula> <tex-math>${P} lt 0.05$ </tex-math></inline-formula>\u0000). Functional connectivity was weaker in the stroke group than in the healthy group across most regions, but was significantly stronger across some regions of the right hemisphere. These findings suggest significant differences in activation patterns across three tasks. In addition, multi-sensory stimulation can promote functional communication between more brain regions in patients. It has potential for neuromodulation in rehabilitation training by setting up different sensory stimulation modalities.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3848-3857"},"PeriodicalIF":4.8,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10721199","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142464253","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 : 2024-10-16DOI: 10.1109/TNSRE.2024.3481886
Yifan Zhang;Yang Yu;Hao Li;Anqi Wu;Ling-Li Zeng;Dewen Hu
Consumer-grade Electroencephalography (EEG) devices equipped with few electrodes often suffer from low spatial resolution, hindering the accurate capture of intricate brain activity patterns. To address this issue, we propose MASER, a novel super-resolution approach for EEG recording. In MASER, we design the eMamba block for extracting EEG features based on the principles of state space models (SSMs). We further stack eMamba blocks to form a low-resolution feature extractor and a high-resolution signal predictor, which enhances the feature representation. During the training of MASER, we fully consider the characteristics of multidimensional biological series signals, incorporating a smoothness constraint loss to achieve more consistent high-resolution reconstructions. MASER pioneers EEG-oriented state space modeling, effectively capturing the temporal dynamics and latent states, thereby revealing complex neural interactions over time. Extensive experiments show that the proposed MASER outperforms the state-of-the-art methods in super-resolution quality on two public EEG datasets, with normalized mean square error reduced by 16.25% and Pearson correlation improved by 1.13%. Moreover, a case study of motor imagery recognition highlights the advantages conferred by high-resolution EEG signals. With a 4x increase in spatial resolution by MASER, the recognition accuracy improves by 5.74%, implying a significant performance elevation in brain-computer interface (BCI) command mapping. By enhancing the spatial resolution of EEG signals, MASER makes EEG-based applications more accessible, reducing cost and setup time while maintaining high performance across various domains such as gaming, education, and healthcare.
{"title":"MASER: Enhancing EEG Spatial Resolution With State Space Modeling","authors":"Yifan Zhang;Yang Yu;Hao Li;Anqi Wu;Ling-Li Zeng;Dewen Hu","doi":"10.1109/TNSRE.2024.3481886","DOIUrl":"10.1109/TNSRE.2024.3481886","url":null,"abstract":"Consumer-grade Electroencephalography (EEG) devices equipped with few electrodes often suffer from low spatial resolution, hindering the accurate capture of intricate brain activity patterns. To address this issue, we propose MASER, a novel super-resolution approach for EEG recording. In MASER, we design the eMamba block for extracting EEG features based on the principles of state space models (SSMs). We further stack eMamba blocks to form a low-resolution feature extractor and a high-resolution signal predictor, which enhances the feature representation. During the training of MASER, we fully consider the characteristics of multidimensional biological series signals, incorporating a smoothness constraint loss to achieve more consistent high-resolution reconstructions. MASER pioneers EEG-oriented state space modeling, effectively capturing the temporal dynamics and latent states, thereby revealing complex neural interactions over time. Extensive experiments show that the proposed MASER outperforms the state-of-the-art methods in super-resolution quality on two public EEG datasets, with normalized mean square error reduced by 16.25% and Pearson correlation improved by 1.13%. Moreover, a case study of motor imagery recognition highlights the advantages conferred by high-resolution EEG signals. With a 4x increase in spatial resolution by MASER, the recognition accuracy improves by 5.74%, implying a significant performance elevation in brain-computer interface (BCI) command mapping. By enhancing the spatial resolution of EEG signals, MASER makes EEG-based applications more accessible, reducing cost and setup time while maintaining high performance across various domains such as gaming, education, and healthcare.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3858-3868"},"PeriodicalIF":4.8,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10720236","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142464256","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 : 2024-10-14DOI: 10.1109/TNSRE.2024.3479283
Longbao Chen;Ding Zhou;Yuquan Leng
Exoskeleton robots enable individuals with impaired physical functions to perform daily activities and maintain independence. However, the discomfort experienced by users when using these devices may limit the application scope of exoskeleton robots. Therefore, this paper systematically defines and analyzes the key design factors affecting the wearing comfort of rigid exoskeleton robots by differentiating and discussing the characteristics of traditional exoskeleton robots and exoskeleton robots equipped with the self-alignment mechanism based on addressing misalignment issues. Furthermore, the various structural configurations of the Physical Human-Robot Attachment Interface (PHRAI) and related quantitative evaluation indicators are explored in depth, and the advantages and limitations of structural customized design methods combining parametric design, Three-Dimensional (3D) scanning, and 3D printing technology are evaluated. Finally, the current concerns in the research field and potential solution strategies are proposed, aiming to provide directional guidance to optimize future exoskeleton robots. The research findings are of significant value for enhancing the comfort of wearing exoskeleton robots and provide valuable theoretical and practical references for future research.
{"title":"A Systematic Review on Rigid Exoskeleton Robot Design for Wearing Comfort: Joint Self-Alignment, Attachment Interface, and Structure Customization","authors":"Longbao Chen;Ding Zhou;Yuquan Leng","doi":"10.1109/TNSRE.2024.3479283","DOIUrl":"10.1109/TNSRE.2024.3479283","url":null,"abstract":"Exoskeleton robots enable individuals with impaired physical functions to perform daily activities and maintain independence. However, the discomfort experienced by users when using these devices may limit the application scope of exoskeleton robots. Therefore, this paper systematically defines and analyzes the key design factors affecting the wearing comfort of rigid exoskeleton robots by differentiating and discussing the characteristics of traditional exoskeleton robots and exoskeleton robots equipped with the self-alignment mechanism based on addressing misalignment issues. Furthermore, the various structural configurations of the Physical Human-Robot Attachment Interface (PHRAI) and related quantitative evaluation indicators are explored in depth, and the advantages and limitations of structural customized design methods combining parametric design, Three-Dimensional (3D) scanning, and 3D printing technology are evaluated. Finally, the current concerns in the research field and potential solution strategies are proposed, aiming to provide directional guidance to optimize future exoskeleton robots. The research findings are of significant value for enhancing the comfort of wearing exoskeleton robots and provide valuable theoretical and practical references for future research.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3815-3827"},"PeriodicalIF":4.8,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10716507","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142464252","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 : 2024-10-10DOI: 10.1109/TNSRE.2024.3477607
Yunfei Liu;Xu Zhang;Haowen Zhao;Xiang Chen;Bo Yao
Decoding movement intentions from motor unit (MU) activities remains an ongoing challenge, which restricts our comprehension of the intricate transition mechanism from microscopic neural drive to macroscopic movements. This study presents an innovative neuro-musculoskeletal (NMS) model driven by MU activities for online estimation of continuous wrist movements. The proposed model employs a physiological and comprehensive utilization of MU firings and waveforms, thus facilitating the localization of MUs to muscle-tendon units (MTU) as well as the computation of MU-specific neural excitation. Subsequently, the MU-specific neural excitation was integrated to form the MTU-specific neural excitation, which were then inputted into a musculoskeletal model to accomplish the joint angle estimation. To assess the effectiveness of this model, high-density surface electromyography and angular data were collected from the forearms of eight subjects during their performance of wrist flexion-extension task. Two pieces of $8times 8$ electrode arrays and a motion capture system were employed for data acquisition. Following offline model calibration with a global optimization algorithm, online angle estimation results demonstrated a significant superiority of the proposed model over the state-of-the-art NMS models (p < 0.05), yielding the lowest normalized root mean square error ( $0.10~pm ~0.02$ ) and the highest determination coefficient ( $0.87~pm ~0.06$ ). This study provides a novel idea for the decoding of joint movements from MU activities. The research findings hold the potential to advance the development of NMS models towards the control of multiple degrees of freedom, with promising applications in the fields of motor control, biomechanics, and neuro-rehabilitation engineering.
从运动单元（MU）活动中解码运动意图仍然是一个持续的挑战，这限制了我们对从微观神经驱动到宏观运动的复杂过渡机制的理解。本研究提出了一种由运动单元活动驱动的创新型神经-肌肉-骨骼（NMS）模型，用于在线估计连续的手腕运动。所提出的模型从生理角度综合利用了肌肉单元的搏动和波形，从而有助于将肌肉单元定位到肌肉-肌腱单元（MTU），并计算特定于肌肉单元的神经兴奋。随后，MU 特定神经激励被整合为 MTU 特定神经激励，然后输入肌肉骨骼模型以完成关节角度估算。为了评估该模型的有效性，研究人员从八名受试者的前臂收集了他们在完成手腕屈伸任务时的高密度表面肌电图和角度数据。数据采集采用了两块 8 × 8 的电极阵列和运动捕捉系统。采用全局优化算法对模型进行离线校准后，在线角度估计结果表明，所提出的模型明显优于最先进的 NMS 模型（p < 0.05），归一化均方根误差最小（0.10 ± 0.02），确定系数最高（0.87 ± 0.06）。这项研究为从 MU 活动中解码关节运动提供了一种新的思路。研究成果有望推动 NMS 模型的发展，实现多自由度控制，在运动控制、生物力学和神经康复工程等领域具有广阔的应用前景。
{"title":"Neuro-Musculoskeletal Modeling for Online Estimation of Continuous Wrist Movements from Motor Unit Activities","authors":"Yunfei Liu;Xu Zhang;Haowen Zhao;Xiang Chen;Bo Yao","doi":"10.1109/TNSRE.2024.3477607","DOIUrl":"10.1109/TNSRE.2024.3477607","url":null,"abstract":"Decoding movement intentions from motor unit (MU) activities remains an ongoing challenge, which restricts our comprehension of the intricate transition mechanism from microscopic neural drive to macroscopic movements. This study presents an innovative neuro-musculoskeletal (NMS) model driven by MU activities for online estimation of continuous wrist movements. The proposed model employs a physiological and comprehensive utilization of MU firings and waveforms, thus facilitating the localization of MUs to muscle-tendon units (MTU) as well as the computation of MU-specific neural excitation. Subsequently, the MU-specific neural excitation was integrated to form the MTU-specific neural excitation, which were then inputted into a musculoskeletal model to accomplish the joint angle estimation. To assess the effectiveness of this model, high-density surface electromyography and angular data were collected from the forearms of eight subjects during their performance of wrist flexion-extension task. Two pieces of \u0000<inline-formula> <tex-math>$8times 8$ </tex-math></inline-formula>\u0000 electrode arrays and a motion capture system were employed for data acquisition. Following offline model calibration with a global optimization algorithm, online angle estimation results demonstrated a significant superiority of the proposed model over the state-of-the-art NMS models (p < 0.05), yielding the lowest normalized root mean square error (\u0000<inline-formula> <tex-math>$0.10~pm ~0.02$ </tex-math></inline-formula>\u0000) and the highest determination coefficient (\u0000<inline-formula> <tex-math>$0.87~pm ~0.06$ </tex-math></inline-formula>\u0000). This study provides a novel idea for the decoding of joint movements from MU activities. The research findings hold the potential to advance the development of NMS models towards the control of multiple degrees of freedom, with promising applications in the fields of motor control, biomechanics, and neuro-rehabilitation engineering.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3804-3814"},"PeriodicalIF":4.8,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10713454","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142400150","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 : 2024-10-09DOI: 10.1109/TNSRE.2024.3477003
Colum Crowe;Marco Sica;Lorna Kenny;Brendan O’Flynn;David Scott Mueller;Suzanne Timmons;John Barton;Salvatore Tedesco
Motor symptoms such as tremor and bradykinesia can develop concurrently in Parkinson’s disease; thus, the ideal home monitoring system should be capable of tracking symptoms continuously despite background noise from daily activities. The goal of this study is to demonstrate the feasibility of detecting symptom episodes in a free-living scenario, providing a higher level of interpretability to aid AI-powered decision-making. Machine learning models trained on wearable sensor data from scripted activities performed by participants in the lab and clinician ratings of the video recordings of these tasks identified tremor, bradykinesia, and dyskinesia in the supervised lab environment with a balanced accuracy of 83%, 75%, and 81%, respectively, when compared to the clinician ratings. The performance of the same models when evaluated on data from subjects performing unscripted activities unsupervised in their own homes achieved a balanced accuracy of 63%, 63%, and 67%, respectively, in comparison to self-assessment patient diaries, further highlighting their limitations. The ankle-worn sensor was found to be advantageous for the detection of dyskinesias but did not show an added benefit for tremor and bradykinesia detection here.
{"title":"Wearable-Enabled Algorithms for the Estimation of Parkinson’s Symptoms Evaluated in a Continuous Home Monitoring Setting Using Inertial Sensors","authors":"Colum Crowe;Marco Sica;Lorna Kenny;Brendan O’Flynn;David Scott Mueller;Suzanne Timmons;John Barton;Salvatore Tedesco","doi":"10.1109/TNSRE.2024.3477003","DOIUrl":"10.1109/TNSRE.2024.3477003","url":null,"abstract":"Motor symptoms such as tremor and bradykinesia can develop concurrently in Parkinson’s disease; thus, the ideal home monitoring system should be capable of tracking symptoms continuously despite background noise from daily activities. The goal of this study is to demonstrate the feasibility of detecting symptom episodes in a free-living scenario, providing a higher level of interpretability to aid AI-powered decision-making. Machine learning models trained on wearable sensor data from scripted activities performed by participants in the lab and clinician ratings of the video recordings of these tasks identified tremor, bradykinesia, and dyskinesia in the supervised lab environment with a balanced accuracy of 83%, 75%, and 81%, respectively, when compared to the clinician ratings. The performance of the same models when evaluated on data from subjects performing unscripted activities unsupervised in their own homes achieved a balanced accuracy of 63%, 63%, and 67%, respectively, in comparison to self-assessment patient diaries, further highlighting their limitations. The ankle-worn sensor was found to be advantageous for the detection of dyskinesias but did not show an added benefit for tremor and bradykinesia detection here.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3828-3836"},"PeriodicalIF":4.8,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10711881","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142390316","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 : 2024-10-03DOI: 10.1109/TNSRE.2024.3472063
Raul C. Sîmpetru;Daniela Souza de Oliveira;Matthias Ponfick;Alessandro Del Vecchio
The loss of bilateral hand function is a debilitating challenge for millions of individuals that suffered a motor-complete spinal cord injury (SCI). We have recently demonstrated in eight tetraplegic individuals the presence of highly functional spared spinal motor neurons in the extrinsic muscles of the hand that are still capable of generating proportional flexion and extension signals. In this work, we hypothesized that an artificial intelligence (AI) system could automatically learn the spared electromyographic (EMG) patterns that encode the attempted movements of the paralyzed digits. We constrained the AI to continuously output the attempted movements in the form of a digital hand so that this signal could be used to control any assistive system (e.g. exoskeletons, electrical stimulation). We trained a convolutional neural network using data from 13 uninjured (control) participants and 8 tetraplegic participants (7 motor-complete, 1 incomplete) to study the latent space learned by the AI. Our model can automatically differentiate between eight different hand movements, including individual finger flexions, grasps, and pinches, achieving a mean accuracy of 98.3% within the SCI group. Analysis of the latent space of the model revealed that proportionally controllable movements exhibited an elliptical path, while movements lacking proportional control followed a chaotic trajectory. We found that proportional control of a movement can only be correctly estimated if the latent space embedding of the movement follows an elliptical path (correlation =0.73; p <0.001). These findings emphasize the reliability of the proposed system for closed-loop applications that require an accurate estimate of spinal cord motor output.
{"title":"Identification of Spared and Proportionally Controllable Hand Motor Dimensions in Motor Complete Spinal Cord Injuries Using Latent Manifold Analysis","authors":"Raul C. Sîmpetru;Daniela Souza de Oliveira;Matthias Ponfick;Alessandro Del Vecchio","doi":"10.1109/TNSRE.2024.3472063","DOIUrl":"10.1109/TNSRE.2024.3472063","url":null,"abstract":"The loss of bilateral hand function is a debilitating challenge for millions of individuals that suffered a motor-complete spinal cord injury (SCI). We have recently demonstrated in eight tetraplegic individuals the presence of highly functional spared spinal motor neurons in the extrinsic muscles of the hand that are still capable of generating proportional flexion and extension signals. In this work, we hypothesized that an artificial intelligence (AI) system could automatically learn the spared electromyographic (EMG) patterns that encode the attempted movements of the paralyzed digits. We constrained the AI to continuously output the attempted movements in the form of a digital hand so that this signal could be used to control any assistive system (e.g. exoskeletons, electrical stimulation). We trained a convolutional neural network using data from 13 uninjured (control) participants and 8 tetraplegic participants (7 motor-complete, 1 incomplete) to study the latent space learned by the AI. Our model can automatically differentiate between eight different hand movements, including individual finger flexions, grasps, and pinches, achieving a mean accuracy of 98.3% within the SCI group. Analysis of the latent space of the model revealed that proportionally controllable movements exhibited an elliptical path, while movements lacking proportional control followed a chaotic trajectory. We found that proportional control of a movement can only be correctly estimated if the latent space embedding of the movement follows an elliptical path (correlation =0.73; p <0.001). These findings emphasize the reliability of the proposed system for closed-loop applications that require an accurate estimate of spinal cord motor output.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3741-3750"},"PeriodicalIF":4.8,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10703163","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142371742","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 : 2024-10-02DOI: 10.1109/TNSRE.2024.3472088
Samuel Diop;Nouha Essid;François Jouen;Jean Bergounioux;Imen Trabelsi
Infantile spasms are a severe epileptic syndrome characterized by short muscular contractions lasting from 0.5 to 2 seconds. They are often misdiagnosed due to their atypical presentation, and treatment is frequently delayed, leading to stagnation or regression in psychomotor development and significant cognitive and motor sequelae. One promising approach to addressing this issue is the use of markerless computer vision techniques. In this paper, we introduce a novel approach for recognizing infantile spasms based exclusively on video data. We utilize an expanded 3D neural network pre-trained on an extensive human action recognition dataset called Kinetics. By employing this model, we extract features from short segments of varying sizes sampled from seizure videos, which allows us to effectively capture the spatio-temporal characteristics of infantile spasms. We then apply multiple classifiers to perform binary classification on these extracted features. The best system achieved an average area under the ROC curve of $0.813pm 0.058$ for a 3-second window.
{"title":"Adapting Action Recognition Neural Networks for Automated Infantile Spasm Detection","authors":"Samuel Diop;Nouha Essid;François Jouen;Jean Bergounioux;Imen Trabelsi","doi":"10.1109/TNSRE.2024.3472088","DOIUrl":"10.1109/TNSRE.2024.3472088","url":null,"abstract":"Infantile spasms are a severe epileptic syndrome characterized by short muscular contractions lasting from 0.5 to 2 seconds. They are often misdiagnosed due to their atypical presentation, and treatment is frequently delayed, leading to stagnation or regression in psychomotor development and significant cognitive and motor sequelae. One promising approach to addressing this issue is the use of markerless computer vision techniques. In this paper, we introduce a novel approach for recognizing infantile spasms based exclusively on video data. We utilize an expanded 3D neural network pre-trained on an extensive human action recognition dataset called Kinetics. By employing this model, we extract features from short segments of varying sizes sampled from seizure videos, which allows us to effectively capture the spatio-temporal characteristics of infantile spasms. We then apply multiple classifiers to perform binary classification on these extracted features. The best system achieved an average area under the ROC curve of \u0000<inline-formula> <tex-math>$0.813pm 0.058$ </tex-math></inline-formula>\u0000 for a 3-second window.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3751-3760"},"PeriodicalIF":4.8,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10703170","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142365131","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：