Conventional thresholding techniques for graph theory analysis, such as absolute, proportional and mean degree, have often been used in characterizing human brain networks under different mental disorders, such as mental stress. However, these approaches may not always be reliable as conventional thresholding approaches are subjected to human biases. Using a mental resilience study, we investigate if data-driven thresholding techniques such as Global Cost Efficiency (GCE-abs) and Orthogonal Minimum Spanning Trees (OMSTs) could provide equivalent results, whilst eliminating human biases. We implemented Phase Slope Index (PSI) to compute effective brain connectivity, and applied data-driven thresholding approaches to filter the brain networks in order to identify key features of low resilience within a cohort of healthy individuals. Our dataset encompassed resting-state EEG recordings gathered from a total of 36 participants (31 females and 5 males). Relevant features were extracted to train and validate a classifier model (Support Vector Machine, SVM). The detection of low stress resilience among healthy individuals using the SVM model scores an accuracy of 80.6% with GCE-abs, and 75% with OMSTs, respectively.
{"title":"Detection of Low Resilience Using Data-Driven Effective Connectivity Measures","authors":"Ayman Siddiqui;Rumaisa Abu Hasan;Syed Saad Azhar Ali;Irraivan Elamvazuthi;Cheng-Kai Lu;Tong Boon Tang","doi":"10.1109/TNSRE.2024.3465269","DOIUrl":"10.1109/TNSRE.2024.3465269","url":null,"abstract":"Conventional thresholding techniques for graph theory analysis, such as absolute, proportional and mean degree, have often been used in characterizing human brain networks under different mental disorders, such as mental stress. However, these approaches may not always be reliable as conventional thresholding approaches are subjected to human biases. Using a mental resilience study, we investigate if data-driven thresholding techniques such as Global Cost Efficiency (GCE-abs) and Orthogonal Minimum Spanning Trees (OMSTs) could provide equivalent results, whilst eliminating human biases. We implemented Phase Slope Index (PSI) to compute effective brain connectivity, and applied data-driven thresholding approaches to filter the brain networks in order to identify key features of low resilience within a cohort of healthy individuals. Our dataset encompassed resting-state EEG recordings gathered from a total of 36 participants (31 females and 5 males). Relevant features were extracted to train and validate a classifier model (Support Vector Machine, SVM). The detection of low stress resilience among healthy individuals using the SVM model scores an accuracy of 80.6% with GCE-abs, and 75% with OMSTs, respectively.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3657-3668"},"PeriodicalIF":4.8,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10684775","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142286183","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 : 2024-09-20DOI: 10.1109/TNSRE.2024.3465016
Kalyn M. Kearney;Tamara Ordonez Diaz;Joel B. Harley;Jennifer A. Nichols
Muscle fatigue impacts upper extremity function but is often overlooked in biomechanical models. The present work leveraged a transfer learning approach to improve torque predictions during fatiguing upper extremity movements. We developed two artificial neural networks to model sustained elbow flexion: one trained solely on recorded data (i.e., direct learning) and one pre-trained on simulated data and fine-tuned on recorded data (i.e., transfer learning). We simulated muscle activations and joint torques using a musculoskeletal model and a muscle fatigue model (n = 1,701 simulations). We also recorded static subject-specific features (e.g., anthropometric measurements) and dynamic muscle activations and torques during sustained elbow flexion in healthy young adults (n = 25 subjects). Using the simulated dataset, we pre-trained a long short-term memory neural network (LSTM) to regress fatiguing elbow flexion torque from muscle activations. We concatenated this pre-trained LSTM with a feedforward architecture, and fine-tuned the model on recorded muscle activations and static features to predict elbow flexion torques. We trained a similar architecture solely on the recorded data and compared each neural network’s predictions on 5 leave-out subjects’ data. The transfer learning model outperformed the direct learning model, as indicated by a decrease of 24.9% in their root-mean-square-errors (6.22 Nm and 8.28 Nm, respectively). The transfer learning model and direct learning model outperformed analogous musculoskeletal simulations, which consistently underpredicted elbow flexion torque. Our results suggest that transfer learning from simulated to recorded datasets can decrease reliance on assumptions inherent to biomechanical models and yield predictions robust to real-world conditions.
{"title":"From Simulation to Reality: Predicting Torque With Fatigue Onset via Transfer Learning","authors":"Kalyn M. Kearney;Tamara Ordonez Diaz;Joel B. Harley;Jennifer A. Nichols","doi":"10.1109/TNSRE.2024.3465016","DOIUrl":"10.1109/TNSRE.2024.3465016","url":null,"abstract":"Muscle fatigue impacts upper extremity function but is often overlooked in biomechanical models. The present work leveraged a transfer learning approach to improve torque predictions during fatiguing upper extremity movements. We developed two artificial neural networks to model sustained elbow flexion: one trained solely on recorded data (i.e., direct learning) and one pre-trained on simulated data and fine-tuned on recorded data (i.e., transfer learning). We simulated muscle activations and joint torques using a musculoskeletal model and a muscle fatigue model (n = 1,701 simulations). We also recorded static subject-specific features (e.g., anthropometric measurements) and dynamic muscle activations and torques during sustained elbow flexion in healthy young adults (n = 25 subjects). Using the simulated dataset, we pre-trained a long short-term memory neural network (LSTM) to regress fatiguing elbow flexion torque from muscle activations. We concatenated this pre-trained LSTM with a feedforward architecture, and fine-tuned the model on recorded muscle activations and static features to predict elbow flexion torques. We trained a similar architecture solely on the recorded data and compared each neural network’s predictions on 5 leave-out subjects’ data. The transfer learning model outperformed the direct learning model, as indicated by a decrease of 24.9% in their root-mean-square-errors (6.22 Nm and 8.28 Nm, respectively). The transfer learning model and direct learning model outperformed analogous musculoskeletal simulations, which consistently underpredicted elbow flexion torque. Our results suggest that transfer learning from simulated to recorded datasets can decrease reliance on assumptions inherent to biomechanical models and yield predictions robust to real-world conditions.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3669-3676"},"PeriodicalIF":4.8,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10684821","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142286184","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 : 2024-09-17DOI: 10.1109/TNSRE.2024.3462392
Tongyue He;Junxin Chen;Xu Xu;Giancarlo Fortino;Wei Wang
With the development of digital medical technology, ubiquitous smartphones are emerging as valuable tools for the detection of complex and elusive diseases. This paper exploits smartphone walking recording for early detection of Parkinson’s disease (PD) and finds that walking recording empowered by deep learning is a valid digital biomarker for early-recognizing PD patients. Specifically, the inertial sensor data is preprocessed, including normalization, scaling, and rotation, and then the processed data is fed into the proposed deep NeuroEnhanceNet. Finally, determine the individual prediction score using the PD-prone strategy and generate the detection results. The proposed deep NeuroEnhanceNet, specifically designed for inertial sensor data, can focus on both the long-term data characteristics within a single channel and the inter-channel correlations. Our method obtains a low false negative rate of 0.053 for the early detection of PD. We further analyze and compare the effectiveness of digital biomarkers captured from the walking and resting processes for early detection of PD. All the code for this work is available at: https://github.com/heyiyia/NeuroEnhanceNet .
{"title":"Early Detection of Parkinson’s Disease Using Deep NeuroEnhanceNet With Smartphone Walking Recordings","authors":"Tongyue He;Junxin Chen;Xu Xu;Giancarlo Fortino;Wei Wang","doi":"10.1109/TNSRE.2024.3462392","DOIUrl":"10.1109/TNSRE.2024.3462392","url":null,"abstract":"With the development of digital medical technology, ubiquitous smartphones are emerging as valuable tools for the detection of complex and elusive diseases. This paper exploits smartphone walking recording for early detection of Parkinson’s disease (PD) and finds that walking recording empowered by deep learning is a valid digital biomarker for early-recognizing PD patients. Specifically, the inertial sensor data is preprocessed, including normalization, scaling, and rotation, and then the processed data is fed into the proposed deep NeuroEnhanceNet. Finally, determine the individual prediction score using the PD-prone strategy and generate the detection results. The proposed deep NeuroEnhanceNet, specifically designed for inertial sensor data, can focus on both the long-term data characteristics within a single channel and the inter-channel correlations. Our method obtains a low false negative rate of 0.053 for the early detection of PD. We further analyze and compare the effectiveness of digital biomarkers captured from the walking and resting processes for early detection of PD. All the code for this work is available at: \u0000<uri>https://github.com/heyiyia/NeuroEnhanceNet</uri>\u0000.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3603-3614"},"PeriodicalIF":4.8,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10681495","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142267740","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 : 2024-09-16DOI: 10.1109/TNSRE.2024.3461589
Aleksandra Badura;Maria Bienkowska;Andrzej Mysliwiec;Ewa Pietka
This study aims to design a time-continuous pain level assessment system for temporomandibular joint therapy. Our objectives cover verifying literature suggestions on pain stimulus, protocols for collecting reference data, and continuous pain recognition models. We use two types of pain data acquired during 1) heat stimulation and 2) temporomandibular joint therapy. Thirty-six electrodermal activity (EDA) features are determined to build a binary classification model. The experimental dataset is used to train the initial model that produces pseudo-labels for weakly-labeled clinical data. In training the final long short-term memory (LSTM) model, we propose a novel multivariate loss involving, i.a., dynamometer data. Significant differences are found between EDA features extracted from experimental and clinical datasets in pain and no pain events. The classification model is validated at different stages of the model development. The final model classifies each four-second frame with a mean accuracy of 0.89 and an F1 score of 0.85. Our study introduces the dynamometer as a novel source of pain-feeling indications that meets the challenges given in the literature: data can be acquired in various procedures and from patients with limited abilities. The main contribution of the study is to design the first time-continuous and short-term pain assessment system for a clinical setting.
{"title":"Continuous Short-Term Pain Assessment in Temporomandibular Joint Therapy Using LSTM Models Supported by Heat-Induced Pain Data Patterns","authors":"Aleksandra Badura;Maria Bienkowska;Andrzej Mysliwiec;Ewa Pietka","doi":"10.1109/TNSRE.2024.3461589","DOIUrl":"10.1109/TNSRE.2024.3461589","url":null,"abstract":"This study aims to design a time-continuous pain level assessment system for temporomandibular joint therapy. Our objectives cover verifying literature suggestions on pain stimulus, protocols for collecting reference data, and continuous pain recognition models. We use two types of pain data acquired during 1) heat stimulation and 2) temporomandibular joint therapy. Thirty-six electrodermal activity (EDA) features are determined to build a binary classification model. The experimental dataset is used to train the initial model that produces pseudo-labels for weakly-labeled clinical data. In training the final long short-term memory (LSTM) model, we propose a novel multivariate loss involving, i.a., dynamometer data. Significant differences are found between EDA features extracted from experimental and clinical datasets in pain and no pain events. The classification model is validated at different stages of the model development. The final model classifies each four-second frame with a mean accuracy of 0.89 and an F1 score of 0.85. Our study introduces the dynamometer as a novel source of pain-feeling indications that meets the challenges given in the literature: data can be acquired in various procedures and from patients with limited abilities. The main contribution of the study is to design the first time-continuous and short-term pain assessment system for a clinical setting.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3565-3576"},"PeriodicalIF":4.8,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10680582","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142267741","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 : 2024-09-16DOI: 10.1109/TNSRE.2024.3461339
Linlin Wang;Mingai Li;Dongqin Xu;Yufei Yang
Decoding motor imagery (MI) using deep learning in cortical level has potential in brain computer interface based intelligent rehabilitation. However, a mass of dipoles is inconvenient to extract the personalized features and requires a more complex neural network. In consideration of the structural and functional similarity of the neurons in a neuroanatomical region, i.e., a region of interest (ROI), we propose that the comprehensive performance of each ROI may be reflected by a specific representative dipole (RD), and the time-frequency spectrums of all RDs are applied simultaneously to Random Forest algorithm to give a quantitative metric of each ROI importance (RI). Then, the more divided sub-band spectral powers are reinforced by RI, and they are interpolated to a 2-dimensional (2D) plane transformed from 3D space of all RDs, yielding an ensemble representation of RD feature image sequences (ERDFIS). Furthermore, a lightweight network, including 2D separable convolution and gated recurrent unit (2DSCG), is developed to extract and classify the frequency-spatial and temporal features from ERDFIS, forming a novel MI decoding method in cortical level (called ERDFIS-2DSCG). Based on two public datasets, the decoding accuracies of ten-fold cross-validation are 89.89% and 94.35%, respectively. The results suggest that RD can embody the overall property of ROI in time-frequency-space domains, and ROI importance is helpful to highlight the subject-based characteristics of MI-EEG. Meanwhile, 2DSCG is matched well with ERDFIS, jointly improving the decoding performance.
利用皮层深度学习对运动图像（MI）进行解码，在基于脑计算机接口的智能康复领域大有可为。然而，大量偶极子不便提取个性化特征，需要更复杂的神经网络。考虑到神经解剖区域（即感兴趣区（ROI））内神经元在结构和功能上的相似性，我们提出每个感兴趣区的综合表现可以通过一个特定的代表性偶极子（RD）来反映，并将所有 RD 的时频谱同时应用于随机森林算法，以给出每个感兴趣区重要性（RI）的量化指标。然后，通过 RI 强化较分散的子带频谱功率，并将其插值到从所有 RD 的三维空间转换而来的二维（2D）平面，从而得到 RD 特征图像序列的集合表示（ERDFIS）。此外，还开发了一种轻量级网络，包括二维可分离卷积和门控递归单元（2DSCG），用于从 ERDFIS 中提取频率-空间和时间特征并对其进行分类，从而形成一种新颖的皮层 MI 解码方法（称为 ERDFIS-2DSCG）。基于两个公开数据集，十倍交叉验证的解码准确率分别为 89.89% 和 94.35%。结果表明，RD能体现ROI在时频域的整体特性，ROI的重要性有助于突出MI-EEG的主体特征。同时，2DSCG与ERDFIS匹配良好，共同提高了解码性能。
{"title":"Cortical ROI Importance Improves MI Decoding From EEG Using Fused Light Neural Network","authors":"Linlin Wang;Mingai Li;Dongqin Xu;Yufei Yang","doi":"10.1109/TNSRE.2024.3461339","DOIUrl":"10.1109/TNSRE.2024.3461339","url":null,"abstract":"Decoding motor imagery (MI) using deep learning in cortical level has potential in brain computer interface based intelligent rehabilitation. However, a mass of dipoles is inconvenient to extract the personalized features and requires a more complex neural network. In consideration of the structural and functional similarity of the neurons in a neuroanatomical region, i.e., a region of interest (ROI), we propose that the comprehensive performance of each ROI may be reflected by a specific representative dipole (RD), and the time-frequency spectrums of all RDs are applied simultaneously to Random Forest algorithm to give a quantitative metric of each ROI importance (RI). Then, the more divided sub-band spectral powers are reinforced by RI, and they are interpolated to a 2-dimensional (2D) plane transformed from 3D space of all RDs, yielding an ensemble representation of RD feature image sequences (ERDFIS). Furthermore, a lightweight network, including 2D separable convolution and gated recurrent unit (2DSCG), is developed to extract and classify the frequency-spatial and temporal features from ERDFIS, forming a novel MI decoding method in cortical level (called ERDFIS-2DSCG). Based on two public datasets, the decoding accuracies of ten-fold cross-validation are 89.89% and 94.35%, respectively. The results suggest that RD can embody the overall property of ROI in time-frequency-space domains, and ROI importance is helpful to highlight the subject-based characteristics of MI-EEG. Meanwhile, 2DSCG is matched well with ERDFIS, jointly improving the decoding performance.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3636-3646"},"PeriodicalIF":4.8,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10680573","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142286182","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 : 2024-09-13DOI: 10.1109/TNSRE.2024.3460348
Boxuan Wei;Lu Xu;Jicong Zhang
Seizure prediction using EEG has significant implications for the daily monitoring and treatment of epilepsy patients. However, the task is challenging due to the underlying spatiotemporal correlations and patient heterogeneity. Traditional methods often use large-scale models with independent components to capture the spatial and temporal features of EEG separately or explore shared patterns among patients with the help of pre-defined functional connectivity. In this paper, we propose a compact model, called the graph convolutional network based on adaptive functional connectivity (AFC-GCN), for seizure prediction. The model can adaptively infer evolution of functional connectivity in epilepsy patients during seizures through data-driven methods and synchronously analyze spatiotemporal response of functional connectivity in multiple topologies. On CHB-MIT datasets, the experimental results demonstrate that AFC-GCN achieves accurate and robust performance with low complexity. (AUC: 0.9820, accuracy: 0.9815, sensitivity: 0.9802, FPR: 0.0172). The proposed method has the potential to predict seizure during daily monitoring.
{"title":"A Compact Graph Convolutional Network With Adaptive Functional Connectivity for Seizure Prediction","authors":"Boxuan Wei;Lu Xu;Jicong Zhang","doi":"10.1109/TNSRE.2024.3460348","DOIUrl":"10.1109/TNSRE.2024.3460348","url":null,"abstract":"Seizure prediction using EEG has significant implications for the daily monitoring and treatment of epilepsy patients. However, the task is challenging due to the underlying spatiotemporal correlations and patient heterogeneity. Traditional methods often use large-scale models with independent components to capture the spatial and temporal features of EEG separately or explore shared patterns among patients with the help of pre-defined functional connectivity. In this paper, we propose a compact model, called the graph convolutional network based on adaptive functional connectivity (AFC-GCN), for seizure prediction. The model can adaptively infer evolution of functional connectivity in epilepsy patients during seizures through data-driven methods and synchronously analyze spatiotemporal response of functional connectivity in multiple topologies. On CHB-MIT datasets, the experimental results demonstrate that AFC-GCN achieves accurate and robust performance with low complexity. (AUC: 0.9820, accuracy: 0.9815, sensitivity: 0.9802, FPR: 0.0172). The proposed method has the potential to predict seizure during daily monitoring.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3531-3542"},"PeriodicalIF":4.8,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10680083","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142267745","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 : 2024-09-13DOI: 10.1109/TNSRE.2024.3459924
Gang Wang;Long Jin;Jiliang Zhang;Xiaoqin Duan;Jiang Yi;Mingming Zhang;Zhongbo Sun
Decoding continuous human motion from surface electromyography (sEMG) in advance is crucial for improving the intelligence of exoskeleton robots. However, incomplete sEMG signals are prevalent on account of unstable data transmission, sensor malfunction, and electrode sheet detachment. These non-ideal factors severely compromise the accuracy of continuous motion recognition and the reliability of clinical applications. To tackle this challenge, this paper develops a multi-task parallel learning framework for continuous motion estimation with incomplete sEMG signals. Concretely, a residual network is incorporated into a recurrent neural network to integrate the information flow of hidden states and reconstruct random and consecutive missing sEMG signals. The attention mechanism is applied for redistributing the distribution of weights. A jointly optimized loss function is devised to enable training the model for simultaneously dealing with signal anomalies/absences and multi-joint continuous motion estimation. The proposed model is implemented for estimating hip, knee, and ankle joint angles of physically competent individuals and patients during diverse exercises. Experimental results indicate that the estimation root-mean-square errors with 60% missing sEMG signals steadily converges to below 5 degrees. Even with multi-channel electrode sheet shedding, our model still demonstrates cutting-edge estimation performance, errors only marginally increase 1 degree.
{"title":"Recurrent Neural Network Enabled Continuous Motion Estimation of Lower Limb Joints From Incomplete sEMG Signals","authors":"Gang Wang;Long Jin;Jiliang Zhang;Xiaoqin Duan;Jiang Yi;Mingming Zhang;Zhongbo Sun","doi":"10.1109/TNSRE.2024.3459924","DOIUrl":"10.1109/TNSRE.2024.3459924","url":null,"abstract":"Decoding continuous human motion from surface electromyography (sEMG) in advance is crucial for improving the intelligence of exoskeleton robots. However, incomplete sEMG signals are prevalent on account of unstable data transmission, sensor malfunction, and electrode sheet detachment. These non-ideal factors severely compromise the accuracy of continuous motion recognition and the reliability of clinical applications. To tackle this challenge, this paper develops a multi-task parallel learning framework for continuous motion estimation with incomplete sEMG signals. Concretely, a residual network is incorporated into a recurrent neural network to integrate the information flow of hidden states and reconstruct random and consecutive missing sEMG signals. The attention mechanism is applied for redistributing the distribution of weights. A jointly optimized loss function is devised to enable training the model for simultaneously dealing with signal anomalies/absences and multi-joint continuous motion estimation. The proposed model is implemented for estimating hip, knee, and ankle joint angles of physically competent individuals and patients during diverse exercises. Experimental results indicate that the estimation root-mean-square errors with 60% missing sEMG signals steadily converges to below 5 degrees. Even with multi-channel electrode sheet shedding, our model still demonstrates cutting-edge estimation performance, errors only marginally increase 1 degree.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3577-3589"},"PeriodicalIF":4.8,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10680114","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142267744","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 : 2024-09-13DOI: 10.1109/TNSRE.2024.3460485
M. C. Mauro;A. Fasano;M. Germanotta;L. Cortellini;S. Insalaco;A. Pavan;A. Comanducci;E. Guglielmelli;I. G. Aprile
Bilateral robotic rehabilitation has proven helpful in the recovery of upper limb motor function in patients with stroke, but its effects on the cortical reorganization mechanisms underlying recovery are still unclear. This pilot Randomized Controlled Trial (RCT) aimed to evaluate the effects on the interhemispheric balance of unilateral or bilateral robotic treatments in patients with subacute stroke, using Quantitative Electroencephalography (qEEG). 19 patients with ischemic stroke underwent a 30-session upper limb neurorehabilitation intervention using a bilateral upper limb exoskeleton. Each patient was randomly assigned to the bilateral (BG, n=10) or unilateral treatment group (UG, n=9). EEG evaluations were performed before (T0) and right after (T $0+text {)}$ the first treatment session, after 30 treatment sessions (T1), and at 1-week follow-up (T2), in both eyes open and eyes closed conditions. From the acquired EEG data, the pairwise-derived Brain Symmetry Index (pdBSI) was computed. In addition, clinical evaluation was performed at T0 and T1 with validated clinical scales. After the treatment, a significant improvement in clinical and EEG evaluations was observed for both groups, but only the BG showed reduced pdBSI in delta and theta bands. In the cluster of sensorimotor channels, there was no significant difference between groups. The observed changes were not maintained at follow-up. No significant changes were observed in the pdBSI after a single rehabilitation session. Results suggest that balancing of interhemispheric symmetry comes along with a clinical improvement in the upper extremity and that the pdBSI can be used to investigate the mechanisms of neuronal plasticity involved in robotic rehabilitation after stroke.
{"title":"Restoring of Interhemispheric Symmetry in Patients With Stroke Following Bilateral or Unilateral Robot-Assisted Upper-Limb Rehabilitation: A Pilot Randomized Controlled Trial","authors":"M. C. Mauro;A. Fasano;M. Germanotta;L. Cortellini;S. Insalaco;A. Pavan;A. Comanducci;E. Guglielmelli;I. G. Aprile","doi":"10.1109/TNSRE.2024.3460485","DOIUrl":"10.1109/TNSRE.2024.3460485","url":null,"abstract":"Bilateral robotic rehabilitation has proven helpful in the recovery of upper limb motor function in patients with stroke, but its effects on the cortical reorganization mechanisms underlying recovery are still unclear. This pilot Randomized Controlled Trial (RCT) aimed to evaluate the effects on the interhemispheric balance of unilateral or bilateral robotic treatments in patients with subacute stroke, using Quantitative Electroencephalography (qEEG). 19 patients with ischemic stroke underwent a 30-session upper limb neurorehabilitation intervention using a bilateral upper limb exoskeleton. Each patient was randomly assigned to the bilateral (BG, n=10) or unilateral treatment group (UG, n=9). EEG evaluations were performed before (T0) and right after (T\u0000<inline-formula> <tex-math>$0+text {)}$ </tex-math></inline-formula>\u0000 the first treatment session, after 30 treatment sessions (T1), and at 1-week follow-up (T2), in both eyes open and eyes closed conditions. From the acquired EEG data, the pairwise-derived Brain Symmetry Index (pdBSI) was computed. In addition, clinical evaluation was performed at T0 and T1 with validated clinical scales. After the treatment, a significant improvement in clinical and EEG evaluations was observed for both groups, but only the BG showed reduced pdBSI in delta and theta bands. In the cluster of sensorimotor channels, there was no significant difference between groups. The observed changes were not maintained at follow-up. No significant changes were observed in the pdBSI after a single rehabilitation session. Results suggest that balancing of interhemispheric symmetry comes along with a clinical improvement in the upper extremity and that the pdBSI can be used to investigate the mechanisms of neuronal plasticity involved in robotic rehabilitation after stroke.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3590-3602"},"PeriodicalIF":4.8,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10679982","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142267743","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 : 2024-09-12DOI: 10.1109/TNSRE.2024.3459801
Hanbin Cho;Moaad Benjaber;C. Alexis Gkogkidis;Marina Buchheit;Juan F. Ruiz-Rodríguez;Benjamin L. Grannan;Kurt E. Weaver;Andrew L. Ko;Steven C. Cramer;Jeffrey G. Ojemann;Timothy Denison;Jeffrey A. Herron
With the development and characterization of biomarkers that may reflect neural network state as well as a patient’s clinical deficits, there is growing interest in more complex stimulation designs. While current implantable neuromodulation systems offer pathways to expand the design and application of adaptive stimulation paradigms, technological drawbacks of these systems limit adaptive neuromodulation exploration. In this paper, we discuss the implementation of a phase-triggered stimulation paradigm using a research platform composed of an investigational system known as the CorTec Brain Interchange (CorTec GmbH, Freiburg, Germany), and an open-source software tool known as OMNI-BIC. We then evaluate the stimulation paradigm’s performance in both benchtop and in vivo human demonstrations. Our findings indicate that the Brain Interchange and OMNI-BIC platform is capable of reliable administration of phase-triggered stimulation and has the potential to help expand investigation within the adaptive neuromodulation design space.
{"title":"Development and Evaluation of a Real-Time Phase-Triggered Stimulation Algorithm for the CorTec Brain Interchange","authors":"Hanbin Cho;Moaad Benjaber;C. Alexis Gkogkidis;Marina Buchheit;Juan F. Ruiz-Rodríguez;Benjamin L. Grannan;Kurt E. Weaver;Andrew L. Ko;Steven C. Cramer;Jeffrey G. Ojemann;Timothy Denison;Jeffrey A. Herron","doi":"10.1109/TNSRE.2024.3459801","DOIUrl":"10.1109/TNSRE.2024.3459801","url":null,"abstract":"With the development and characterization of biomarkers that may reflect neural network state as well as a patient’s clinical deficits, there is growing interest in more complex stimulation designs. While current implantable neuromodulation systems offer pathways to expand the design and application of adaptive stimulation paradigms, technological drawbacks of these systems limit adaptive neuromodulation exploration. In this paper, we discuss the implementation of a phase-triggered stimulation paradigm using a research platform composed of an investigational system known as the CorTec Brain Interchange (CorTec GmbH, Freiburg, Germany), and an open-source software tool known as OMNI-BIC. We then evaluate the stimulation paradigm’s performance in both benchtop and in vivo human demonstrations. Our findings indicate that the Brain Interchange and OMNI-BIC platform is capable of reliable administration of phase-triggered stimulation and has the potential to help expand investigation within the adaptive neuromodulation design space.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3625-3635"},"PeriodicalIF":4.8,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10679661","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142204860","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 : 2024-09-11DOI: 10.1109/TNSRE.2024.3458396
Andrea Bizzego;Alessandro Carollo;Mengyu Lim;Gianluca Esposito
Functional near-infrared spectroscopy (fNIRS) is an increasingly popular tool for cross-cultural neuroimaging studies. However, the reproducibility and comparability of fNIRS studies is still an open issue in the scientific community. The paucity of experimental practices and the lack of clear guidelines regarding fNIRS use contribute to undermining the reproducibility of results. For this reason, much effort is now directed at assessing the impact of heterogeneous experimental practices in creating divergent fNIRS results. The current work aims to assess differences in fNIRS signal quality in data collected by two different labs in two different cohorts: Singapore (N=74) and Italy (N=84). Random segments of 20s were extracted from each channel in each participant’s NIRScap and 1280 deep features were obtained using a deep learning model trained to classify the quality of fNIRS data. Two datasets were generated: ALL dataset (segments with bad and good data quality) and GOOD dataset (segments with good quality). Each dataset was divided into train and test partitions, which were used to train and evaluate the performance of a Support Vector Machine (SVM) model in classifying the cohorts from signal quality features. Results showed that the SG cohort had significantly higher occurrences of bad signal quality in the majority of the fNIRS channels. Moreover, the SVM correctly classified the cohorts when using the ALL dataset. However, the performance dropped almost completely (except for five channels) when the SVM had to classify the cohorts using data from the GOOD dataset. These results suggest that fNIRS raw data obtained by different labs might possess different levels of quality as well as different latent characteristics beyond quality per se. The current study highlights the importance of defining clear guidelines in the conduction of fNIRS experiments in the reporting of data quality in fNIRS manuscripts.
{"title":"Effects of Individual Research Practices on fNIRS Signal Quality and Latent Characteristics","authors":"Andrea Bizzego;Alessandro Carollo;Mengyu Lim;Gianluca Esposito","doi":"10.1109/TNSRE.2024.3458396","DOIUrl":"10.1109/TNSRE.2024.3458396","url":null,"abstract":"Functional near-infrared spectroscopy (fNIRS) is an increasingly popular tool for cross-cultural neuroimaging studies. However, the reproducibility and comparability of fNIRS studies is still an open issue in the scientific community. The paucity of experimental practices and the lack of clear guidelines regarding fNIRS use contribute to undermining the reproducibility of results. For this reason, much effort is now directed at assessing the impact of heterogeneous experimental practices in creating divergent fNIRS results. The current work aims to assess differences in fNIRS signal quality in data collected by two different labs in two different cohorts: Singapore (N=74) and Italy (N=84). Random segments of 20s were extracted from each channel in each participant’s NIRScap and 1280 deep features were obtained using a deep learning model trained to classify the quality of fNIRS data. Two datasets were generated: ALL dataset (segments with bad and good data quality) and GOOD dataset (segments with good quality). Each dataset was divided into train and test partitions, which were used to train and evaluate the performance of a Support Vector Machine (SVM) model in classifying the cohorts from signal quality features. Results showed that the SG cohort had significantly higher occurrences of bad signal quality in the majority of the fNIRS channels. Moreover, the SVM correctly classified the cohorts when using the ALL dataset. However, the performance dropped almost completely (except for five channels) when the SVM had to classify the cohorts using data from the GOOD dataset. These results suggest that fNIRS raw data obtained by different labs might possess different levels of quality as well as different latent characteristics beyond quality per se. The current study highlights the importance of defining clear guidelines in the conduction of fNIRS experiments in the reporting of data quality in fNIRS manuscripts.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3515-3521"},"PeriodicalIF":4.8,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10677394","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142204864","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：