Pub Date : 2025-12-17DOI: 10.1109/TNSRE.2025.3644746
Amir Roshani Talesh;Qi Kang;Eric J. Lang;Mesut Sahin
Transcranial AC stimulation (tACS) of the cerebellum can entrain spiking activity in the Purkinje cells (PCs) of the cerebellar cortex and, through their projections, the cells in the cerebellar nuclei (CN). In this paper, we investigated if the cells in the motor thalamus (Mthal) can also be modulated (i.e. spikes entrained) via the CN-Mthal projections in rodents. A total of 82 thalamic cells were found, presumably in the Mthal by their stereotaxic coordinates, that were modulated by tACS of the cerebellum. Out of the 346 cells isolated, the thalamic cells with shorter action potentials and regular firing patterns had a higher probability of modulation by cerebellar stimulation than the cells with wider action potentials. The modulation level had a tuning curve with a maximum around 100-200 Hz. Spike histograms over the stimulation cycle transitioned between unimodal and bimodal distributions depending on the frequency. Most cells had a unimodal distribution at low frequencies, a bimodal distribution for frequencies between 80-125 Hz, and then a unimodal one for frequencies above 150 Hz. In addition, tACS of the motor cortex (MC) was also tested in a subset of thalamic cells. Unlike cerebellar stimulation, modulation levels peaked at two distinct frequencies, presumably due to entrainment through multiple MC-Mthal pathways with different preferred frequencies. The results demonstrate the feasibility of modulating a deep brain structure such as the thalamus through multi-synaptic pathways by stimulation of the cerebellar cortex (and the motor cortex) using a non-invasive neuromodulation method.
{"title":"tACS of the Cerebellum and the Motor Cortex Entrains the Spiking Activity of the Cells in Motor Thalamus in a Frequency Dependent Manner","authors":"Amir Roshani Talesh;Qi Kang;Eric J. Lang;Mesut Sahin","doi":"10.1109/TNSRE.2025.3644746","DOIUrl":"10.1109/TNSRE.2025.3644746","url":null,"abstract":"Transcranial AC stimulation (tACS) of the cerebellum can entrain spiking activity in the Purkinje cells (PCs) of the cerebellar cortex and, through their projections, the cells in the cerebellar nuclei (CN). In this paper, we investigated if the cells in the motor thalamus (Mthal) can also be modulated (i.e. spikes entrained) via the CN-Mthal projections in rodents. A total of 82 thalamic cells were found, presumably in the Mthal by their stereotaxic coordinates, that were modulated by tACS of the cerebellum. Out of the 346 cells isolated, the thalamic cells with shorter action potentials and regular firing patterns had a higher probability of modulation by cerebellar stimulation than the cells with wider action potentials. The modulation level had a tuning curve with a maximum around 100-200 Hz. Spike histograms over the stimulation cycle transitioned between unimodal and bimodal distributions depending on the frequency. Most cells had a unimodal distribution at low frequencies, a bimodal distribution for frequencies between 80-125 Hz, and then a unimodal one for frequencies above 150 Hz. In addition, tACS of the motor cortex (MC) was also tested in a subset of thalamic cells. Unlike cerebellar stimulation, modulation levels peaked at two distinct frequencies, presumably due to entrainment through multiple MC-Mthal pathways with different preferred frequencies. The results demonstrate the feasibility of modulating a deep brain structure such as the thalamus through multi-synaptic pathways by stimulation of the cerebellar cortex (and the motor cortex) using a non-invasive neuromodulation method.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"323-333"},"PeriodicalIF":5.2,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11301855","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145774536","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}
With the rapid growth of the elderly population, fall accidents have received increasing attention due to their serious health hazards. Pre-impact fall detection (PIFD) based on wearable sensors emerges as a promising approach for proactive fall prevention in healthcare monitoring. In this research, based on Inertial Measurement Units (IMUs), we construct and publicly provide a large-scale motion dataset named FallTL, which includes falls and activities of daily living (ADLs) collected from multiple body segments. Furthermore, we develop STA-Net, a novel Spatial-Temporal Attention Network to perform PIFD based on IMU data from a single body segment. STA-Net incorporates a dual-branch architecture: a temporal attention branch that models temporal signal dependencies and a spatial attention branch that captures cross-modality feature interactions, enabling robust representation learning from sensor data. We evaluate STA-Net across three datasets and it achieves advantageous performance and comparable lead time under cross-subject validation, outperforming state-of-the-art baselines. In addition, our analysis further investigates the influence of sensor placement and data modality on detection performance. These results indicate that accurate and robust PIFD is feasible with minimally obtrusive, single-location sensor setups, offering practical implications for wearable fall monitoring systems.
{"title":"Fall Monitoring With Single IMU: A Large-Scale Dataset and a Novel Dual-Branch Network","authors":"Yize Cai;Junxin Chen;Qiang He;Jun Mou;David Camacho","doi":"10.1109/TNSRE.2025.3645365","DOIUrl":"10.1109/TNSRE.2025.3645365","url":null,"abstract":"With the rapid growth of the elderly population, fall accidents have received increasing attention due to their serious health hazards. Pre-impact fall detection (PIFD) based on wearable sensors emerges as a promising approach for proactive fall prevention in healthcare monitoring. In this research, based on Inertial Measurement Units (IMUs), we construct and publicly provide a large-scale motion dataset named FallTL, which includes falls and activities of daily living (ADLs) collected from multiple body segments. Furthermore, we develop STA-Net, a novel Spatial-Temporal Attention Network to perform PIFD based on IMU data from a single body segment. STA-Net incorporates a dual-branch architecture: a temporal attention branch that models temporal signal dependencies and a spatial attention branch that captures cross-modality feature interactions, enabling robust representation learning from sensor data. We evaluate STA-Net across three datasets and it achieves advantageous performance and comparable lead time under cross-subject validation, outperforming state-of-the-art baselines. In addition, our analysis further investigates the influence of sensor placement and data modality on detection performance. These results indicate that accurate and robust PIFD is feasible with minimally obtrusive, single-location sensor setups, offering practical implications for wearable fall monitoring systems.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"287-299"},"PeriodicalIF":5.2,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11303325","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145774420","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}
This study investigated the large-scale dynamic brain network mechanisms underlying cognitive decline in Parkinson’s disease (PD) by integrating high-density Electroencephalography (EEG) signal source localization and co-activation pattern (CAP) analysis to track transient network states during cognitive tasks. Twenty patients with PD and fourteen healthy controls (HC) underwent simultaneous EEG acquisition while performing Chinese character reading, color recognition, and Stroop tasks; cognitive functions were assessed using the Montreal Cognitive Assessment (MoCA). High-density EEG signals were reconstructed using standardized low-resolution brain electromagnetic tomography (sLORETA), yielding six CAPs representing whole-brain transient dynamic activation. Results indicated that the decoupling between the default mode network (DMN) and the task-related network (TRN) is impaired in PD patients. Specifically, during the Stroop task, PD patients showed reduced dwell time in CAP4 (TRN activation/DMN inhibition), prolonged DMN activation, and increased transitions from TRN to DMN states. CAP fraction of time correlated positively with MoCA scores, suggesting DMN-TRN decoupling efficiency predicts cognitive performance. PD patients also exhibited compensatory overactivation of the anterior cingulate cortex (ACC) and salience network (SN). In conclusion, PD is characterized by disrupted dynamic DMN-TRN interactions, frequent state switching, and compensatory hyperactivation, directly contributing to cognitive decline. This study maps large-scale dynamic brain networks in PD with millisecond resolution, revealing new insights into transient network states and compensatory mechanisms, identifying potential biomarkers, and informing interventions targeting network uncoupling efficiency.
{"title":"Abnormal Large-Scale Dynamic Brain Networks in Parkinson’s Disease With Cognitive Impairment: Insights From EEG Co-Activation Patterns","authors":"Ping Xie;Hui Lv;Peng Wang;Zilong Wang;Yingying Hao;Zhiqi Mao;Haohao Zhang;Xiaoling Chen","doi":"10.1109/TNSRE.2025.3644182","DOIUrl":"10.1109/TNSRE.2025.3644182","url":null,"abstract":"This study investigated the large-scale dynamic brain network mechanisms underlying cognitive decline in Parkinson’s disease (PD) by integrating high-density Electroencephalography (EEG) signal source localization and co-activation pattern (CAP) analysis to track transient network states during cognitive tasks. Twenty patients with PD and fourteen healthy controls (HC) underwent simultaneous EEG acquisition while performing Chinese character reading, color recognition, and Stroop tasks; cognitive functions were assessed using the Montreal Cognitive Assessment (MoCA). High-density EEG signals were reconstructed using standardized low-resolution brain electromagnetic tomography (sLORETA), yielding six CAPs representing whole-brain transient dynamic activation. Results indicated that the decoupling between the default mode network (DMN) and the task-related network (TRN) is impaired in PD patients. Specifically, during the Stroop task, PD patients showed reduced dwell time in CAP4 (TRN activation/DMN inhibition), prolonged DMN activation, and increased transitions from TRN to DMN states. CAP fraction of time correlated positively with MoCA scores, suggesting DMN-TRN decoupling efficiency predicts cognitive performance. PD patients also exhibited compensatory overactivation of the anterior cingulate cortex (ACC) and salience network (SN). In conclusion, PD is characterized by disrupted dynamic DMN-TRN interactions, frequent state switching, and compensatory hyperactivation, directly contributing to cognitive decline. This study maps large-scale dynamic brain networks in PD with millisecond resolution, revealing new insights into transient network states and compensatory mechanisms, identifying potential biomarkers, and informing interventions targeting network uncoupling efficiency.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"405-415"},"PeriodicalIF":5.2,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11300314","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145762549","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 : 2025-12-12DOI: 10.1109/TNSRE.2025.3643813
Sunguk Hong;Mingeun Cho;Sung-Min Park
Pupillometry has recently emerged as a sensitive biomarker for autonomic and cortical activity, offering a non-invasive readout for neuromodulation research. However, existing commercial and deep learning–based pupillometry systems are primarily designed for humans, rendering them unsuitable for rodent experiments due to differences in ocular morphology, fur-induced optical artifacts, and the computational demands of high-resolution imaging. In this study, we present a low-cost, integrated real-time rodent pupillometry system built on an embedded platform. The proposed rule-based pupillometry algorithm was optimized with adaptive ellipse fitting, RGB masking artifact suppression, and greedy tracking, achieving robust performance under infrared illumination without requiring GPU acceleration. By minimizing errors caused by complex fur patterns and rodent-specific ocular features, our approach achieved an 86.0% detection rate in rat pupillometry, substantially surpassing the 63.1% attained by existing approach. The system was validated in vivo through vagus nerve stimulation (VNS) experiments in Long-Evans rats, where dynamic changes in pupil size reliably reflected stimulation intensity. By enabling an effective evaluation of VNS, these findings highlight the utility of our system as a practical preclinical tool and underscore the broader potential of pupillometry as a non-invasive biomarker for neuromodulation.
{"title":"Real-Time Rodent Pupillometry on an Embedded Platform for Neuromodulation","authors":"Sunguk Hong;Mingeun Cho;Sung-Min Park","doi":"10.1109/TNSRE.2025.3643813","DOIUrl":"10.1109/TNSRE.2025.3643813","url":null,"abstract":"Pupillometry has recently emerged as a sensitive biomarker for autonomic and cortical activity, offering a non-invasive readout for neuromodulation research. However, existing commercial and deep learning–based pupillometry systems are primarily designed for humans, rendering them unsuitable for rodent experiments due to differences in ocular morphology, fur-induced optical artifacts, and the computational demands of high-resolution imaging. In this study, we present a low-cost, integrated real-time rodent pupillometry system built on an embedded platform. The proposed rule-based pupillometry algorithm was optimized with adaptive ellipse fitting, RGB masking artifact suppression, and greedy tracking, achieving robust performance under infrared illumination without requiring GPU acceleration. By minimizing errors caused by complex fur patterns and rodent-specific ocular features, our approach achieved an 86.0% detection rate in rat pupillometry, substantially surpassing the 63.1% attained by existing approach. The system was validated in vivo through vagus nerve stimulation (VNS) experiments in Long-Evans rats, where dynamic changes in pupil size reliably reflected stimulation intensity. By enabling an effective evaluation of VNS, these findings highlight the utility of our system as a practical preclinical tool and underscore the broader potential of pupillometry as a non-invasive biomarker for neuromodulation.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"205-214"},"PeriodicalIF":5.2,"publicationDate":"2025-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11299494","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145742249","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 : 2025-12-10DOI: 10.1109/TNSRE.2025.3642228
Atsushi Takagi;Naotoshi Abekawa
The control of the lower limbs is essential to activities of daily living like walking and balancing, which are fundamental indicators of health linked to fall risk and mortality. Despite its importance, there exist few methods that quantify lower limb control. This study evaluated whether the variability of fifteen-second circular leg movements relates to lower limb control, as assessed by a footedness questionnaire, and whether it also reflects functional performance in a postural balance task. Twenty-five healthy participants performed circular movements with their left and right legs, and they also completed one-legged stance trials on a force plate. Sway area and sway velocity were used as postural stability metrics. We found a linear relationship between each leg’s acceleration variability and its log-transformed sway area and sway velocity. Moreover, across three repeated measurements per limb, circular acceleration variability was more reliable than the sway area and sway velocity as it had the largest intra-class correlation coefficient. Furthermore, the lateral difference between the left and right leg’s acceleration variability was linearly related to the revised Waterloo Footedness Questionnaire’s score. Together, these findings suggest that the variability of circular leg movements provides a robust and functional assessment of the lower limb’s lateralization and postural stability.
{"title":"Variability of Circular Leg Movements Is Related to Footedness and Postural Stability","authors":"Atsushi Takagi;Naotoshi Abekawa","doi":"10.1109/TNSRE.2025.3642228","DOIUrl":"10.1109/TNSRE.2025.3642228","url":null,"abstract":"The control of the lower limbs is essential to activities of daily living like walking and balancing, which are fundamental indicators of health linked to fall risk and mortality. Despite its importance, there exist few methods that quantify lower limb control. This study evaluated whether the variability of fifteen-second circular leg movements relates to lower limb control, as assessed by a footedness questionnaire, and whether it also reflects functional performance in a postural balance task. Twenty-five healthy participants performed circular movements with their left and right legs, and they also completed one-legged stance trials on a force plate. Sway area and sway velocity were used as postural stability metrics. We found a linear relationship between each leg’s acceleration variability and its log-transformed sway area and sway velocity. Moreover, across three repeated measurements per limb, circular acceleration variability was more reliable than the sway area and sway velocity as it had the largest intra-class correlation coefficient. Furthermore, the lateral difference between the left and right leg’s acceleration variability was linearly related to the revised Waterloo Footedness Questionnaire’s score. Together, these findings suggest that the variability of circular leg movements provides a robust and functional assessment of the lower limb’s lateralization and postural stability.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"198-204"},"PeriodicalIF":5.2,"publicationDate":"2025-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11296943","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145722438","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 : 2025-12-09DOI: 10.1109/TNSRE.2025.3641901
Chia-Hsuan Lee;Ying-Po Hsu;Chih-Ching Chang
This study systematically compared full-body, upper limb, lower limb, and trunk kinematic features in fall risk classification among community-dwelling older adults. Full-body and upper limb features yielded higher accuracy than lower limb and trunk, underscoring the key role of arm movements in balance control. Feature importance analysis selected 12.5% of key variables, including wrist displacement and upper limb velocity, boosting model accuracy from 57% to 78%, demonstrating strong clinical potential. Different machine-learning models showed complementary strengths: XGBoost excelled with nonlinear lower limb features, while random forest better integrated heterogeneous full-body data. By contrast, traditional linear kinematic-based models achieved a maximum accuracy of only 0.61, reflecting their limited ability to capture the nonlinear, multiscale, and sensory integration aspects of postural control. Integrating multi-regional movement coordination enhanced prediction, highlighting the multidimensional nature of balance regulation and supporting the development of efficient clinical fall risk screening tools.
{"title":"Movement Pattern Analysis Based on Point-Line-Plane Hierarchies and Machine Learning for Fall Risk Assessment in Community-Dwelling Older Adults","authors":"Chia-Hsuan Lee;Ying-Po Hsu;Chih-Ching Chang","doi":"10.1109/TNSRE.2025.3641901","DOIUrl":"10.1109/TNSRE.2025.3641901","url":null,"abstract":"This study systematically compared full-body, upper limb, lower limb, and trunk kinematic features in fall risk classification among community-dwelling older adults. Full-body and upper limb features yielded higher accuracy than lower limb and trunk, underscoring the key role of arm movements in balance control. Feature importance analysis selected 12.5% of key variables, including wrist displacement and upper limb velocity, boosting model accuracy from 57% to 78%, demonstrating strong clinical potential. Different machine-learning models showed complementary strengths: XGBoost excelled with nonlinear lower limb features, while random forest better integrated heterogeneous full-body data. By contrast, traditional linear kinematic-based models achieved a maximum accuracy of only 0.61, reflecting their limited ability to capture the nonlinear, multiscale, and sensory integration aspects of postural control. Integrating multi-regional movement coordination enhanced prediction, highlighting the multidimensional nature of balance regulation and supporting the development of efficient clinical fall risk screening tools.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"185-197"},"PeriodicalIF":5.2,"publicationDate":"2025-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11289570","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145714206","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 : 2025-12-08DOI: 10.1109/TNSRE.2025.3641557
Xiaotong Liu;Min Ren;Qiong Li;Yongzhen Huang
Depression is a severe mental health disorder with significant emotional and physical impacts. To identify and assess its severity, self-rating scales are commonly employed, which evaluate depressive symptoms through a series of questionnaire-based items. While these scales provide valuable subjective insights, gait analysis has emerged as a complementary, non-intrusive method for depression assessment, offering objective perspectives on an individual’s mental state. Existing studies primarily use scale scores as ground truth while overlooking the semantic richness within the scale content. In this study, we propose a novel depression severity prediction framework that integrates gait features with scale content to enhance depression assessment. Specifically, the scale content is modeled as a multilevel semantic structure, comprising individual-independent and individual-specific components. Fusion strategies are tailored accordingly to align each type with the gait features. The individual-independent content, which provides general descriptions of depressive symptoms, is fused with gait features via a cross-attention mechanism to offer broad semantic guidance. In contrast, the individual-specific content, derived from participants’ personalized responses, is used to align the fused features for more accurate and tailored prediction. We conduct extensive experiments on the D-Gait dataset, demonstrating that integrating scale content significantly enhances performance, with a notable 6.74% improvement in Concordance Correlation Coefficient compared to gait-only models.
{"title":"Integrating Gait With Multilevel Scale Representations for Depression Severity Prediction","authors":"Xiaotong Liu;Min Ren;Qiong Li;Yongzhen Huang","doi":"10.1109/TNSRE.2025.3641557","DOIUrl":"10.1109/TNSRE.2025.3641557","url":null,"abstract":"Depression is a severe mental health disorder with significant emotional and physical impacts. To identify and assess its severity, self-rating scales are commonly employed, which evaluate depressive symptoms through a series of questionnaire-based items. While these scales provide valuable subjective insights, gait analysis has emerged as a complementary, non-intrusive method for depression assessment, offering objective perspectives on an individual’s mental state. Existing studies primarily use scale scores as ground truth while overlooking the semantic richness within the scale content. In this study, we propose a novel depression severity prediction framework that integrates gait features with scale content to enhance depression assessment. Specifically, the scale content is modeled as a multilevel semantic structure, comprising individual-independent and individual-specific components. Fusion strategies are tailored accordingly to align each type with the gait features. The individual-independent content, which provides general descriptions of depressive symptoms, is fused with gait features via a cross-attention mechanism to offer broad semantic guidance. In contrast, the individual-specific content, derived from participants’ personalized responses, is used to align the fused features for more accurate and tailored prediction. We conduct extensive experiments on the D-Gait dataset, demonstrating that integrating scale content significantly enhances performance, with a notable 6.74% improvement in Concordance Correlation Coefficient compared to gait-only models.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"175-184"},"PeriodicalIF":5.2,"publicationDate":"2025-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11284896","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145707537","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}
Electrical stimulation of the hypoglossal nerve is an established therapy for obstructive sleep apnea, as activation of tongue muscles helps maintain airway patency during sleep. However, surgical implantation of electrodes carries inherent risks and limits broader application. In this study, we investigated a non-invasive approach using low-intensity pulsed ultrasound neuromodulation to stimulate the hypoglossal nerve and evaluated its effect on tongue muscle activity and upper-airway function. A 1-MHz ultrasound transducer was applied to the cervical region of anesthetized mice to deliver acoustic stimulation. Electromyography recordings from tongue muscles demonstrated that ultrasound effectively induced muscle activation via hypoglossal nerve neuromodulation. In addition, oxygen saturation and tongue displacement were monitored to assess functional improvements in upper-airway patency and to ensure safety with respect to tissue integrity and thermal effects. The results confirmed that ultrasound stimulation successfully modulated nerve activity and elicited tongue movements without evidence of tissue damage. These findings suggest that ultrasound-based neuromodulation offers a promising, safe, and non-invasive alternative for obstructive sleep disorder treatment.
{"title":"Low-Intensity Pulsed Ultrasound Neuromodulation of the Hypoglossal Nerve for the Treatment of Sleep Apnea: An Animal Study","authors":"Thi-Thuyet Truong;Yi-Hsiang Chuang;Hsin Huang;Onanong Mee-Inta;Yu-Min Kuo;Jeng-Wen Chen;Wen-Tai Chiu;Chih-Chung Huang","doi":"10.1109/TNSRE.2025.3640964","DOIUrl":"10.1109/TNSRE.2025.3640964","url":null,"abstract":"Electrical stimulation of the hypoglossal nerve is an established therapy for obstructive sleep apnea, as activation of tongue muscles helps maintain airway patency during sleep. However, surgical implantation of electrodes carries inherent risks and limits broader application. In this study, we investigated a non-invasive approach using low-intensity pulsed ultrasound neuromodulation to stimulate the hypoglossal nerve and evaluated its effect on tongue muscle activity and upper-airway function. A 1-MHz ultrasound transducer was applied to the cervical region of anesthetized mice to deliver acoustic stimulation. Electromyography recordings from tongue muscles demonstrated that ultrasound effectively induced muscle activation via hypoglossal nerve neuromodulation. In addition, oxygen saturation and tongue displacement were monitored to assess functional improvements in upper-airway patency and to ensure safety with respect to tissue integrity and thermal effects. The results confirmed that ultrasound stimulation successfully modulated nerve activity and elicited tongue movements without evidence of tissue damage. These findings suggest that ultrasound-based neuromodulation offers a promising, safe, and non-invasive alternative for obstructive sleep disorder treatment.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"163-174"},"PeriodicalIF":5.2,"publicationDate":"2025-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11278805","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145687366","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 : 2025-12-02DOI: 10.1109/TNSRE.2025.3639490
Wenbin Zhang;Jianwei Lai;Baoguo Xu;Hong Zeng;Ting Wu;Hexuan Hu;Aiguo Song
Brain-controlled robotic hand rehabilitation systems based on motor intention recognition have been used to promote recovery of hand function in stroke patients. However, the low decoding accuracy of motor imagery (MI) and unclear neural response mechanisms limit its widespread application. This study introduces a novel vibrotactile-assisted brain-controlled soft robotic hand rehabilitation system to validate its effectiveness in activating the motor sensory areas of the brain and to explore the neural response mechanisms of vibration stimulation in hand rehabilitation training. A total of 23 healthy subjects and 5 stroke patients were recruited to perform EEG and fNIRS-based experiments. Healthy subjects performed an EEG-based active rehabilitation task and an fNIRS-based passive rehabilitation task driven by the soft glove. Stroke patients only completed an EEG-based passive rehabilitation task. All experiments were conducted under two conditions: with and without vibrotactile stimulation. EEG results revealed that vibration stimulation significantly enhanced motor-sensory cortex activation during MI, and improved the online decoding performance of subjects with poor training outcomes. Grasping and stretching movements driven by the soft glove effectively activated the subjects’ motorsensory cortex. Vibration stimulation boosted the event-related desynchronization (ERD) phenomenon in the contralateral somatosensory cortex of the healthy subjects, but was not significant in the motor cortex. Meanwhile, it strengthened bilateral sensorimotor activation in stroke patients. Moreover, fNIRS results indicated that vibration stimulation increased the concentration of HbO in the motor-sensory areas during passive movement and enhanced the bidirectional functional connectivity between the left and right hemispheres. These findings suggest that the proposed tactile-assisted hand rehabilitation system can effectively enhance neural activation in the motor-sensory cortex, potentially leading to improved hand function recovery in stroke patients.
{"title":"The Role of Vibrotactile Stimulation in Soft Rehabilitation Glove-Assisted Hand Rehabilitation Training: A Pilot Study","authors":"Wenbin Zhang;Jianwei Lai;Baoguo Xu;Hong Zeng;Ting Wu;Hexuan Hu;Aiguo Song","doi":"10.1109/TNSRE.2025.3639490","DOIUrl":"10.1109/TNSRE.2025.3639490","url":null,"abstract":"Brain-controlled robotic hand rehabilitation systems based on motor intention recognition have been used to promote recovery of hand function in stroke patients. However, the low decoding accuracy of motor imagery (MI) and unclear neural response mechanisms limit its widespread application. This study introduces a novel vibrotactile-assisted brain-controlled soft robotic hand rehabilitation system to validate its effectiveness in activating the motor sensory areas of the brain and to explore the neural response mechanisms of vibration stimulation in hand rehabilitation training. A total of 23 healthy subjects and 5 stroke patients were recruited to perform EEG and fNIRS-based experiments. Healthy subjects performed an EEG-based active rehabilitation task and an fNIRS-based passive rehabilitation task driven by the soft glove. Stroke patients only completed an EEG-based passive rehabilitation task. All experiments were conducted under two conditions: with and without vibrotactile stimulation. EEG results revealed that vibration stimulation significantly enhanced motor-sensory cortex activation during MI, and improved the online decoding performance of subjects with poor training outcomes. Grasping and stretching movements driven by the soft glove effectively activated the subjects’ motorsensory cortex. Vibration stimulation boosted the event-related desynchronization (ERD) phenomenon in the contralateral somatosensory cortex of the healthy subjects, but was not significant in the motor cortex. Meanwhile, it strengthened bilateral sensorimotor activation in stroke patients. Moreover, fNIRS results indicated that vibration stimulation increased the concentration of HbO in the motor-sensory areas during passive movement and enhanced the bidirectional functional connectivity between the left and right hemispheres. These findings suggest that the proposed tactile-assisted hand rehabilitation system can effectively enhance neural activation in the motor-sensory cortex, potentially leading to improved hand function recovery in stroke patients.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"149-162"},"PeriodicalIF":5.2,"publicationDate":"2025-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11272914","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145661156","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}
Conventional cross-subject electroencephalogram (EEG) signal identification frameworks require centralized aggregation of all subjects’ data for feature extraction, which inherently poses substantial risks of data privacy breaches. In response to this critical issue, the present study delves into the classification of steady-state visual evoked potential (SSVEP) signals with an emphasis on data privacy preservation. First, we design a federated learning framework (FedGF) consisting of a central server and multiple clients, where the server generates global features and coordinates distributed training across clients, while retaining subject-specific raw data locally to ensure privacy protection. Then, to enhance model generalizability, FedGF employs data-free knowledge distillation (DFKD) to achieve knowledge transfer across clients through global feature learning. Extensive experiments on two public datasets (Dataset 1 ‘session01’ and 2 ‘session02’) and one private dataset (Dataset 3) demonstrate the superiority of the proposed method over baseline approaches, achieving performance improvements of 0.52%, 0.65%, and 0.53%, respectively. Finally, we develop a novel smart soft gripper with thermochromic capabilities and seamlessly integrate it with the trained network, demonstrating robust performance in daily grasping tasks. The source code is available at https://github.com/raow923/FedGF
{"title":"Improving Generalization in Federated Learning for Steady-State Visual Evoked Potential Classification and Its Application in Soft Gripper","authors":"Rao Wei;Changchun Hua;Jiannan Chen;Dianrui Mu;Jing Zhao","doi":"10.1109/TNSRE.2025.3639091","DOIUrl":"10.1109/TNSRE.2025.3639091","url":null,"abstract":"Conventional cross-subject electroencephalogram (EEG) signal identification frameworks require centralized aggregation of all subjects’ data for feature extraction, which inherently poses substantial risks of data privacy breaches. In response to this critical issue, the present study delves into the classification of steady-state visual evoked potential (SSVEP) signals with an emphasis on data privacy preservation. First, we design a federated learning framework (FedGF) consisting of a central server and multiple clients, where the server generates global features and coordinates distributed training across clients, while retaining subject-specific raw data locally to ensure privacy protection. Then, to enhance model generalizability, FedGF employs data-free knowledge distillation (DFKD) to achieve knowledge transfer across clients through global feature learning. Extensive experiments on two public datasets (Dataset 1 ‘session01’ and 2 ‘session02’) and one private dataset (Dataset 3) demonstrate the superiority of the proposed method over baseline approaches, achieving performance improvements of 0.52%, 0.65%, and 0.53%, respectively. Finally, we develop a novel smart soft gripper with thermochromic capabilities and seamlessly integrate it with the trained network, demonstrating robust performance in daily grasping tasks. The source code is available at <uri>https://github.com/raow923/FedGF</uri>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"126-136"},"PeriodicalIF":5.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11271668","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145653758","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：