Pub Date : 2024-10-01DOI: 10.1109/TNSRE.2024.3471646
Saqib Mamoon;Zhengwang Xia;Amani Alfakih;Jianfeng Lu
Resting-state functional magnetic resonance imaging (rs-fMRI) has emerged as a powerful tool for exploring interactions among brain regions. A growing body of research is actively investigating various computational approaches for estimating causal effects among brain regions. Compared to traditional methods, causal relationship reveals the causal influences among distinct brain regions, offering a deeper understanding of brain network dynamics. However, existing methods either neglect the concept of temporal lag across brain regions or set the temporal lag value to a fixed value. To address this limitation, we propose a Unified Causal and Temporal Lag Network (termed UCLN) that jointly learns the causal effects and temporal lag values among brain regions. Our method effectively captures variations in temporal lag between distant brain regions by avoiding the predefined lag value across the entire brain. The brain networks obtained are directed and weighted graphs, enabling a more comprehensive disentanglement of complex interactions. In addition, we also introduce three guiding mechanisms for efficient brain network modeling. The proposed method outperforms state-of-the-art approaches in classification accuracy on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Our findings indicate that the method not only achieves superior classification but also successfully identifies crucial neuroimaging biomarkers associated with the disease.
{"title":"UCLN: Toward the Causal Understanding of Brain Disorders With Temporal Lag Dynamics","authors":"Saqib Mamoon;Zhengwang Xia;Amani Alfakih;Jianfeng Lu","doi":"10.1109/TNSRE.2024.3471646","DOIUrl":"10.1109/TNSRE.2024.3471646","url":null,"abstract":"Resting-state functional magnetic resonance imaging (rs-fMRI) has emerged as a powerful tool for exploring interactions among brain regions. A growing body of research is actively investigating various computational approaches for estimating causal effects among brain regions. Compared to traditional methods, causal relationship reveals the causal influences among distinct brain regions, offering a deeper understanding of brain network dynamics. However, existing methods either neglect the concept of temporal lag across brain regions or set the temporal lag value to a fixed value. To address this limitation, we propose a Unified Causal and Temporal Lag Network (termed UCLN) that jointly learns the causal effects and temporal lag values among brain regions. Our method effectively captures variations in temporal lag between distant brain regions by avoiding the predefined lag value across the entire brain. The brain networks obtained are directed and weighted graphs, enabling a more comprehensive disentanglement of complex interactions. In addition, we also introduce three guiding mechanisms for efficient brain network modeling. The proposed method outperforms state-of-the-art approaches in classification accuracy on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Our findings indicate that the method not only achieves superior classification but also successfully identifies crucial neuroimaging biomarkers associated with the disease.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3729-3740"},"PeriodicalIF":4.8,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10701500","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142365133","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 : 2024-10-01DOI: 10.1109/TNSRE.2024.3471856
Zuyu Du;Yaodan Xu;Anyi Cheng;Yibin Jin;Lin Xu
Vibration exercise (VE) has shown promising results for improving muscle strength and power performance when superimposed on high-level muscle contraction. However, low-level contraction may be more preferable in many rehabilitation programs due to the weakness of the patients. Unfortunately, the effects and underlying physiological mechanisms of VE superimposed on low-level contraction are unclear. This study aims to investigate the fatiguing effects and motor unit (MU) firing patterns during VE with low-level muscle contraction. Twenty-one healthy participants performed 60-s isometric contraction of the upper limb under a baseline force at ${30}%$ maximum voluntary contraction and superimposed vibration with an amplitude of ${50}%$ baseline and different frequencies at 0 Hz (control), 15, 25, 35, and 45 Hz. High-density surface electromyography (EMG) was recorded on the biceps brachii. The decay in muscle fiber conduction velocity, calculated in 3-s sliding windows, was employed as an indicator of myoelectric fatigue. MU firing patterns were obtained by decomposing the high-density EMG into MU spike trains. VE, particularly at 25 Hz, produces increased myoelectric fatigue as compared to the control condition. Besides, synchronized MU discharges are observed at the vibration frequency for 15- and 25-Hz VE and the sub-harmonics for 35- and 45-Hz VE. Furthermore, VE-induced increase in MU synchronization (as compared to control) seems to decrease with myoelectric fatigue. Significance: Our findings suggest that VE may be a suitable modality for rehabilitation programs, providing useful insights for subscribing appropriate VE training protocols.
振动训练（VE）与高水平肌肉收缩叠加后，在改善肌肉力量和动力表现方面取得了可喜的成果。然而，在许多康复计划中，由于患者身体虚弱，低水平收缩可能更为可取。遗憾的是，VE 叠加低水平收缩的效果和潜在生理机制尚不清楚。本研究旨在探讨在低水平肌肉收缩下进行 VE 时的疲劳效应和运动单位（MU）的发射模式。21 名健康参与者在基线力为最大自主收缩力 30% 的情况下进行了 60 秒的上肢等长收缩，并叠加了振幅为基线力 50%、频率为 0 Hz（对照组）、15、25、35 和 45 Hz 的不同振动。对肱二头肌进行了高密度表面肌电图（EMG）记录。以 3 秒滑动窗口计算的肌纤维传导速度衰减被用作肌电疲劳的指标。通过将高密度肌电图分解为 MU 尖峰序列，可获得 MU 发火模式。与对照组相比，VE（尤其是 25 Hz 频率）会增加肌电疲劳。此外，在 15 赫兹和 25 赫兹 VE 的振动频率以及 35 赫兹和 45 赫兹 VE 的次谐波频率下，均可观察到同步 MU 放电。此外，VE 引起的 MU 同步性增加（与对照组相比）似乎会随着肌电疲劳而减少。意义重大：我们的研究结果表明，VE可能是一种适合康复计划的模式，为制定适当的VE训练方案提供了有益的启示。
{"title":"Myoelectric Fatigue and Motor-Unit Firing Patterns During Sinusoidal Vibration Superimposed on Low-Intensity Isometric Contraction","authors":"Zuyu Du;Yaodan Xu;Anyi Cheng;Yibin Jin;Lin Xu","doi":"10.1109/TNSRE.2024.3471856","DOIUrl":"10.1109/TNSRE.2024.3471856","url":null,"abstract":"Vibration exercise (VE) has shown promising results for improving muscle strength and power performance when superimposed on high-level muscle contraction. However, low-level contraction may be more preferable in many rehabilitation programs due to the weakness of the patients. Unfortunately, the effects and underlying physiological mechanisms of VE superimposed on low-level contraction are unclear. This study aims to investigate the fatiguing effects and motor unit (MU) firing patterns during VE with low-level muscle contraction. Twenty-one healthy participants performed 60-s isometric contraction of the upper limb under a baseline force at \u0000<inline-formula> <tex-math>${30}%$ </tex-math></inline-formula>\u0000 maximum voluntary contraction and superimposed vibration with an amplitude of \u0000<inline-formula> <tex-math>${50}%$ </tex-math></inline-formula>\u0000 baseline and different frequencies at 0 Hz (control), 15, 25, 35, and 45 Hz. High-density surface electromyography (EMG) was recorded on the biceps brachii. The decay in muscle fiber conduction velocity, calculated in 3-s sliding windows, was employed as an indicator of myoelectric fatigue. MU firing patterns were obtained by decomposing the high-density EMG into MU spike trains. VE, particularly at 25 Hz, produces increased myoelectric fatigue as compared to the control condition. Besides, synchronized MU discharges are observed at the vibration frequency for 15- and 25-Hz VE and the sub-harmonics for 35- and 45-Hz VE. Furthermore, VE-induced increase in MU synchronization (as compared to control) seems to decrease with myoelectric fatigue. Significance: Our findings suggest that VE may be a suitable modality for rehabilitation programs, providing useful insights for subscribing appropriate VE training protocols.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3773-3781"},"PeriodicalIF":4.8,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10701468","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142365132","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}
Early screening for Mild Cognitive Impairment (MCI) is crucial in delaying cognitive deterioration and treating dementia. Conventional neuropsychological tests, commonly used for MCI detection, often lack ecological validity due to their simplistic and quiet testing environments. To address this gap, our study developed an immersive VR supermarket cognitive assessment program (IVRSCAP), simulating daily cognitive activities to enhance the ecological validity of MCI detection. This program involved elderly participants from Chengdu Second People’s Hospital and various communities, comprising both MCI patients (N=301) and healthy elderly individuals (N=1027). They engaged in the VR supermarket cognitive test, generating complex datasets including User Behavior Data, Tested Cognitive Dimension Game Data, Trajectory Data, and Regional Data. To analyze this data, we introduced an adaptive ensemble learning method for imbalanced samples. Our study’s primary contribution is demonstrating the superior performance of this algorithm in classifying MCI and healthy groups based on their performance in IVRSCAP. Comparative analysis confirmed its efficacy over traditional imbalanced sample processing methods and classic ensemble learning voting algorithms, significantly outperforming in metrics such as recall, F1-score, AUC, and G-mean. Our findings advocate the combined use of IVRSCAP and our algorithm as a technologically advanced, ecologically valid approach for enhancing early MCI detection strategies. This aligns with our broader aim of integrating realistic simulations with advanced computational techniques to improve diagnostic accuracy and treatment efficacy in cognitive health assessments.
{"title":"An Ensemble Learning Algorithm for Cognitive Evaluation by an Immersive Virtual Reality Supermarket","authors":"Yifan Wang;Ping Yang;Jiangtao Yu;Shang Zhang;Liang Gong;Chunfeng Liu;Wenjun Zhou;Bo Peng","doi":"10.1109/TNSRE.2024.3470802","DOIUrl":"10.1109/TNSRE.2024.3470802","url":null,"abstract":"Early screening for Mild Cognitive Impairment (MCI) is crucial in delaying cognitive deterioration and treating dementia. Conventional neuropsychological tests, commonly used for MCI detection, often lack ecological validity due to their simplistic and quiet testing environments. To address this gap, our study developed an immersive VR supermarket cognitive assessment program (IVRSCAP), simulating daily cognitive activities to enhance the ecological validity of MCI detection. This program involved elderly participants from Chengdu Second People’s Hospital and various communities, comprising both MCI patients (N=301) and healthy elderly individuals (N=1027). They engaged in the VR supermarket cognitive test, generating complex datasets including User Behavior Data, Tested Cognitive Dimension Game Data, Trajectory Data, and Regional Data. To analyze this data, we introduced an adaptive ensemble learning method for imbalanced samples. Our study’s primary contribution is demonstrating the superior performance of this algorithm in classifying MCI and healthy groups based on their performance in IVRSCAP. Comparative analysis confirmed its efficacy over traditional imbalanced sample processing methods and classic ensemble learning voting algorithms, significantly outperforming in metrics such as recall, F1-score, AUC, and G-mean. Our findings advocate the combined use of IVRSCAP and our algorithm as a technologically advanced, ecologically valid approach for enhancing early MCI detection strategies. This aligns with our broader aim of integrating realistic simulations with advanced computational techniques to improve diagnostic accuracy and treatment efficacy in cognitive health assessments.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3761-3772"},"PeriodicalIF":4.8,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10700781","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142345947","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}
The pathogenesis of essential tremor (ET) remains unclear, and the efficacy of related drug treatment is inadequate for proper tremor control. Hence, in the current study, consecutive low-frequency repetitive transcranial magnetic stimulation (rTMS) modulation on cerebellum was accomplished in a population of ET patients, along with pre- and post-treatment resting-state electroencephalogram (EEG) networks being constructed. The results primarily clarified the decreasing of resting-state network interactions occurring in ET, especially the weaker frontal-parietal connectivity, compared to healthy individuals. While after the rTMS stimulation, promotions in both network connectivity and properties, as well as clinical scales, were identified. Furthermore, significant correlations between network characteristics and clinical scale scores enabled the development of predictive models for assessing rTMS intervention efficacy. Using a multivariable linear model, clinical scales after one-month rTMS treatment were accurately predicted, underscoring the potential of brain networks in evaluating rTMS effectiveness for ET. The findings consistently demonstrated that repetitive low-frequency rTMS neuromodulation on cerebellum can significantly improve the manifestations of ET, and individual networks will be reliable tools for evaluating the rTMS efficacy, thereby guiding personalized treatment strategies for ET patients.
本质性震颤（ET）的发病机制尚不清楚，相关药物治疗的疗效也不足以有效控制震颤。因此，本研究对 ET 患者群体的小脑进行了连续低频重复经颅磁刺激（rTMS）调制，并构建了治疗前后的静息脑电图（EEG）网络。研究结果主要阐明了 ET 患者静息态网络交互作用的减少，尤其是与健康人相比，ET 患者的额叶-顶叶连通性较弱。而在经颅磁刺激后，网络连通性和属性以及临床量表都得到了提升。此外，网络特征与临床量表评分之间的重要相关性使我们能够开发用于评估经颅磁刺激干预效果的预测模型。利用多变量线性模型，一个月经颅磁刺激治疗后的临床量表可被准确预测，这凸显了脑网络在评估经颅磁刺激治疗ET疗效方面的潜力。研究结果一致表明，对小脑进行重复低频经颅磁刺激神经调控可显著改善ET的表现，个体网络将成为评估经颅磁刺激疗效的可靠工具，从而指导ET患者的个性化治疗策略。
{"title":"Prediction of rTMS Efficacy in Patients With Essential Tremor: Biomarkers From Individual Resting-State EEG Network","authors":"Runyang He;Xue Shi;Lin Jiang;Yan Zhu;Zian Pei;Lin Zhu;Xiaolin Su;Dezhong Yao;Peng Xu;Yi Guo;Fali Li","doi":"10.1109/TNSRE.2024.3469576","DOIUrl":"10.1109/TNSRE.2024.3469576","url":null,"abstract":"The pathogenesis of essential tremor (ET) remains unclear, and the efficacy of related drug treatment is inadequate for proper tremor control. Hence, in the current study, consecutive low-frequency repetitive transcranial magnetic stimulation (rTMS) modulation on cerebellum was accomplished in a population of ET patients, along with pre- and post-treatment resting-state electroencephalogram (EEG) networks being constructed. The results primarily clarified the decreasing of resting-state network interactions occurring in ET, especially the weaker frontal-parietal connectivity, compared to healthy individuals. While after the rTMS stimulation, promotions in both network connectivity and properties, as well as clinical scales, were identified. Furthermore, significant correlations between network characteristics and clinical scale scores enabled the development of predictive models for assessing rTMS intervention efficacy. Using a multivariable linear model, clinical scales after one-month rTMS treatment were accurately predicted, underscoring the potential of brain networks in evaluating rTMS effectiveness for ET. The findings consistently demonstrated that repetitive low-frequency rTMS neuromodulation on cerebellum can significantly improve the manifestations of ET, and individual networks will be reliable tools for evaluating the rTMS efficacy, thereby guiding personalized treatment strategies for ET patients.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3719-3728"},"PeriodicalIF":4.8,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10697210","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142345951","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 : 2024-09-27DOI: 10.1109/TNSRE.2024.3469284
Kyeonggu Lee;Minyoung Chun;Bori Jung;Yunsu Kim;Chaeyoun Yang;JongKwan Choi;Jihyun Cha;Seung-Hwan Lee;Chang-Hwan Im
Transcranial photobiomodulation (tPBM) has been widely studied for its potential to enhance cognitive functions of the elderly. However, its efficacy varies, with some individuals exhibiting no significant response to the treatment. Considering these inconsistencies, we introduce a machine learning approach aimed at distinguishing between individuals that respond and do not respond to tPBM treatment based on functional near-infrared spectroscopy (fNIRS) acquired before the treatment. We measured nine cognitive scores and recorded fNIRS data from 62 older adults with cognitive decline (43 experimental and 19 control subjects). The experimental group underwent tPBM intervention over a span of 12 weeks. Based on the comparison of the global cognitive score (GCS), merging the nine cognitive scores into a single representation, acquired before and after tPBM treatment, we classified all participants as responders or non-responders to tPBM with a threshold for the GCS change. The fNIRS data were recorded during the resting state, recognition memory task (RMT), Stroop task, and verbal fluency task. A regularized support vector machine was utilized to classify the responders and non-responders to tPBM. The most promising performance of our machine learning model was observed when using the fNIRS data collected during the RMT, which yielded an accuracy of 0.8537, an F1-score of 0.8421, sensitivity of 0.7619, and specificity of 0.95. To the best of our knowledge, this is the first study to demonstrate the feasibility of predicting the tPBM efficacy. Our approach is expected to contribute to more efficient treatment planning by excluding ineffective treatment options.
{"title":"Machine-Learning-Based Prediction of Photobiomodulation Effects on Older Adults With Cognitive Decline Using Functional Near-Infrared Spectroscopy","authors":"Kyeonggu Lee;Minyoung Chun;Bori Jung;Yunsu Kim;Chaeyoun Yang;JongKwan Choi;Jihyun Cha;Seung-Hwan Lee;Chang-Hwan Im","doi":"10.1109/TNSRE.2024.3469284","DOIUrl":"10.1109/TNSRE.2024.3469284","url":null,"abstract":"Transcranial photobiomodulation (tPBM) has been widely studied for its potential to enhance cognitive functions of the elderly. However, its efficacy varies, with some individuals exhibiting no significant response to the treatment. Considering these inconsistencies, we introduce a machine learning approach aimed at distinguishing between individuals that respond and do not respond to tPBM treatment based on functional near-infrared spectroscopy (fNIRS) acquired before the treatment. We measured nine cognitive scores and recorded fNIRS data from 62 older adults with cognitive decline (43 experimental and 19 control subjects). The experimental group underwent tPBM intervention over a span of 12 weeks. Based on the comparison of the global cognitive score (GCS), merging the nine cognitive scores into a single representation, acquired before and after tPBM treatment, we classified all participants as responders or non-responders to tPBM with a threshold for the GCS change. The fNIRS data were recorded during the resting state, recognition memory task (RMT), Stroop task, and verbal fluency task. A regularized support vector machine was utilized to classify the responders and non-responders to tPBM. The most promising performance of our machine learning model was observed when using the fNIRS data collected during the RMT, which yielded an accuracy of 0.8537, an F1-score of 0.8421, sensitivity of 0.7619, and specificity of 0.95. To the best of our knowledge, this is the first study to demonstrate the feasibility of predicting the tPBM efficacy. Our approach is expected to contribute to more efficient treatment planning by excluding ineffective treatment options.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3710-3718"},"PeriodicalIF":4.8,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10697190","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142345949","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 : 2024-09-26DOI: 10.1109/TNSRE.2024.3468995
Ryan G. L. Koh;Mafalda Ribeiro;Leen Jabban;Binying Fang;Karlo Nesovic;Sayeh Bayat;Benjamin W. Metcalfe
Peripheral nerve interfaces (PNIs) can enable communication with the peripheral nervous system and have a broad range of applications including in bioelectronic medicine and neuroprostheses. They can modulate neural activity through stimulation or monitor conditions by recording from the peripheral nerves. The recent growth of Machine Learning (ML) has led to the application of a wide variety of ML techniques to PNIs, especially in circumstances where the goal is classification or regression. However, the extent to which ML has been applied to PNIs or the range of suitable ML techniques has not been documented. Therefore, a scoping review was conducted to determine and understand the state of ML in the PNI field. The review searched five databases and included 63 studies after full-text review. Most studies incorporated a supervised learning approach to classify activity, with the most common algorithms being some form of neural network (artificial neural network, convolutional neural network or recurrent neural network). Unsupervised, semi-supervised and reinforcement learning (RL) approaches are currently underutilized and could be better leveraged to improve performance in this domain.
外周神经接口（PNIs）可实现与外周神经系统的通信，在生物电子医学和神经义肢等领域有着广泛的应用。它们可以通过刺激来调节神经活动，或通过记录外周神经来监测情况。近年来，机器学习（ML）技术的发展促使人们将各种 ML 技术应用于 PNIs，尤其是在以分类或回归为目标的情况下。然而，ML 在 PNI 中的应用程度或合适的 ML 技术范围尚未记录在案。因此，我们进行了一次范围审查，以确定和了解 ML 在 PNI 领域的应用情况。该综述搜索了五个数据库，并在全文审阅后纳入了 63 项研究。大多数研究采用了监督学习方法对活动进行分类，最常见的算法是某种形式的神经网络（人工神经网络、卷积神经网络或递归神经网络）。无监督、半监督和强化学习方法目前还未得到充分利用，可以更好地利用这些方法来提高该领域的性能。
{"title":"A Scoping Review of Machine Learning Applied to Peripheral Nerve Interfaces","authors":"Ryan G. L. Koh;Mafalda Ribeiro;Leen Jabban;Binying Fang;Karlo Nesovic;Sayeh Bayat;Benjamin W. Metcalfe","doi":"10.1109/TNSRE.2024.3468995","DOIUrl":"10.1109/TNSRE.2024.3468995","url":null,"abstract":"Peripheral nerve interfaces (PNIs) can enable communication with the peripheral nervous system and have a broad range of applications including in bioelectronic medicine and neuroprostheses. They can modulate neural activity through stimulation or monitor conditions by recording from the peripheral nerves. The recent growth of Machine Learning (ML) has led to the application of a wide variety of ML techniques to PNIs, especially in circumstances where the goal is classification or regression. However, the extent to which ML has been applied to PNIs or the range of suitable ML techniques has not been documented. Therefore, a scoping review was conducted to determine and understand the state of ML in the PNI field. The review searched five databases and included 63 studies after full-text review. Most studies incorporated a supervised learning approach to classify activity, with the most common algorithms being some form of neural network (artificial neural network, convolutional neural network or recurrent neural network). Unsupervised, semi-supervised and reinforcement learning (RL) approaches are currently underutilized and could be better leveraged to improve performance in this domain.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3689-3698"},"PeriodicalIF":4.8,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10695459","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142345946","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 : 2024-09-26DOI: 10.1109/TNSRE.2024.3468339
Xiaoshan Xie;Min Yang
Medical image segmentation is a crucial component of computer-aided clinical diagnosis, with state-of-the-art models often being variants of U-Net. Despite their success, these models’ skip connections introduce an unnecessary semantic gap between the encoder and decoder, which hinders their ability to achieve the high precision required for clinical applications. Awareness of this semantic gap and its detrimental influences have increased over time. However, a quantitative understanding of how this semantic gap compromises accuracy and reliability remains lacking, emphasizing the need for effective mitigation strategies. In response, we present the first quantitative evaluation of the semantic gap between corresponding layers of U-Net and identify two key characteristics: 1) The direct skip connection (DSC) exhibits a semantic gap that negatively impacts models’ performance; 2) The magnitude of the semantic gap varies across different layers. Based on these findings, we re-examine this issue through the lens of skip connections. We introduce a Multichannel Fusion Transformer (MCFT) and propose a novel USCT-UNet architecture, which incorporates U-shaped skip connections (USC) to replace DSC, allocates varying numbers of MCFT blocks based on the semantic gap magnitude at different layers, and employs a spatial channel cross-attention (SCCA) module to facilitate the fusion of features between the decoder and USC. We evaluate USCT-UNet on four challenging datasets, and the results demonstrate that it effectively eliminates the semantic gap. Compared to using DSC, our USC and SCCA strategies achieve maximum improvements of 4.79% in the Dice coefficient, 5.70% in mean intersection over union (MIoU), and 3.26 in Hausdorff distance.
{"title":"USCT-UNet: Rethinking the Semantic Gap in U-Net Network From U-Shaped Skip Connections With Multichannel Fusion Transformer","authors":"Xiaoshan Xie;Min Yang","doi":"10.1109/TNSRE.2024.3468339","DOIUrl":"10.1109/TNSRE.2024.3468339","url":null,"abstract":"Medical image segmentation is a crucial component of computer-aided clinical diagnosis, with state-of-the-art models often being variants of U-Net. Despite their success, these models’ skip connections introduce an unnecessary semantic gap between the encoder and decoder, which hinders their ability to achieve the high precision required for clinical applications. Awareness of this semantic gap and its detrimental influences have increased over time. However, a quantitative understanding of how this semantic gap compromises accuracy and reliability remains lacking, emphasizing the need for effective mitigation strategies. In response, we present the first quantitative evaluation of the semantic gap between corresponding layers of U-Net and identify two key characteristics: 1) The direct skip connection (DSC) exhibits a semantic gap that negatively impacts models’ performance; 2) The magnitude of the semantic gap varies across different layers. Based on these findings, we re-examine this issue through the lens of skip connections. We introduce a Multichannel Fusion Transformer (MCFT) and propose a novel USCT-UNet architecture, which incorporates U-shaped skip connections (USC) to replace DSC, allocates varying numbers of MCFT blocks based on the semantic gap magnitude at different layers, and employs a spatial channel cross-attention (SCCA) module to facilitate the fusion of features between the decoder and USC. We evaluate USCT-UNet on four challenging datasets, and the results demonstrate that it effectively eliminates the semantic gap. Compared to using DSC, our USC and SCCA strategies achieve maximum improvements of 4.79% in the Dice coefficient, 5.70% in mean intersection over union (MIoU), and 3.26 in Hausdorff distance.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3782-3793"},"PeriodicalIF":4.8,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10695464","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142345952","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 : 2024-09-25DOI: 10.1109/TNSRE.2024.3465515
Quang Manh Doan;Tran Hiep Dinh;Avinash Kumar Singh;Chin-Teng Lin;Nguyen Linh Trung
Smoothing filters are widely used in EEG signal processing for noise removal while preserving signals’ features. Inspired by our recent work on Upscale and Downscale Representation (UDR), this paper proposes a cascade arrangement of some effective image-processing techniques for signal filtering in the image domain. The UDR concept is to visualize EEG signals at an appropriate line width and convert it to a binary image. The smoothing process is then conducted by skeletonizing the signal object to a unit width and projecting it back to the time domain. Two successive UDRs could result in a better-smoothing performance, but their binary image conversion should be restricted. The process is computationally ineffective, especially at higher line width values. Cascaded Thinning UDR (CTUDR) is proposed, exploiting morphological operations to perform a two-stage upscale and downscale within one binary image representation. CTUDR is verified on a signal smoothing and classification task and compared with conventional techniques, such as the Moving Average, the Binomial, the Median, and the Savitzky Golay filters. Simulated EEG data with added white Gaussian noise is employed in the former, while cognitive conflict data obtained from a 3D object selection task is utilized in the latter. CTUDR outperforms its counterparts, scoring the best fitting error and correlation coefficient in signal smoothing while achieving the highest gain in Accuracy (0.7640%) and F-measure (0.7607%) when used as a smoothing filter for training data of EEGNet.
{"title":"Cascaded Thinning in Upscale and Downscale Representation for EEG Signal Processing","authors":"Quang Manh Doan;Tran Hiep Dinh;Avinash Kumar Singh;Chin-Teng Lin;Nguyen Linh Trung","doi":"10.1109/TNSRE.2024.3465515","DOIUrl":"10.1109/TNSRE.2024.3465515","url":null,"abstract":"Smoothing filters are widely used in EEG signal processing for noise removal while preserving signals’ features. Inspired by our recent work on Upscale and Downscale Representation (UDR), this paper proposes a cascade arrangement of some effective image-processing techniques for signal filtering in the image domain. The UDR concept is to visualize EEG signals at an appropriate line width and convert it to a binary image. The smoothing process is then conducted by skeletonizing the signal object to a unit width and projecting it back to the time domain. Two successive UDRs could result in a better-smoothing performance, but their binary image conversion should be restricted. The process is computationally ineffective, especially at higher line width values. Cascaded Thinning UDR (CTUDR) is proposed, exploiting morphological operations to perform a two-stage upscale and downscale within one binary image representation. CTUDR is verified on a signal smoothing and classification task and compared with conventional techniques, such as the Moving Average, the Binomial, the Median, and the Savitzky Golay filters. Simulated EEG data with added white Gaussian noise is employed in the former, while cognitive conflict data obtained from a 3D object selection task is utilized in the latter. CTUDR outperforms its counterparts, scoring the best fitting error and correlation coefficient in signal smoothing while achieving the highest gain in Accuracy (0.7640%) and F-measure (0.7607%) when used as a smoothing filter for training data of EEGNet.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3677-3688"},"PeriodicalIF":4.8,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10693637","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142345948","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 : 2024-09-25DOI: 10.1109/TNSRE.2024.3467692
Rafael Ornelas-Kobayashi;Ivan Gomez-Orozco;Antonio Gogeascoechea;Edwin Van Asseldonk;Massimo Sartori
The central nervous system employs distinct motor control strategies depending on task demands. Accordingly, the activity of alpha-motoneuron (MN) pools innervating skeletal muscle fibers is modulated based on muscle force and rate of force development (RFD). In human subjects, biophysical MN models enable inferring in vivo the neural processes (e.g., synaptic input, activity of the entire MN pool, etc.) underlying this modulation, which are otherwise challenging to measure experimentally. Due to unique neurophysiological characteristics of individuals, personalizing these models is essential to study motor control in humans. Therefore, this work studied the mechanisms involved in the modulation of RFD using person-specific MN pool models driven by in vivo common synaptic input estimates (i.e., derived from surface high-density electromyography). Specifically, we assessed how in vivo MN activity changed across RFD and muscle force. This included modulation of recruitment and rate coding in the complete MN pool, as well as model-based estimates of excitatory synaptic gains ( $Delta $ IF). We found RFD-specific changes in MN activity associated to changes in $Delta $ IF. Moreover, we showed that MN pool models driven by RFD-specific $Delta $ IFs reproduced in vivo MN firing features and associated force profiles at different RFDs. Altogether, this work represents a step towards modelling the mechanisms of force generation in humans and creating person-specific models of the spinal circuitry. This will open a window for studying in vivo human neuromechanics and motor restoring interventions.
{"title":"Personalized Alpha-Motoneuron Pool Models Driven by Neural Data Encode the Mechanisms Controlling Rate of Force Development","authors":"Rafael Ornelas-Kobayashi;Ivan Gomez-Orozco;Antonio Gogeascoechea;Edwin Van Asseldonk;Massimo Sartori","doi":"10.1109/TNSRE.2024.3467692","DOIUrl":"10.1109/TNSRE.2024.3467692","url":null,"abstract":"The central nervous system employs distinct motor control strategies depending on task demands. Accordingly, the activity of alpha-motoneuron (MN) pools innervating skeletal muscle fibers is modulated based on muscle force and rate of force development (RFD). In human subjects, biophysical MN models enable inferring in vivo the neural processes (e.g., synaptic input, activity of the entire MN pool, etc.) underlying this modulation, which are otherwise challenging to measure experimentally. Due to unique neurophysiological characteristics of individuals, personalizing these models is essential to study motor control in humans. Therefore, this work studied the mechanisms involved in the modulation of RFD using person-specific MN pool models driven by in vivo common synaptic input estimates (i.e., derived from surface high-density electromyography). Specifically, we assessed how in vivo MN activity changed across RFD and muscle force. This included modulation of recruitment and rate coding in the complete MN pool, as well as model-based estimates of excitatory synaptic gains (\u0000<inline-formula> <tex-math>$Delta $ </tex-math></inline-formula>\u0000IF). We found RFD-specific changes in MN activity associated to changes in \u0000<inline-formula> <tex-math>$Delta $ </tex-math></inline-formula>\u0000IF. Moreover, we showed that MN pool models driven by RFD-specific \u0000<inline-formula> <tex-math>$Delta $ </tex-math></inline-formula>\u0000IFs reproduced in vivo MN firing features and associated force profiles at different RFDs. Altogether, this work represents a step towards modelling the mechanisms of force generation in humans and creating person-specific models of the spinal circuitry. This will open a window for studying in vivo human neuromechanics and motor restoring interventions.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3699-3709"},"PeriodicalIF":4.8,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10693625","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142345950","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.2024.3465243
Chia-Hung Cho;Pin-Jui Huang;Meng-Chao Chen;Chii-Wann Lin
Deep Brain Stimulation (DBS) is effective for movement disorders, particularly Parkinson’s disease (PD). However, a closed-loop DBS system using reinforcement learning (RL) for automatic parameter tuning, offering enhanced energy efficiency and the effect of thalamus restoration, is yet to be developed for clinical and commercial applications. In this research, we instantiate a basal ganglia-thalamic (BGT) model and design it as an interactive environment suitable for RL models. Four finely tuned RL agents based on different frameworks, namely Soft Actor-Critic (SAC), Twin Delayed Deep Deterministic Policy Gradient (TD3), Proximal Policy Optimization (PPO), and Advantage Actor-Critic (A2C), are established for further comparison. Within the implemented RL architectures, the optimized TD3 demonstrates a significant 67% reduction in average power dissipation when compared to the open-loop system while preserving the normal response of the simulated BGT circuitry. As a result, our method mitigates thalamic error responses under pathological conditions and prevents overstimulation. In summary, this study introduces a novel approach to implementing an adaptive parameter-tuning closed-loop DBS system. Leveraging the advantages of TD3, our proposed approach holds significant promise for advancing the integration of RL applications into DBS systems, ultimately optimizing therapeutic effects in future clinical trials.
{"title":"Closed-Loop Deep Brain Stimulation With Reinforcement Learning and Neural Simulation","authors":"Chia-Hung Cho;Pin-Jui Huang;Meng-Chao Chen;Chii-Wann Lin","doi":"10.1109/TNSRE.2024.3465243","DOIUrl":"10.1109/TNSRE.2024.3465243","url":null,"abstract":"Deep Brain Stimulation (DBS) is effective for movement disorders, particularly Parkinson’s disease (PD). However, a closed-loop DBS system using reinforcement learning (RL) for automatic parameter tuning, offering enhanced energy efficiency and the effect of thalamus restoration, is yet to be developed for clinical and commercial applications. In this research, we instantiate a basal ganglia-thalamic (BGT) model and design it as an interactive environment suitable for RL models. Four finely tuned RL agents based on different frameworks, namely Soft Actor-Critic (SAC), Twin Delayed Deep Deterministic Policy Gradient (TD3), Proximal Policy Optimization (PPO), and Advantage Actor-Critic (A2C), are established for further comparison. Within the implemented RL architectures, the optimized TD3 demonstrates a significant 67% reduction in average power dissipation when compared to the open-loop system while preserving the normal response of the simulated BGT circuitry. As a result, our method mitigates thalamic error responses under pathological conditions and prevents overstimulation. In summary, this study introduces a novel approach to implementing an adaptive parameter-tuning closed-loop DBS system. Leveraging the advantages of TD3, our proposed approach holds significant promise for advancing the integration of RL applications into DBS systems, ultimately optimizing therapeutic effects in future clinical trials.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"32 ","pages":"3615-3624"},"PeriodicalIF":4.8,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10684783","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142286181","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：