ABSTRACT
【Objective】 To observe the effects of mirror neuron system theory(MNST) on hand dexterity and fine motor function in preschool children with developmental coordination disorder(DCD), so as to provide reference for the rehabilitation of children with DCD. 【Methods】 A total of 51 children with DCD treated at Nantong Maternal and Child Health Care Hospital from June 2021 to April 2023 were enrolled in this study, and were randomly assigned to treatment group (n=26) and control group (n=25) except for 5 cases who missed in the follow-up. Both groups received conventional rehabilitation training, while the treatment group received MNST additionally. The hand dexterity and fine motor function of both groups were assessed using the hand dexterity subscale of the Movement Assessment Battery for Children-Second Edition (MABC-2), Peabody Developmental Motor Scale-Fine Motor (PDMS-FM), and Function Independence Measure for Children (WeeFIM) before and after 12 weeks of treatment. 【Results】 Before treatment, there were no significant differences in hand dexterity subscale of MABC-2, PDMS-FM, and WeeFIM scores between the two groups (P>0.05). After treatment, both groups showed improvements in hand dexterity subscale of MABC-2, PDMS-FM, and WeeFIM scores (treatment group: t=35.620, 42.084, 40.072; control group: t=14.000, 12.017, 14.054, P<0.001), with the treatment group showing significantly greater improvements compared to the control group (t=2.611, 3.120, 2.331, P<0.05). 【Conclusion】 MNST combined with conventional rehabilitation training can enhance hand dexterity and fine motor function in children with DCD, thereby improving children′s activities of daily living.
ABSTRACT
To address the problem of low accuracy in multi-classification recognition of motor imagery electroencephalogram(EEG)signals,a recognition method is proposed based on differential entropy and convolutional neural network for 4-class classification of motor imagery.EEG signals are extracted into 4 frequency bands(Alpha,Beta,Theta,and Gamma)through the filter,followed by the computation of differential entropy for each frequency band.According to the spatial characteristics of brain electrodes,the data structure is reconstructed into three-dimensional EEG signal feature cube which is input into convolutional neural network for 4-class classification.The method achieves an accuracy of 95.88%on the BCI Competition IV-2a public dataset.Additionally,a 4-class classification motor imagery dataset is established in the laboratory for the same processing,and an accuracy of 94.50%is obtained.The test results demonstrate that the proposed method exhibits superior recognition performance.
ABSTRACT
Objective:Aiming at the problem of target user electroencephalogram (EEG) recognition, an EEG recognition method was presented based on common spatial patterns (CSP) and transfer learning.Methods:Firstly, preprocess was adopted on the original EEG data, and time windows 0.5~2.5 s and broad frequency band 8~30 Hz EEG signals, which contained α and β wave, were selected. Here event-related desynchronization (ERD) phenomenon existed significant differences. Afterwards, by CSP preprocessed EEG signals of multi-user were conducted to extract feature and feature vectors were obtained, respectively. Finally, by transfer learning target user EEG recognition was completed.Results:In channel Cz, ERD of right hand motor imagery was higher than ERD of foot motor imagery. The classification accuracy of users aa, al, av, aw, and ay were 93.8%, 100.0%, 84.2%, 94.6%, and 94.4%, respectively. The average classification accuracy was 92.4%, which was better than the commonly used classifiers SVM and EM. The method was only lower than the method of the first winner in the competition adopted by Tsinghua University 1.8%.Conclusions:EEG recognition method based on CSP and transfer learning increased target user EEG recognition performance by using non-target users and had important implications for the study of motor imagery brain-computer interface.
ABSTRACT
ObjectiveTo observe the effect of motor imagery therapy on hand function and motor imagery ability of stroke patients. MethodsFrom March, 2018 to March, 2020, 41 stroke patients in Beijing Bo'ai Hospital were selected and randomly divided into control group (n = 20) and observation group (n = 21). Both groups received conventional rehabilitation training, and the observation group received motor imagery therapy in addition, for four weeks. Before and after training, the scores of Fugl-Meyer Assessment-Hand (FMA-H) and Kinesthetic and Visual Imagery Questionnaire-10 (KVIQ-10), and the accuracy of mental rotation task were compared between two groups. ResultsOne patient in the observation group dropped down. Before training, there was no significant difference in the scores of FMA-H and KVIQ, and the accuracy of mental rotation task between two groups (P > 0.05). After training, all the indexes improved in both groups (t > 6.611, P < 0.001), and the scores of FMA-H (t = 3.742, P < 0.001) and KVIQ (t = 4.122, P < 0.001), and the accuracy of mental rotation task (t = 2.075, P < 0.05) were higher in the observation group than in the control group. ConclusionMotor imagery therapy could facilliate the recovery of hand dysfunction and improve the motor imagery ability of stroke patients.
ABSTRACT
ObjectiveTo explore the effects of graded motor imagery (GMI) combined with repetitive transcranial magnetic stimulation (rTMS) on upper limb function and activities of daily living of stroke patients. MethodsFrom June, 2022 to February, 2023, 45 stroke patients from Xuzhou Rehabilitation Hospital and Xuzhou Central Hospital were recruited and divided into control group (n = 15), GMI group (n = 15) and combined group (n = 15) randomly. All the groups received conventional rehabilitation, in addition, GMI group received GMI and the combined group received GMI and rTMS, for four weeks. They were assessed with Fugl-Meyer Assessment-Upper Extremities (FMA-UE), Action Research Arm Test (ARAT), modified Barthel Index (MBI) and Hong Kong version of Functional Test for the Hemiplegic Upper Extremity (FTHUE-HK) before and after treatment. ResultsThe scores of FMA-UE, ARAT and MBI, and grades of FTHUE-HK improved in all the groups after treatment (|t| > 9.681, P < 0.001), and all these indexes were the best in the combined group (F > 13.241, P < 0.001). ConclusionGMI combined with rTMS can further improve the motor function of upper limbs and activities of daily living of stroke patients.
ABSTRACT
Stroke is a disease with a high disability rate, and often leads to limb dysfunction, especially upper limb motor dysfunction, which significantly affects the patients’ abilities and quality of life. With patients' increasing demand for functional recovery, various therapeutic techniques of rehabilitation medicine have been rapidly developed. As an important active central intervention technology, motor imagery training can be initiated by the patient's brain and activate the sensorimotor network to accelerate the repair of limb functions. The development of preventive medicine has promoted the continuous evolution of the concept of rehabilitation. The strategies of full cycle functional protection and disability prevention have been improved and developed in the clinical and scientific research practice of upper limb rehabilitation after stroke. The motor imagery training can activate the upper limb motor neural network in the early stage of stroke to prevent functional loss; In the recovery period, it can accelerate the neural function remodeling and reduce the upper limb disability; In the later stage after stroke, it can improve the performance of upper limb function in daily life, thus helping patients return to family life and society. This article reviews the research progress in recent years in China and abroad in the application of motor imagery training for the full cycle function protection and disability prevention of stroke.
ABSTRACT
ObjectiveTo explore the effect of motor imagery (MI) on knee function after unicompartmental knee arthroplasty (UKA). MethodsFrom January to September, 2022, 32 patients underwent UKA for the first time in Xuanwu Hospital were randomly divided into control group (n = 16) and experimental group (n = 16). All the patients accepted routine rehabilitation, and the experimental group accepted MI in addition, until four weeks after discharge. They were assessed with Oxford Knee Score (OKS), Visual Analogue Scale for pain (VAS), range of motion (ROM) of knee, and Timed Up and Go Test (TUGT) before and after treatment. ResultsAll the indexes improved after treatment (|t| > 2.517, P < 0.05), except ROM in the control group; and they improved more in the experimental group than in the control group (F > 7.999, P < 0.01), except the VAS score. ConclusionMI can further improve the knee function after UKA, but do less for pain.
ABSTRACT
ObjectiveTo observe the effect of brain-computer interface (BCI) training based on motor imagery on hand function in hemiplegic patients with subacute stroke. MethodsFrom June, 2020 to December, 2021, 40 patients with hemiplegia in subacute stroke from Department of Rehabilitation Medicine, Fifth Affiliated Hospital of Zhengzhou University were divided into control group (n = 20) and experimental group (n = 20) using random number table. Both groups accepted medication and routine comprehensive rehabilitation, while the control group accepted hand rehabilitation robot training, and the experimental group accepted the robot training using motor imagery-based BCI, for four weeks. They were assessed with Fugl-Meyer Assessment-Upper Extremities (FMA-UE), modified Barthel Index, modified Ashworth scale, and measured integrated electromyogram of the superficial finger flexors, finger extensors and short thumb extensors of the affected forearm during maximum isometric voluntary contraction with surface electromyography. ResultsTwo patients in the control group and one in the experimental group dropped off. All the indexes improved in both groups after treatment (t > 2.322, Z > 2.631, P < 0.05), and they were better in the experimental group than in the control group (t > 2.227, Z > 2.078, P < 0.05), except the FMA-UE score of wrist. ConclusionMotor imagery-based BCI training is more effective on hand function and activities of daily living in hemiplegic patients with subacute stroke.
ABSTRACT
The brain-computer interface (BCI) based on motor imagery electroencephalography (MI-EEG) enables direct information interaction between the human brain and external devices. In this paper, a multi-scale EEG feature extraction convolutional neural network model based on time series data enhancement is proposed for decoding MI-EEG signals. First, an EEG signals augmentation method was proposed that could increase the information content of training samples without changing the length of the time series, while retaining its original features completely. Then, multiple holistic and detailed features of the EEG data were adaptively extracted by multi-scale convolution module, and the features were fused and filtered by parallel residual module and channel attention. Finally, classification results were output by a fully connected network. The application experimental results on the BCI Competition IV 2a and 2b datasets showed that the proposed model achieved an average classification accuracy of 91.87% and 87.85% for the motor imagery task, respectively, which had high accuracy and strong robustness compared with existing baseline models. The proposed model does not require complex signals pre-processing operations and has the advantage of multi-scale feature extraction, which has high practical application value.
Subject(s)
Humans , Time Factors , Brain , Electroencephalography , Imagery, Psychotherapy , Neural Networks, ComputerABSTRACT
Transfer learning is provided with potential research value and application prospect in motor imagery electroencephalography (MI-EEG)-based brain-computer interface (BCI) rehabilitation system, and the source domain classification model and transfer strategy are the two important aspects that directly affect the performance and transfer efficiency of the target domain model. Therefore, we propose a parameter transfer learning method based on shallow visual geometry group network (PTL-sVGG). First, Pearson correlation coefficient is used to screen the subjects of the source domain, and the short-time Fourier transform is performed on the MI-EEG data of each selected subject to acquire the time-frequency spectrogram images (TFSI). Then, the architecture of VGG-16 is simplified and the block design is carried out, and the modified sVGG model is pre-trained with TFSI of source domain. Furthermore, a block-based frozen-fine-tuning transfer strategy is designed to quickly find and freeze the block with the greatest contribution to sVGG model, and the remaining blocks are fine-tuned by using TFSI of target subjects to obtain the target domain classification model. Extensive experiments are conducted based on public MI-EEG datasets, the average recognition rate and Kappa value of PTL-sVGG are 94.9% and 0.898, respectively. The results show that the subjects' optimization is beneficial to improve the model performance in source domain, and the block-based transfer strategy can enhance the transfer efficiency, realizing the rapid and effective transfer of model parameters across subjects on the datasets with different number of channels. It is beneficial to reduce the calibration time of BCI system, which promote the application of BCI technology in rehabilitation engineering.
Subject(s)
Humans , Algorithms , Brain-Computer Interfaces , Electroencephalography/methods , Imagination , Machine LearningABSTRACT
Objective: To observe the effects of Tuina (Chinese therapeutic massage) combined with graded motor imagery (GMI) on the upper-limb motor function and quality of life (QOL) in patients with poststroke hemiplegia.Methods: A total of 216 patients with hemiplegia caused by stroke were randomized into two groups by tossing a coin, with 108 cases in each group. The control group was treated with GMI, and the observation group was given additional Tuina treatment for four weeks in total. Before and after the treatment, the Fugl-Meyer assessment for upper extremity (FMA-UE), supper-limb/hand Brunnstrom staging, box and block test (BBT) for hand, co-contraction ratio (CR) of the upper-limb muscles, visual analog scale (VAS) for shoulder pain, modified Ashworth scale (MAS), modified Barthel index (MBI), and short-form 36-item health survey (SF-36) were adopted for observation of the two groups. Results: After the treatment, the scores of FMA-UE, upper-limb/hand Brunnstrom staging, hand BBT, MBI, and SF-36 increased (P<0.05), and the CR of biceps brachii at flexion, the CR of triceps brachii at extension, and the scores of VAS and MAS decreased in both groups (P<0.05). The scores of FMA-UE, upper-limb/hand Brunnstrom staging, and hand BBT were higher in the observation group than in the control group after the intervention (P<0.05); the CR of biceps brachii at flexion and the CR of triceps brachii at extension were lower in the observation group than in the control group (P<0.05). After the treatment, the scores of MBI and SF-36 were higher in the observation group than in the control group (P<0.05), and the scores of VAS and MAS were lower in the observation group than in the control group (P<0.05). Conclusion: Tuina combined with GMI can produce more significant effects in improving the upper-limb motor function and QOL in patients with hemiplegia after stroke.
ABSTRACT
Objective:To observe any effect of combining motor imagery therapy (MIT) with repeated transcranial magnetic stimulation (rTMS) for improving upper limb motor functioning after a stroke.Methods:Ninety stroke survivors were randomly divided into a control group, an MIT group and a combination group, each of 30. All received conventional rehabilitation therapy, while the MIT group additionally received MIT and the combination group received the MIT along with 1Hz rTMS applied over the M1 region of the contralateral cortex. Before and after 4 weeks of treatment, everyone′s upper limb functioning was quantified using the Fugl-Meyer assessment scale (FMA) and the Hong Kong version of the hemiplegia upper limb function test (FTHUE-HK). Motor evoked potentials (MEPs), cortical latency (CL) and central motor conduction time (CMCT) were also recorded.Results:After the treatment the average FMA and FTHUE-HK scores of all three groups had improved significantly. The average CL and CMCT were significantly shortened. Compared with the control group, the average upper limb FMA score and FTHUE-HK scores of the treatment group were significantly higher. The combination group showed a significant improvement in its average MEP cortical latency and CMCT values.Conclusions:MIT therapy alone can improve the upper limb motor functioning of stroke survivors, but it is more effective in combination with rTMS.
ABSTRACT
The effective classification of multi-task motor imagery electroencephalogram (EEG) is helpful to achieve accurate multi-dimensional human-computer interaction, and the high frequency domain specificity between subjects can improve the classification accuracy and robustness. Therefore, this paper proposed a multi-task EEG signal classification method based on adaptive time-frequency common spatial pattern (CSP) combined with convolutional neural network (CNN). The characteristics of subjects' personalized rhythm were extracted by adaptive spectrum awareness, and the spatial characteristics were calculated by using the one-versus-rest CSP, and then the composite time-domain characteristics were characterized to construct the spatial-temporal frequency multi-level fusion features. Finally, the CNN was used to perform high-precision and high-robust four-task classification. The algorithm in this paper was verified by the self-test dataset containing 10 subjects (33 ± 3 years old, inexperienced) and the dataset of the 4th 2018 Brain-Computer Interface Competition (BCI competition Ⅳ-2a). The average accuracy of the proposed algorithm for the four-task classification reached 93.96% and 84.04%, respectively. Compared with other advanced algorithms, the average classification accuracy of the proposed algorithm was significantly improved, and the accuracy range error between subjects was significantly reduced in the public dataset. The results show that the proposed algorithm has good performance in multi-task classification, and can effectively improve the classification accuracy and robustness.
Subject(s)
Humans , Adult , Imagination , Neural Networks, Computer , Imagery, Psychotherapy/methods , Electroencephalography/methods , Algorithms , Brain-Computer Interfaces , Signal Processing, Computer-AssistedABSTRACT
Aiming at the problem of low recognition accuracy of motor imagery electroencephalogram signal due to individual differences of subjects, an individual adaptive feature representation method of motor imagery electroencephalogram signal is proposed in this paper. Firstly, based on the individual differences and signal characteristics in different frequency bands, an adaptive channel selection method based on expansive relevant features with label F (ReliefF) was proposed. By extracting five time-frequency domain observation features of each frequency band signal, ReliefF algorithm was employed to evaluate the effectiveness of the frequency band signal in each channel, and then the corresponding signal channel was selected for each frequency band. Secondly, a feature representation method of common space pattern (CSP) based on fast correlation-based filter (FCBF) was proposed (CSP-FCBF). The features of electroencephalogram signal were extracted by CSP, and the best feature sets were obtained by using FCBF to optimize the features, so as to realize the effective state representation of motor imagery electroencephalogram signal. Finally, support vector machine (SVM) was adopted as a classifier to realize identification. Experimental results show that the proposed method in this research can effectively represent the states of motor imagery electroencephalogram signal, with an average identification accuracy of (83.0±5.5)% for four types of states, which is 6.6% higher than the traditional CSP feature representation method. The research results obtained in the feature representation of motor imagery electroencephalogram signal lay the foundation for the realization of adaptive electroencephalogram signal decoding and its application.
Subject(s)
Humans , Imagination , Signal Processing, Computer-Assisted , Brain-Computer Interfaces , Electroencephalography/methods , Imagery, Psychotherapy , AlgorithmsABSTRACT
Objective:To explore the effect of combining motor imagery therapy (MIT) with kinesio taping in rehabilitating the upper limb motor function of stroke survivors.Methods:Ninety-two stroke survivors were randomized into a control group ( n=31), an MIT group ( n=31), and a combination group ( n=30). All were given 40 minutes of basic rehabilitation therapy daily, while the MIT group received additional MIT therapy, and the combination group received kinesio taping with the MIT therapy. The taping was applied according to a patient′s condition and changed every other day. The MIT was conducted twice a day. The experiment lasted 8 weeks, six days a week. Before and after the 8 weeks, the upper limb functioning, ability in the activities of daily living and muscle tension of each subject were assessed using the Fugl-Meyer assessment for the upper extremities (FMA-UE), the Hong Kong version of the functional test for a hemiplegic upper extremity (FTHUE-HK), the modified Barthel index (MBI) and the modified Ashworth scale (MAS). Results:The average post-treatment FMA-UE and MBI scores of the combination group were significantly higher than those of the MIT group, and both were significantly higher than the control group′s averages. The average FTHUE-HK grading of the combination group and MIT group after the treatment was significantly higher than in the control group, with that of the combination group significantly superior to the MIT group′s average. After the intervention the average MAS rating of the combination group was significantly lower than that of the control group.Conclusion:MIT combined with Kinesio taping can significantly improve the upper limb motor functioning of stroke survivors, and significantly reduce their abnormal muscle tone compared to traditional treatments.
ABSTRACT
Motor imagery electroencephalogram (EEG) signals are non-stationary time series with a low signal-to-noise ratio. Therefore, the single-channel EEG analysis method is difficult to effectively describe the interaction characteristics between multi-channel signals. This paper proposed a deep learning network model based on the multi-channel attention mechanism. First, we performed time-frequency sparse decomposition on the pre-processed data, which enhanced the difference of time-frequency characteristics of EEG signals. Then we used the attention module to map the data in time and space so that the model could make full use of the data characteristics of different channels of EEG signals. Finally, the improved time-convolution network (TCN) was used for feature fusion and classification. The BCI competition IV-2a data set was used to verify the proposed algorithm. The experimental results showed that the proposed algorithm could effectively improve the classification accuracy of motor imagination EEG signals, which achieved an average accuracy of 83.03% for 9 subjects. Compared with the existing methods, the classification accuracy of EEG signals was improved. With the enhanced difference features between different motor imagery EEG data, the proposed method is important for the study of improving classifier performance.
Subject(s)
Humans , Algorithms , Brain-Computer Interfaces , Electroencephalography/methods , Imagery, Psychotherapy , ImaginationABSTRACT
Motor imagery (MI), motion intention of the specific body without actual movements, has attracted wide attention in fields as neuroscience. Classification algorithms for motor imagery electroencephalogram (MI-EEG) signals are able to distinguish different MI tasks based on the physiological information contained by the EEG signals, especially the features extracted from them. In recent years, there have been some new advances in classification algorithms for MI-EEG signals in terms of classifiers versus machine learning strategies. In terms of classifiers, traditional machine learning classifiers have been improved by some researchers, deep learning and Riemannian geometry classifiers have been widely applied as well. In terms of machine learning strategies, ensemble learning, adaptive learning, and transfer learning strategies have been utilized to improve classification accuracies or reach other targets. This paper reviewed the progress of classification algorithms for MI-EEG signals, summarized and evaluated the existing classifiers and machine learning strategies, to provide new ideas for developing classification algorithms with higher performance.
Subject(s)
Algorithms , Brain-Computer Interfaces , Electroencephalography , Imagery, Psychotherapy , Imagination , Machine LearningABSTRACT
Objective:To observe the effects of functional electrical stimulation (FES) controlled by brain-computer interface on upper limb motor dysfunction in stroke patients. Methods:From July, 2019 to November, 2020, 34 stroke patients hospitalized in neurological rehabilitation department were randomly divided into control group (n = 17) and experimental group (n = 17). They were treated with simple FES and FES controlled by brain-computer interface, respectively. The reaction time, joint position error of elbow joint, the scores of Fugl-Meyer Assessment-Upper Extremity (FMA-UE), modified Barthel Index (MBI) and event-related desynchronization (ERD) powers of affected upper limb were evaluated before and after intervention. Results:After intervention, the reaction time, joint position error of the elbow joint, the scores of FMA, MBI and ERD power of the affected elbow joint improved in both groups (F > 10.825, |Z| > 3.624, P < 0.05), and they were better in the experimental group than in the control group (F > 5.853, |Z| > 3.201, P < 0.05). Conclusion:FES controlled by brain-computer interface is positive on the rehabilitation of stroke patients with upper limb dysfunction.
ABSTRACT
Objective:To evaluate the effect of motor imagery training on motor and executive function in the older population. Methods:Articles about the impact of motor imagery training on the motor and cognitive functions of the elderly in the databases of Web of Sciences, PubMed, CNKI, Wanfang data and VIP were searched from 1980 to 2020. The training program, rehabilitation effect and relatec factors of motor image training in the elderly were analyzed and summarized. Results:Twelve articles were included finally. The motor image training that suited the elderly over 60 years old was usually combined with actual exercise training, mostly for four to twelve weeks, two to three times a week and 15 to 60 minutes a time. Motor imagery training was effective on standing balance, postural control, falls and muscle strength, to improve the ability to solve conflict problems, working memory and cognitive flexibility. Conclusion:Motor imagery training is an effective way to delay the decline of physical function and improve the executive function of the elderly. It is needed to construct a reasonable and standard motor imagery training program according to the characteristics of the elderly, to improve the effect.
ABSTRACT
Results and Conclusion:The mean of articles published was 70.5 a year. Germany, USA, UK were the top countries of cooperative documents; Tübingen University, Keio University and Shanghai Jiao Tong University were the top institutions. The most cooperative articles were involved the team of Gharabaghi A. Motor imagery-brain computer interface, network, motor function, especially walking function, may be the focuses in the future. Objective:To summarize the research structure of motor imagery applied in stroke and identify the hotspots and development. Methods:Literatures about motor imagery applied in stroke collected in Web of Science core database between 2010 to 2020 were obtained, and analyzed with CiteSpace software to draw the relevant knowledge mapping of related countries, institutions, authors, and keywords, etc.