1
|
Behmer LP. Mu-ERD reflects action understanding, but the effect is small. Brain Res 2024; 1832:148854. [PMID: 38493572 DOI: 10.1016/j.brainres.2024.148854] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2023] [Revised: 03/05/2024] [Accepted: 03/07/2024] [Indexed: 03/19/2024]
Abstract
Since the mid-2000's, many researchers have provided evidence that mu-ERD measured at the motor cortex may reflect the collective activation of upstream brain regions associated with the human mirror system during action observation paradigms; however, several recent papers have called these findings into question. Our study represents an effort to address these criticisms. In our study, participants watched videos in which the type of grip an actor used to grasp a coffee mug either conveyed the goal with 100 % certainty (unambiguous-goal trials), or offered no predictive information (ambiguous-goal trials). If mu-ERD indexes action understanding, then we predicted that mu-ERD should increase while participants watched the actor grasp the mug for unambiguous-goal trials, but not for ambiguous-goal trials. During the intervals where participants watched the actor execute the goal, mu-ERD for unambiguous-goal trials should remain steady, whereas mu-ERD for ambiguous-goal trials should now increase. Conversely, if mu-ERD does not index action understanding, and instead reflects general motor processes associated with action (such as the activation of population vectors in M1 or planning processes), then mu-ERD should show no difference across conditions. Across most comparisons, we found that mu-ERD mostly reflected general motor processes; however, there was a small effect when participants overserved unambiguous-goal trials while watching the actor execute the goal suggesting that mu-ERD does reflect mirroring, but the effect is small.
Collapse
|
2
|
Nagarajan A, Robinson N, Ang KK, Chua KSG, Chew E, Guan C. Transferring a deep learning model from healthy subjects to stroke patients in a motor imagery brain-computer interface. J Neural Eng 2024; 21:016007. [PMID: 38091617 DOI: 10.1088/1741-2552/ad152f] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2023] [Accepted: 12/13/2023] [Indexed: 01/18/2024]
Abstract
Objective.Motor imagery (MI) brain-computer interfaces (BCIs) based on electroencephalogram (EEG) have been developed primarily for stroke rehabilitation, however, due to limited stroke data, current deep learning methods for cross-subject classification rely on healthy data. This study aims to assess the feasibility of applying MI-BCI models pre-trained using data from healthy individuals to detect MI in stroke patients.Approach.We introduce a new transfer learning approach where features from two-class MI data of healthy individuals are used to detect MI in stroke patients. We compare the results of the proposed method with those obtained from analyses within stroke data. Experiments were conducted using Deep ConvNet and state-of-the-art subject-specific machine learning MI classifiers, evaluated on OpenBMI two-class MI-EEG data from healthy subjects and two-class MI versus rest data from stroke patients.Main results.Results of our study indicate that through domain adaptation of a model pre-trained using healthy subjects' data, an average MI detection accuracy of 71.15% (±12.46%) can be achieved across 71 stroke patients. We demonstrate that the accuracy of the pre-trained model increased by 18.15% after transfer learning (p<0.001). Additionally, the proposed transfer learning method outperforms the subject-specific results achieved by Deep ConvNet and FBCSP, with significant enhancements of 7.64% (p<0.001) and 5.55% (p<0.001) in performance, respectively. Notably, the healthy-to-stroke transfer learning approach achieved similar performance to stroke-to-stroke transfer learning, with no significant difference (p>0.05). Explainable AI analyses using transfer models determined channel relevance patterns that indicate contributions from the bilateral motor, frontal, and parietal regions of the cortex towards MI detection in stroke patients.Significance.Transfer learning from healthy to stroke can enhance the clinical use of BCI algorithms by overcoming the challenge of insufficient clinical data for optimal training.
Collapse
Affiliation(s)
- Aarthy Nagarajan
- School of Computer Science and Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore
| | - Neethu Robinson
- School of Computer Science and Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore
| | - Kai Keng Ang
- School of Computer Science and Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore
- Institute for Infocomm Research, Agency of Science, Technology and Research (A*STAR), 1 Fusionopolis Way, Singapore 138632, Singapore
| | - Karen Sui Geok Chua
- Department of Rehabilitation Medicine, Tan Tock Seng Hospital, 11 Jln Tan Tock Seng, Singapore 308433, Singapore
| | - Effie Chew
- National University Health System, 1E Kent Ridge Road, Singapore 119228, Singapore
| | - Cuntai Guan
- School of Computer Science and Engineering, Nanyang Technological University, 50 Nanyang Ave, Singapore 639798, Singapore
| |
Collapse
|
3
|
Xu F, Wang Y, Li H, Yu X, Wang C, Liu M, Jiang L, Feng C, Li J, Wang D, Yan Z, Zhang Y, Leng J. Time-Varying Effective Connectivity for Describing the Dynamic Brain Networks of Post-stroke Rehabilitation. Front Aging Neurosci 2022; 14:911513. [PMID: 35686023 PMCID: PMC9171495 DOI: 10.3389/fnagi.2022.911513] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/02/2022] [Accepted: 04/19/2022] [Indexed: 11/13/2022] Open
Abstract
Hemiplegia is a common motor dysfunction caused by a stroke. However, the dynamic network mechanism of brain processing information in post-stroke hemiplegic patients has not been revealed when performing motor imagery (MI) tasks. We acquire electroencephalography (EEG) data from healthy subjects and post-stroke hemiplegic patients and use the Fugl-Meyer assessment (FMA) to assess the degree of motor function damage in stroke patients. Time-varying MI networks are constructed using the adaptive directed transfer function (ADTF) method to explore the dynamic network mechanism of MI in post-stroke hemiplegic patients. Finally, correlation analysis has been conducted to study potential relationships between global efficiency and FMA scores. The performance of our proposed method has shown that the brain network pattern of stroke patients does not significantly change from laterality to bilateral symmetry when performing MI recognition. The main change is that the contralateral motor areas of the brain damage and the effective connection between the frontal lobe and the non-motor areas are enhanced, to compensate for motor dysfunction in stroke patients. We also find that there is a correlation between FMA scores and global efficiency. These findings help us better understand the dynamic brain network of patients with post-stroke when processing MI information. The network properties may provide a reliable biomarker for the objective evaluation of the functional rehabilitation diagnosis of stroke patients.
Collapse
Affiliation(s)
- Fangzhou Xu
- International School for Optoelectronic Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
- *Correspondence: Fangzhou Xu
| | - Yuandong Wang
- International School for Optoelectronic Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
- School of Electrical Engineering and Automation, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
| | - Han Li
- International School for Optoelectronic Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
- School of Electrical Engineering and Automation, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
| | - Xin Yu
- International School for Optoelectronic Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
- School of Electrical Engineering and Automation, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
| | - Chongfeng Wang
- International School for Optoelectronic Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
- School of Electrical Engineering and Automation, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
| | - Ming Liu
- International School for Optoelectronic Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
- School of Electrical Engineering and Automation, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
| | - Lin Jiang
- The Clinical Hospital of Chengdu Brain Science Institute, Ministry of Education Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, China
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China
| | - Chao Feng
- International School for Optoelectronic Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
| | - Jianfei Li
- International School for Optoelectronic Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
| | - Dezheng Wang
- The Department of Physical Medicine and Rehabilitation, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, China
| | - Zhiguo Yan
- School of Electrical Engineering and Automation, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
- Zhiguo Yan
| | - Yang Zhang
- The Department of Physical Medicine and Rehabilitation, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, China
- Yang Zhang
| | - Jiancai Leng
- International School for Optoelectronic Engineering, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
- Jiancai Leng
| |
Collapse
|
4
|
The Neurophysiological Impact of Subacute Stroke: Changes in Cortical Oscillations Evoked by Bimanual Finger Movement. Stroke Res Treat 2022; 2022:9772147. [PMID: 35154632 PMCID: PMC8831071 DOI: 10.1155/2022/9772147] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2021] [Revised: 12/08/2021] [Accepted: 12/29/2021] [Indexed: 11/17/2022] Open
Abstract
Introduction. To design more effective interventions, such as neurostimulation, for stroke rehabilitation, there is a need to understand early physiological changes that take place that may be relevant for clinical monitoring. We aimed to study changes in neurophysiology following recent ischemic stroke, both at rest and with motor planning and execution. Materials and Methods. We included 10 poststroke patients, between 7 and 10 days after stroke, and 20 age-matched controls to assess changes in cortical motor output via transcranial magnetic stimulation and in dynamics of oscillations, as recorded using electroencephalography (EEG). Results. We found significant differences in cortical oscillatory patterns comparing stroke patients with healthy participants, particularly in the beta rhythm during motor planning (
) and execution (
) of a complex movement with fingers from both hands simultaneously. Discussion. The stroke lesion induced a decrease in event-related desynchronization in patients, in comparison to controls, providing evidence for decreased disinhibition. Conclusions. After a stroke lesion, the dynamics of cortical oscillations is changed, with an increasing neural beta synchronization in the course of motor preparation and performance of complex bimanual finger tasks. The observed patterns may provide a potential functional measure that could be used to monitor and design interventional approaches in subacute stages.
Collapse
|
5
|
Li F, Jiang L, Zhang Y, Huang D, Wei X, Jiang Y, Yao D, Xu P, Li H. The time-varying networks of the wrist extension in post-stroke hemiplegic patients. Cogn Neurodyn 2021; 16:757-766. [PMID: 35847531 PMCID: PMC9279526 DOI: 10.1007/s11571-021-09738-2] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2021] [Revised: 10/05/2021] [Accepted: 10/19/2021] [Indexed: 01/16/2023] Open
Abstract
Hemiplegia is a common dysfunction caused by the brain stroke and leads to movement disability. Although the lateralization of movement-related potential, the event-related desynchronization, and more complicated inter-regional information coupling have been investigated, seldom studies have focused on investigating the dynamic information exchanging among multiple brain regions during motor execution for post-stroke hemiplegic patients. With high temporal-resolution electroencephalogram (EEG), the time-varying network is able to reflect the dynamical complex network modalities corresponding to the movements at a millisecond level. In our present study, the wrist extension experiment was designed, along with related EEG datasets being collected. Thereafter, the corresponding time-varying networks underlying the wrist extension were accordingly constructed by adopting the adaptive directed transfer function and then statistically explored, to further uncover the dynamic network deficits (i.e., motor dysfunction) in post-stroke hemiplegic patients. Results of this study found the effective connectivity between the stroked motor area and other areas decreased in patients when compared to healthy controls; on the contrary, the enhanced connectivity between non-stroked motor areas and other areas, especially the frontal and parietal-occipital lobes, were further identified for patients during their accomplishing the designed wrist extension, which might dynamically compensate for the deficited patients' motor behaviors. These findings not only helped deepen our knowledge of the mechanism underlying the patients' motor behaviors, but also facilitated the real-time strategies for clinical therapy of brain stroke, as well as providing a reliable biomarker to predict the future rehabilitation. Supplementary Information The online version contains supplementary material available at 10.1007/s11571-021-09738-2.
Collapse
|
6
|
Li MA, Wang RT, Wei LN. Fuzzy support vector machine with joint optimization of genetic algorithm and fuzzy c-means. Technol Health Care 2021; 29:921-937. [PMID: 33459673 DOI: 10.3233/thc-202619] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
BACKGROUND Motor imagery electroencephalogram (MI-EEG) play an important role in the field of neurorehabilitation, and a fuzzy support vector machine (FSVM) is one of the most used classifiers. Specifically, a fuzzy c-means (FCM) algorithm was used to membership calculation to deal with the classification problems with outliers or noises. However, FCM is sensitive to its initial value and easily falls into local optima. OBJECTIVE The joint optimization of genetic algorithm (GA) and FCM is proposed to enhance robustness of fuzzy memberships to initial cluster centers, yielding an improved FSVM (GF-FSVM). METHOD The features of each channel of MI-EEG are extracted by the improved refined composite multivariate multiscale fuzzy entropy and fused to form a feature vector for a trial. Then, GA is employed to optimize the initial cluster center of FCM, and the fuzzy membership degrees are calculated through an iterative process and further applied to classify two-class MI-EEGs. RESULTS Extensive experiments are conducted on two publicly available datasets, the average recognition accuracies achieve 99.89% and 98.81% and the corresponding kappa values are 0.9978 and 0.9762, respectively. CONCLUSION The optimized cluster centers of FCM via GA are almost overlapping, showing great stability, and GF-FSVM obtains higher classification accuracies and higher consistency as well.
Collapse
Affiliation(s)
- Ming-Ai Li
- Faculty of Information Technology, Beijing University of Technology, Beijing, China.,Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing, China.,Engineering Research Center of Digital Community, Ministry of Education, Beijing, China
| | - Ruo-Tu Wang
- Faculty of Information Technology, Beijing University of Technology, Beijing, China
| | - Li-Na Wei
- Faculty of Information Technology, Beijing University of Technology, Beijing, China
| |
Collapse
|