Large-Scale Cortical Network Analysis and Classification of MI-BCI Tasks Based on Bayesian Nonnegative Matrix Factorization
Motor imagery (MI) is a high-level cognitive process that has been widely applied to clinical rehabilitation and brain-computer interfaces (BCIs). However, the decoding of MI tasks still faces challenges, and the neural mechanisms underlying its application are unclear, which seriously hinders the d...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10550019/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850100900845060096 |
|---|---|
| author | Shiqi Yu Bin Mao Yuanhang Zhou Yunhong Liu Chanlin Yi Fali Li Dezhong Yao Peng Xu X. San Liang Tao Zhang |
| author_facet | Shiqi Yu Bin Mao Yuanhang Zhou Yunhong Liu Chanlin Yi Fali Li Dezhong Yao Peng Xu X. San Liang Tao Zhang |
| author_sort | Shiqi Yu |
| collection | DOAJ |
| description | Motor imagery (MI) is a high-level cognitive process that has been widely applied to clinical rehabilitation and brain-computer interfaces (BCIs). However, the decoding of MI tasks still faces challenges, and the neural mechanisms underlying its application are unclear, which seriously hinders the development of MI-based clinical applications and BCIs. Here, we combined EEG source reconstruction and Bayesian nonnegative matrix factorization (NMF) methods to construct large-scale cortical networks of left-hand and right-hand MI tasks. Compared to right-hand MI, the results showed that the significantly increased functional network connectivities (FNCs) mainly located among the visual network (VN), sensorimotor network (SMN), right temporal network, right central executive network, and right parietal network in the left-hand MI at the <inline-formula> <tex-math notation="LaTeX">$\beta $ </tex-math></inline-formula> (13-30Hz) and all (8-30Hz) frequency bands. For the network properties analysis, we found that the clustering coefficient, global efficiency, and local efficiency were significantly increased and characteristic path length was significantly decreased in left-hand MI compared to right-hand MI at the <inline-formula> <tex-math notation="LaTeX">$\beta $ </tex-math></inline-formula> and all frequency bands. These network pattern differences indicated that the left-hand MI may need more modulation of multiple large-scale networks (i.e., VN and SMN) mainly located in the right hemisphere. Finally, based on the spatial pattern network of FNC and network properties, we propose a classification model. The proposed model achieves a top classification accuracy of 78.2% in cross-subject two-class MI-BCI tasks. Overall, our findings provide new insights into the neural mechanisms of MI and a potential network biomarker to identify MI-BCI tasks. |
| format | Article |
| id | doaj-art-9cef0e2ca405494eb0090c0e10c67ed2 |
| institution | DOAJ |
| issn | 1534-4320 1558-0210 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj-art-9cef0e2ca405494eb0090c0e10c67ed22025-08-20T02:40:10ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102024-01-01322187219710.1109/TNSRE.2024.340987210550019Large-Scale Cortical Network Analysis and Classification of MI-BCI Tasks Based on Bayesian Nonnegative Matrix FactorizationShiqi Yu0https://orcid.org/0009-0003-9911-9975Bin Mao1Yuanhang Zhou2Yunhong Liu3Chanlin Yi4https://orcid.org/0000-0001-7989-2440Fali Li5https://orcid.org/0000-0002-2450-4591Dezhong Yao6https://orcid.org/0000-0002-8042-879XPeng Xu7https://orcid.org/0000-0002-7932-0386X. San Liang8Tao Zhang9https://orcid.org/0000-0002-2891-4213Mental Health Education Center and the School of Science, Xihua University, Chengdu, ChinaMental Health Education Center and the School of Science, Xihua University, Chengdu, ChinaMental Health Education Center and the School of Science, Xihua University, Chengdu, ChinaMental Health Education Center and the School of Science, Xihua University, Chengdu, ChinaClinical Hospital of Chengdu Brain Science Institute, MOE Key Laboratory for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, ChinaClinical Hospital of Chengdu Brain Science Institute, MOE Key Laboratory for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, ChinaClinical Hospital of Chengdu Brain Science Institute, MOE Key Laboratory for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, ChinaClinical Hospital of Chengdu Brain Science Institute, MOE Key Laboratory for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, ChinaArtificial Intelligence Department, Division of Frontier Research, Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai, ChinaMental Health Education Center and the School of Science, Xihua University, Chengdu, ChinaMotor imagery (MI) is a high-level cognitive process that has been widely applied to clinical rehabilitation and brain-computer interfaces (BCIs). However, the decoding of MI tasks still faces challenges, and the neural mechanisms underlying its application are unclear, which seriously hinders the development of MI-based clinical applications and BCIs. Here, we combined EEG source reconstruction and Bayesian nonnegative matrix factorization (NMF) methods to construct large-scale cortical networks of left-hand and right-hand MI tasks. Compared to right-hand MI, the results showed that the significantly increased functional network connectivities (FNCs) mainly located among the visual network (VN), sensorimotor network (SMN), right temporal network, right central executive network, and right parietal network in the left-hand MI at the <inline-formula> <tex-math notation="LaTeX">$\beta $ </tex-math></inline-formula> (13-30Hz) and all (8-30Hz) frequency bands. For the network properties analysis, we found that the clustering coefficient, global efficiency, and local efficiency were significantly increased and characteristic path length was significantly decreased in left-hand MI compared to right-hand MI at the <inline-formula> <tex-math notation="LaTeX">$\beta $ </tex-math></inline-formula> and all frequency bands. These network pattern differences indicated that the left-hand MI may need more modulation of multiple large-scale networks (i.e., VN and SMN) mainly located in the right hemisphere. Finally, based on the spatial pattern network of FNC and network properties, we propose a classification model. The proposed model achieves a top classification accuracy of 78.2% in cross-subject two-class MI-BCI tasks. Overall, our findings provide new insights into the neural mechanisms of MI and a potential network biomarker to identify MI-BCI tasks.https://ieeexplore.ieee.org/document/10550019/Motor imagerylarge-scale networkBayesian NMFfunctional network connectivitymachine learning |
| spellingShingle | Shiqi Yu Bin Mao Yuanhang Zhou Yunhong Liu Chanlin Yi Fali Li Dezhong Yao Peng Xu X. San Liang Tao Zhang Large-Scale Cortical Network Analysis and Classification of MI-BCI Tasks Based on Bayesian Nonnegative Matrix Factorization IEEE Transactions on Neural Systems and Rehabilitation Engineering Motor imagery large-scale network Bayesian NMF functional network connectivity machine learning |
| title | Large-Scale Cortical Network Analysis and Classification of MI-BCI Tasks Based on Bayesian Nonnegative Matrix Factorization |
| title_full | Large-Scale Cortical Network Analysis and Classification of MI-BCI Tasks Based on Bayesian Nonnegative Matrix Factorization |
| title_fullStr | Large-Scale Cortical Network Analysis and Classification of MI-BCI Tasks Based on Bayesian Nonnegative Matrix Factorization |
| title_full_unstemmed | Large-Scale Cortical Network Analysis and Classification of MI-BCI Tasks Based on Bayesian Nonnegative Matrix Factorization |
| title_short | Large-Scale Cortical Network Analysis and Classification of MI-BCI Tasks Based on Bayesian Nonnegative Matrix Factorization |
| title_sort | large scale cortical network analysis and classification of mi bci tasks based on bayesian nonnegative matrix factorization |
| topic | Motor imagery large-scale network Bayesian NMF functional network connectivity machine learning |
| url | https://ieeexplore.ieee.org/document/10550019/ |
| work_keys_str_mv | AT shiqiyu largescalecorticalnetworkanalysisandclassificationofmibcitasksbasedonbayesiannonnegativematrixfactorization AT binmao largescalecorticalnetworkanalysisandclassificationofmibcitasksbasedonbayesiannonnegativematrixfactorization AT yuanhangzhou largescalecorticalnetworkanalysisandclassificationofmibcitasksbasedonbayesiannonnegativematrixfactorization AT yunhongliu largescalecorticalnetworkanalysisandclassificationofmibcitasksbasedonbayesiannonnegativematrixfactorization AT chanlinyi largescalecorticalnetworkanalysisandclassificationofmibcitasksbasedonbayesiannonnegativematrixfactorization AT falili largescalecorticalnetworkanalysisandclassificationofmibcitasksbasedonbayesiannonnegativematrixfactorization AT dezhongyao largescalecorticalnetworkanalysisandclassificationofmibcitasksbasedonbayesiannonnegativematrixfactorization AT pengxu largescalecorticalnetworkanalysisandclassificationofmibcitasksbasedonbayesiannonnegativematrixfactorization AT xsanliang largescalecorticalnetworkanalysisandclassificationofmibcitasksbasedonbayesiannonnegativematrixfactorization AT taozhang largescalecorticalnetworkanalysisandclassificationofmibcitasksbasedonbayesiannonnegativematrixfactorization |