{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T06:07:06Z","timestamp":1789020426794,"version":"build-2803163510"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T00:00:00Z","timestamp":1788998400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurosci."],"abstract":"<jats:p>Motor imagery electroencephalography (MI-EEG) decoding remains challenging because of the low signal-to-noise ratio, non-stationarity, and inter-subject variability of EEG signals. This study proposes a dynamic multi-branch EEG decoding network (DMB-EDN) that jointly models temporal dynamics, learnable time-frequency patterns, and rhythm-specific spectral information. DMB-EDN combines a learnable Gabor-based time-frequency representation with physiologically guided rhythm modeling and employs trial-conditioned dynamic fusion to estimate the contribution of each branch separately for each EEG trial. This design enables adaptive coordination of complementary data-driven and physiology-guided representations. The proposed method was evaluated on the BCI Competition IV 2a dataset, the High Gamma Dataset, and a self-collected spinal cord injury (SCI) dataset. Under subject-specific evaluation, DMB-EDN achieved an average accuracy of 96.41% and a kappa of 0.952 on BCI Competition IV 2a. On the High Gamma Dataset, it achieved performance comparable to the strongest baseline under near-saturated conditions. Under leave-one-subject-out evaluation on the SCI dataset, DMB-EDN obtained an accuracy of 85.00% and a kappa of 0.700, providing preliminary evidence of improved offline cross-subject decoding. Ablation experiments confirmed the complementary contributions of the three representation branches and trial-conditioned fusion, while fusion-weight analysis revealed systematic class- and oscillation-related variations. These results demonstrate the effectiveness of DMB-EDN for EEG decoding, although validation on larger multicenter cohorts and prospective online BCI systems remains necessary.<\/jats:p>","DOI":"10.3389\/fnins.2026.1918072","type":"journal-article","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T05:31:20Z","timestamp":1789018280000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A dynamic multi-branch EEG decoding network for motor imagery classification with preliminary clinical validation"],"prefix":"10.3389","volume":"20","author":[{"given":"Jingxin","family":"Cai","sequence":"first","affiliation":[{"name":"School of Medical Information Engineering, Shandong University of Traditional Chinese Medicine","place":["Jinan, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyao","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Medical Information Engineering, Shandong University of Traditional Chinese Medicine","place":["Jinan, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangyu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Medical Information Engineering, Shandong University of Traditional Chinese Medicine","place":["Jinan, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaomeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Medical Information Engineering, Shandong University of Traditional Chinese Medicine","place":["Jinan, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenglin","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Medical Information Engineering, Shandong University of Traditional Chinese Medicine","place":["Jinan, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Chen","sequence":"additional","affiliation":[{"name":"Affiliated Hospital of Shandong University of Traditional Chinese Medicine","place":["Jinan, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangzhou","family":"Xu","sequence":"additional","affiliation":[{"name":"International School for Optoelectronic Engineering, Qilu University of Technology (Shandong Academy of Sciences)","place":["Jinan, Shandong, China"]},{"name":"Jinan Engineering Laboratory of Human-Machine Intelligent Cooperation","place":["Jinan, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fulei","family":"Hu","sequence":"additional","affiliation":[{"name":"Rehabilitation and Physical Therapy Department, Affiliated Hospital of Shandong University of Traditional Chinese Medicine","place":["Jinan, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"2249","DOI":"10.1109\/TII.2022.3197419","article-title":"Physics-informed attention temporal convolutional network for EEG-based motor imagery classification","volume":"19","author":"Altaheri","year":"2023","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"995","DOI":"10.3390\/diagnostics12040995","article-title":"A multi-branch convolutional neural network with squeeze-and-excitation attention blocks for EEG-based motor imagery signals classification","volume":"12","author":"Altuwaijri","year":"2022","journal-title":"Diagnostics"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"39","DOI":"10.3389\/fnins.2012.00039","article-title":"Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b","volume":"6","author":"Ang","year":"2012","journal-title":"Front. Neurosci."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1109\/TNSRE.2016.2646763","article-title":"EEG-based strategies to detect motor imagery for control and rehabilitation","volume":"25","author":"Ang","year":"2017","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/MSP.2008.4408441","article-title":"Optimizing spatial filters for robust EEG single-trial analysis","volume":"25","author":"Blankertz","year":"2008","journal-title":"IEEE Signal Process. Mag."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"106156","DOI":"10.1016\/j.bspc.2024.106156","article-title":"Multi-branch spatial-temporal-spectral convolutional neural networks for multi-task motor imagery EEG classification","volume":"93","author":"Cai","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/10589759.2025.2584623","article-title":"Direction-aware attention for detail-preserving terahertz image super-resolution","author":"Chen","year":"2025","journal-title":"Nondestruct. Test. Eval."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"111129","DOI":"10.1016\/j.asoc.2023.111129","article-title":"A multiscale feature fusion network based on attention mechanism for motor imagery EEG decoding","volume":"151","author":"Gao","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"ref9","author":"Hu","year":"2018"},{"key":"ref10","author":"Ingolfsson","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"108419","DOI":"10.1016\/j.bspc.2025.108419","article-title":"A composite classification algorithm of motor imagery EEG signals based on the PLV-GCN+LSTM model","volume":"112","author":"Kang","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"056013","DOI":"10.1088\/1741-2552\/aace8c","article-title":"EEGNet: a compact convolutional neural network for EEG-based brain\u2013computer interfaces","volume":"15","author":"Lawhern","year":"2018","journal-title":"J. Neural Eng."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"108648","DOI":"10.1016\/j.bspc.2025.108648","article-title":"BioMIFormer: biologically inspired spatiotemporal transformer for motor imagery EEG interpretation","volume":"112","author":"Liu","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"7126","DOI":"10.1109\/JBHI.2024.3450753","article-title":"MSVTNet: multi-scale vision transformer neural network for EEG-based motor imagery decoding","volume":"28","author":"Liu","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref15","author":"Mane","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"108692","DOI":"10.1016\/j.bspc.2025.108692","article-title":"TFCA-TransNet: convolutional time\u2013frequency\u2013spatial feature fusion with channel attention transformer network for EEG-MI signal decoding","volume":"112","author":"Miao","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"120209","DOI":"10.1016\/j.neuroimage.2023.120209","article-title":"LMDA-net: a lightweight multi-dimensional attention network for general EEG-based brain\u2013computer interfaces and interpretability","volume":"276","author":"Miao","year":"2023","journal-title":"NeuroImage"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"102826","DOI":"10.1016\/j.bspc.2021.102826","article-title":"Electroencephalography-based motor imagery classification using temporal convolutional network fusion","volume":"69","author":"Musallam","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1038\/s41393-019-0390-1","article-title":"Motor imagery for pain and motor function after spinal cord injury: a systematic review","volume":"58","author":"Opsommer","year":"2020","journal-title":"Spinal Cord"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1423","DOI":"10.3390\/s19061423","article-title":"EEG-based brain\u2013computer interfaces using motor imagery: techniques and challenges","volume":"19","author":"Padfield","year":"2019","journal-title":"Sensors"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"101182","DOI":"10.1016\/j.patter.2025.101182","article-title":"GREEN: a lightweight architecture using learnable wavelets and Riemannian geometry for biomarker exploration with EEG signals","volume":"6","author":"Paillard","year":"2025","journal-title":"Patterns"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"108879","DOI":"10.1016\/j.bspc.2025.108879","article-title":"An EEG signal encryption algorithm based on a dual-composite IT-ICMIC chaotic map and adaptive non-uniform partition","volume":"113","author":"Peng","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1842","DOI":"10.1016\/S1388-2457(99)00141-8","article-title":"Event-related EEG\/MEG synchronization and desynchronization: basic principles","volume":"110","author":"Pfurtscheller","year":"1999","journal-title":"Clin. Neurophysiol."},{"key":"ref24","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1109\/86.895946","article-title":"Optimal spatial filtering of single-trial EEG during imagined hand movement","volume":"8","author":"Ramoser","year":"2000","journal-title":"IEEE Trans. Rehabil. Eng."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"87","DOI":"10.3389\/fncom.2019.00087","article-title":"Intra- and inter-subject variability in EEG-based sensorimotor brain\u2013computer interface: a review","volume":"13","author":"Saha","year":"2020","journal-title":"Front. Comput. Neurosci."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"5391","DOI":"10.1002\/hbm.23730","article-title":"Deep learning with convolutional neural networks for EEG decoding and visualization","volume":"38","author":"Schirrmeister","year":"2017","journal-title":"Hum. Brain Mapp."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1109\/TNSRE.2022.3230250","article-title":"EEG conformer: convolutional transformer for EEG decoding and visualization","volume":"31","author":"Song","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"55","DOI":"10.3389\/fnins.2012.00055","article-title":"Review of the BCI competition IV","volume":"6","author":"Tangermann","year":"2012","journal-title":"Front. Neurosci."},{"key":"ref29","first-page":"5998","volume-title":"Attention is all you need Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"102738","DOI":"10.1016\/j.artmed.2023.102738","article-title":"An in-depth survey on deep learning-based motor imagery electroencephalogram classification","volume":"147","author":"Wang","year":"2024","journal-title":"Artif. Intell. Med."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1016\/S1388-2457(02)00057-3","article-title":"Brain\u2013computer interfaces for communication and control","volume":"113","author":"Wolpaw","year":"2002","journal-title":"Clin. Neurophysiol."},{"key":"ref32","author":"Woo","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"6319","DOI":"10.1109\/TITS.2026.3680498","article-title":"Graph-MDETR: a graph-guided mamba-DETR network for UAV catenary support component detection in electrified railways","volume":"27","author":"Yang","year":"2026","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"046014","DOI":"10.1088\/1741-2552\/abed81","article-title":"EEG-inception: an accurate and robust end-to-end neural network for EEG-based motor imagery classification","volume":"18","author":"Zhang","year":"2021","journal-title":"J. Neural Eng."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"108381","DOI":"10.1016\/j.bspc.2025.108381","article-title":"MBBi-TCNet: multi-branch bidirectional temporal convolutional network for EEG classification of mental imagery","volume":"111","author":"Zhang","year":"2026","journal-title":"Biomed. Signal Process. Control"}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1918072\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T05:31:21Z","timestamp":1789018281000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1918072\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,10]]},"references-count":35,"alternative-id":["10.3389\/fnins.2026.1918072"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2026.1918072","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,10]]},"article-number":"1918072"}}