CFSPMNet: Cross-subject Fourier-guided Spatial-Patch Mamba Network for EEG Motor Imagery Decoding in Stroke Patients
2026-05-11 • Machine Learning
Machine LearningArtificial IntelligenceComputer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new method called CFSPMNet to help computers interpret brain signals from stroke patients doing motor imagery tasks, even when the computer hasn’t seen those patients before. They designed the system to understand hidden brain state patterns by reorganizing data in the Fourier domain and carefully selecting reliable signals from new patients. Testing showed their method works better than existing approaches on two stroke EEG datasets. Their work suggests that modeling latent neural states can improve brain-computer interfaces used for stroke rehabilitation.
Motor imagery EEG (MI-EEG)Cross-patient adaptationFourier domainLatent neural statesBrain-computer interface (BCI)Pseudo-labelingState-space propagationStroke rehabilitationElectroencephalography (EEG)Neural signal decoding
Authors
Xiangkai Wang, Yun Zhao, Dongyi He, Qingling Xia, Gen Li, Xinlai Xing, Yuchi Pan, Bin Jiang
Abstract
Motor imagery electroencephalography (MI-EEG) decoding offers a non-invasive route for post-stroke rehabilitation, but cross-patient use remains difficult because pathological neural reorganization changes task-related EEG dynamics, aperiodic activity, local excitability, cross-regional coordination, and trial-level brain-state context. This makes source-learned MI representations unreliable for unseen patients. To address this problem, we propose CFSPMNet, a cross-patient adaptation framework that models post-stroke MI-EEG as latent neural-state organization. CFSPMNet combines a Fourier-Reorganized State Mamba Network (FRSM) with Shared-Private Prototype Matching (SPPM). FRSM represents each trial as a latent physiological token sequence, reorganizes token states in the Fourier domain, and uses Fourier-derived trial context to guide Mamba state-space propagation. SPPM improves target pseudo-label updating by combining semantic confidence with shared-private physiological consistency, filtering confident but physiologically inconsistent target predictions. Leave-one-subject-out experiments on two stroke MI-EEG datasets show that CFSPMNet outperforms representative CNN-, Transformer-, Mamba-, and adaptation-based baselines, achieving average accuracies of 68.23% on XW-Stroke and 73.33% on 2019-Stroke, with gains of 5.63 and 8.25 percentage points over the strongest competitors. Ablation, sensitivity, feature-alignment, pseudo-label selection, and neurophysiological visualization analyses further support the roles of Fourier-domain token-state reorganization and calibrated pseudo-label updating. These results suggest that latent neural-state modeling can improve rehabilitation-oriented cross-patient BCI decoding. Code is available at https://github.com/wxk1224/CFSPMNet.