PA-TCNet: Pathology-Aware Temporal Calibration with Physiology-Guided Target Refinement for Cross-Subject Motor Imagery EEG Decoding in Stroke Patients

2026-04-17

AI Summary

This work addresses the challenges of cross-subject decoding of motor imagery electroencephalography (MI-EEG) in stroke patients, where lesion-induced abnormal temporal dynamics and high inter-subject heterogeneity hinder model generalization. To tackle these issues, the authors propose the PA-TCNet framework, which innovatively integrates pathology-aware rhythmic state modeling with physiology-guided target calibration. Specifically, the Pathology-aware Rhythmic State Mamba (PRSM) module disentangles spatiotemporal features to separate stable rhythmic patterns from transient perturbations, while the Physiology-Guided Target Calibration (PGTC) module dynamically refines pseudo-labels using a sensorimotor template. Evaluated on the XW-Stroke and 2019-Stroke datasets, the method achieves average accuracies of 66.56% and 72.75%, respectively, significantly outperforming existing approaches and substantially enhancing the robustness and transferability of cross-subject MI-BCI systems.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Intelligent Robots: State Estimation
• Machine Learning: Neuro-Symbolic Learning

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Stroke patient cross-subject electroencephalography (EEG) decoding of motor imagery (MI) brain-computer interface (BCI) is essential for motor rehabilitation, yet lesion-related abnormal temporal dynamics and pronounced inter-patient heterogeneity often undermine generalization. Existing adaptation methods are easily misled by pathological slow-wave activity and unstable target-domain pseudo-labels. To address this challenge, we propose PA-TCNet, a pathology-aware temporal calibration framework with physiology-guided target refinement for stroke motor imagery decoding. PA-TCNet integrates two coordinated components. The Pathology-aware Rhythmic State Mamba (PRSM) module decomposes EEG spatiotemporal features into slowly varying rhythmic context and fast transient perturbations, injecting the fused pathological context into selective state propagation to more effectively capture abnormal temporal dynamics. The Physiology-Guided Target Calibration (PGTC) module constructs source-domain sensorimotor region-of-interest templates, imposing physiological consistency constraints and dynamically refining target-domain pseudo-labels, thereby improving adaptation reliability. Leave-one-subject-out experiments on two independent stroke EEG datasets, XW-Stroke and 2019-Stroke, yielded mean accuracies of 66.56\% and 72.75\%, respectively, outperforming state-of-the-art baselines. These results indicate that jointly modeling pathological temporal dynamics and physiology-constrained pseudo-supervision can provide more robust cross-subject initialization for personalized post-stroke MI-BCI rehabilitation. The implemented code is available at https://github.com/wxk1224/PA-TCNet.

Problem

• cross-subject EEG decoding
• motor imagery
• stroke rehabilitation
• temporal dynamics
• inter-patient heterogeneity

Innovation

• Pathology-aware
• Temporal calibration
• Physiology-guided
• Cross-subject EEG decoding
• Motor imagery BCI