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

TL;DR

PA-TCNet introduces a novel pathology-aware framework for stroke EEG decoding, effectively capturing abnormal temporal dynamics and refining pseudo-labels to enhance cross-subject motor imagery classification.

Contribution

It proposes a new integrated approach combining pathology-aware rhythmic analysis and physiology-guided pseudo-label refinement for improved stroke EEG decoding.

Findings

Achieved mean accuracies of 66.56% and 72.75% on two datasets, surpassing existing methods.

Effectively models abnormal temporal dynamics and physiological constraints for better adaptation.

Code is publicly available at https://github.com/wxk1224/PA-TCNet.

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.