MTGNet: A task-oriented and spectrally guided framework for EEG denoising.

Electroencephalography (EEG) is widely used in brain-computer interfaces (BCIs), but its microvolt-level signals are easily contaminated by electromyography (EMG), electrooculography (EOG), and mixed physiological artifacts. This study develops an EEG denoising framework that suppresses artifacts while preserving information used by downstream biomedical artificial intelligence (AI) tasks. Approach. We propose MTGNet, a task-oriented and spectrally guided EEG denoising framework. MTGNet combines Low-Rank Adaptation (LoRA)-based Task-Aware Consistency Regularization (TACR), a spectrally aware Guidance Network, and parallel Mamba-Transformer backbone. A pretrained 11.97M-parameter backbone learns to preserve intrinsic EEG characteristics from paired noisy-clean data, while 0.33M LoRA parameters enable task-specific adaptation without requiring paired clean EEG references. Main results. On EEGDenoiseNet, MTGNet reduces spectral relative root-mean-square error (S-RRMSE) by over 18.9%, 31.5%, and 14.0% for EMG, EOG, and hybrid artifacts, respectively (p<0.001). On a real-world fatigue EEG dataset, it improves classification accuracy by 6.20-6.69 percentage points compared with unprocessed inputs (p<0.05). Ablation, cross-classifier, and cross-dataset analyses validate the proposed components and support the transferability of MTGNet across the evaluated settings. Significance. The proposed framework provides a practical approach to task-aware EEG denoising, while future work should further validate its applicability across real-world EEG settings involving diverse tasks, artifact types, and acquisition conditions.