Key result
DHCT-GAN significantly outperformed recent state-of-the-art networks in removing various EEG artifacts by independently learning and fusing features from clean and artifact signals.
Why the study?
EEG signals are often influenced by physiological artifacts, and existing deep learning denoising methods have not adequately explored integrating cross-disciplinary knowledge such as insights from artifact research.
DHCT-GAN provides an improved deep learning-based method for EEG signal denoising by integrating features from both clean and artifact signals.
Electroencephalogram (EEG) signals are important bioelectrical signals widely used in brain activity studies, cognitive mechanism research, and the diagnosis and treatment of neurological disorders. However, EEG signals are often influenced by various physiological artifacts, which can significantly affect data analysis and diagnosis. Recently, deep learning-based EEG denoising methods have exhibited unique advantages over traditional methods. Most existing methods mainly focus on identifying the characteristics of clean EEG signals to facilitate artifact removal; however, the potential to integrate cross-disciplinary knowledge, such as insights from artifact research, remains an area that requires further exploration. In this study, we developed DHCT-GAN, a new EEG denoising model, using a dual-branch hybrid network architecture. This model independently learns features from both clean EEG signals and artifact signals, then fuses this information through an adaptive gating network to generate denoised EEG signals that accurately preserve EEG signal features while effectively removing artifacts. We evaluated DHCT-GAN's performance through waveform analysis, power spectral density (PSD) analysis, and six performance metrics. The results demonstrate that DHCT-GAN significantly outperforms recent state-of-the-art networks in removing various artifacts. Furthermore, ablation experiments revealed that the hybrid model surpasses single-branch models in artifact removal, underscoring the crucial role of artifact knowledge constraints in improving denoising effectiveness.
No takes yet. Share an insight, caveat, or question.
Zhao et al. (2025) studied EEG signal artifacts. DHCT-GAN (dual-branch hybrid CNN-Transformer network) vs. Recent state-of-the-art networks and single-branch models was evaluated on Denoising effectiveness (waveform analysis, PSD analysis, and six performance metrics). DHCT-GAN significantly outperformed recent state-of-the-art networks in removing various EEG artifacts by independently learning and fusing features from clean and artifact signals.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: