A Segmentation-Denoising Network for Artifact Removal From Single-Channel EEG

As an important neurorecording technique, electroencephalography (EEG) is often contaminated by various artifacts, which obstructs subsequent analysis. In recent years, deep learning-based (DL-based) methods have been proven to be promising for artifact removal. However, most denoising methods focus on recovering clean EEG from raw signals contaminated by the noise over the entire recording period, ignoring that the practical EEG recordings may contain clean segments in addition to noise segments. Therefore, the general model may cause distortion when dealing with clean segments. In this article, we propose a simple, yet effective segmentation-denoising network (SDNet) for artifact removal. The proposed method is capable of differentiating noisy EEG segments from clean ones via semantic segmentation, avoiding the distortion caused by processing clean segments. We conduct a performance comparison on semisimulated and real EEG data. The experimental results demonstrate that SDNet outperforms the state-of-art approaches. This work provides a novel way to reconstruct artifact-attenuated EEG signals, and may further benefit the EEG-based diagnosis and treatment.

Automated summary

In this article, a simple yet effective segmentation-denoising network (SDNet) is proposed for artifact removal in electroencephalography (EEG). It can differentiate noisy EEG segments from clean ones via semantic segmentation, avoiding distortion caused by processing clean segments. Experimental results demonstrate that SDNet outperforms state-of-the-art approaches, providing a novel way to reconstruct artifact-attenuated EEG signals and potentially benefiting EEG-based diagnosis and treatment.