Reduction of EEG artifacts by ICA in different sleep stages

Contamination of sleep EEG signals by the eye, muscle and heart activity is a problem for EEG interpretation and analysis of sleep disorders and influence of drugs. The aim of this paper is to evaluate a method of artifact reduction applied in different sleep stages: awakeness, stage 2, delta and REM sleep. Artifacts, particularly certain types, may be more likely found in particular settings and stages of sleep. To overcome the limitation of regression methods in bidirectional contamination, a method based on Independent Component Analysis (ICA) using time structure is applied. Artifact identification is based on time, frequency and scalp topography aspects of the independent components. Influence of artifacts is evaluated by calculating some target spectral variables before and after their reduction, using significance probability maps. Results show that ICA is a useful technique for the evaluation of these variables with clinical interest in different sleep stages.