Canonical Correlation Analysis Applied to Remove Muscle Artifacts From the Electroencephalogram

TLDR

EEG recordings are frequently contaminated by muscle artifacts. The study introduces a canonical correlation analysis (CCA)–based blind source separation method to remove muscle artifacts from EEG. The CCA method was validated on synthetic data and applied to real ictal EEG recordings contaminated with muscle activity. The CCA approach outperformed low‑pass filtering and ICA‑based removal, successfully eliminating muscle artifacts while preserving underlying ictal activity.

Abstract

The electroencephalogram (EEG) is often contaminated by muscle artifacts. In this paper, a new method for muscle artifact removal in EEG is presented, based on canonical correlation analysis (CCA) as a blind source separation (BSS) technique. This method is demonstrated on a synthetic data set. The method outperformed a low-pass filter with different cutoff frequencies and an independent component analysis (ICA)-based technique for muscle artifact removal. In addition, the method is applied on a real ictal EEG recording contaminated with muscle artifacts. The proposed method removed successfully the muscle artifact without altering the recorded underlying ictal activity