I see artifacts: ICA-based EEG artifact removal does not improve deep network decoding across three BCI tasks

TL;DR

This study evaluates whether ICA-based EEG artifact removal improves deep learning decoding across three BCI tasks, finding minimal benefits relative to computational costs.

Contribution

It systematically compares different ICA decomposition and artifact rejection strategies across multiple EEG datasets and neural network architectures.

Findings

ICA-based noise rejection offers minimal decoding performance improvement.

Component rejection does not consistently outperform no rejection.

ICA computations require significant computational resources.

Abstract

In this paper, we conduct a detailed investigation on the effect of independent component (IC)-based noise rejection methods in neural network classifier-based decoding of electroencephalography (EEG) data in different task datasets. We apply a pipeline matrix of two popular different independent component (IC) decomposition methods (Infomax and Adaptive Mixture Independent Component Analysis (AMICA)) with three different component rejection strategies (none, ICLabel, and multiple artifact rejection algorithm [MARA]) on three different EEG datasets (motor imagery, long-term memory formation, and visual memory). We cross-validate processed data from each pipeline with three architectures commonly used for EEG classification (two convolutional neural networks and one long short-term memory-based model. We compare decoding performances on within-participant and within-dataset levels.Our results show that the benefit from using IC-based noise rejection for decoding analyses is at best minor, as component-rejected data did not show consistently better performance than data without rejections; especially given the significant computational resources required for independent component analysis (ICA) computations.