Convolutional Monge Mapping between EEG Datasets to Support Independent Component Labeling

EEG recordings contain rich information about neural activity and are used in the diagnosis and monitoring of multiple neuropathologies, including epilepsy and psychosis, but are subject to artifacts and noise. While EEG analysis can benefit from automating artifact removal through independent component analysis and automatic labeling of independent components (ICs), differences in recording equipment and context (the presence of noise from electrical wiring and other devices) may impact the performance of IC classifiers. Here we investigate how these differences can be minimized by appropriate spectral normalization through filtering using Convolutional Monge Mapping Normalization (CMMN), which was previously shown to improve deep neural network approaches for sleep staging. We propose a novel extension of the CMMN method with two alternative approaches to computing the source reference spectrum the target signals are mapped to: (1) channel-averaged and l 1 -normalized barycenter, and (2) a subject-to-subject mapping that finds the source subject with the closest spectrum to the target subject. Notably, our extension yields space-time separable filters that can be used to map between datasets with different numbers of EEG channels. We apply these filters in an IC classification task, and show significant improvement in recognizing brain versus non-brain ICs.