On the interpretation of linear Riemannian tangent space model parameters in M/EEG

TL;DR

This paper introduces a method to interpret parameters of linear Riemannian tangent space models in MEG/EEG, enhancing their transparency and understanding of underlying neural sources.

Contribution

The authors propose a transformation technique that makes tangent space model parameters interpretable as true source patterns, validated through simulations and real data.

Findings

The method accurately identifies true source patterns under typical assumptions.

Riemannian tangent space methods are robust to variations in source patterns.

The interpretability of model parameters improves understanding of neural signals.

Abstract

Riemannian tangent space methods offer state-of-the-art performance in magnetoencephalography (MEG) and electroencephalography (EEG) based applications such as brain-computer interfaces and biomarker development. One limitation, particularly relevant for biomarker development, is limited model interpretability compared to established component-based methods. Here, we propose a method to transform the parameters of linear tangent space models into interpretable patterns. Using typical assumptions, we show that this approach identifies the true patterns of latent sources, encoding a target signal. In simulations and two real MEG and EEG datasets, we demonstrate the validity of the proposed approach and investigate its behavior when the model assumptions are violated. Our results confirm that Riemannian tangent space methods are robust to differences in the source patterns across observations. We found that this robustness property also transfers to the associated patterns.