Manifold-regression to predict from MEG/EEG brain signals without source modeling

06/04/2019
by   David Sabbagh, et al.
2

Magnetoencephalography and electroencephalography (M/EEG) can reveal neuronal dynamics non-invasively in real-time and are therefore appreciated methods in medicine and neuroscience. Recent advances in modeling brain-behavior relationships have highlighted the effectiveness of Riemannian geometry for summarizing the spatially correlated time-series from M/EEG in terms of their covariance. However, after artefact-suppression, M/EEG data is often rank deficient which limits the application of Riemannian concepts. In this article, we focus on the task of regression with rank-reduced covariance matrices. We study two Riemannian approaches that vectorize the M/EEG covariance between-sensors through projection into a tangent space. The Wasserstein distance readily applies to rank-reduced data but lacks affine-invariance. This can be overcome by finding a common subspace in which the covariance matrices are full rank, enabling the affine-invariant geometric distance. We investigated the implications of these two approaches in synthetic generative models, which allowed us to control estimation bias of a linear model for prediction. We show that Wasserstein and geometric distances allow perfect out-of-sample prediction on the generative models. We then evaluated the methods on real data with regard to their effectiveness in predicting age from M/EEG covariance matrices. The findings suggest that the data-driven Riemannian methods outperform different sensor-space estimators and that they get close to the performance of biophysics-driven source-localization model that requires MRI acquisitions and tedious data processing. Our study suggests that the proposed Riemannian methods can serve as fundamental building-blocks for automated large-scale analysis of M/EEG.

READ FULL TEXT
research
03/10/2023

Sliced-Wasserstein on Symmetric Positive Definite Matrices for M/EEG Signals

When dealing with electro or magnetoencephalography records, many superv...
research
01/14/2015

Using Riemannian geometry for SSVEP-based Brain Computer Interface

Riemannian geometry has been applied to Brain Computer Interface (BCI) f...
research
02/24/2023

Barycenter Estimation of Positive Semi-Definite Matrices with Bures-Wasserstein Distance

Brain-computer interface (BCI) builds a bridge between human brain and e...
research
02/09/2021

Clinical BCI Challenge-WCCI2020: RIGOLETTO – RIemannian GeOmetry LEarning, applicaTion To cOnnectivity

This short technical report describes the approach submitted to the Clin...
research
12/01/2017

Subject Selection on a Riemannian Manifold for Unsupervised Cross-subject Seizure Detection

Inter-subject variability between individuals poses a challenge in inter...
research
08/09/2022

Partial Least Square Regression via Three-factor SVD-type Manifold Optimization for EEG Decoding

Partial least square regression (PLSR) is a widely-used statistical mode...
research
08/26/2022

Solving large-scale MEG/EEG source localization and functional connectivity problems simultaneously using state-space models

State-space models are used in many fields when dynamics are unobserved....

Please sign up or login with your details

Forgot password? Click here to reset