Edge Sparse Basis Network: A Deep Learning Framework for EEG Source Localization

TL;DR

This paper introduces the Edge Sparse Basis Network (ESBN), a deep learning framework that improves EEG source localization by combining spatial basis functions with edge sparsity priors, validated on synthetic and real data.

Contribution

The paper proposes a novel deep learning framework, ESBN, integrating edge sparsity and Gaussian basis functions for more accurate EEG source localization.

Findings

ESBN outperforms traditional methods on synthetic data

Unsupervised fine-tuning yields more focal localizations on real data

Framework is suitable for real-time EEG applications

Abstract

EEG source localization is an important technical issue in EEG analysis. Despite many numerical methods existed for EEG source localization, they all rely on strong priors and the deep sources are intractable. Here we propose a deep learning framework using spatial basis function decomposition for EEG source localization. This framework combines the edge sparsity prior and Gaussian source basis, called Edge Sparse Basis Network (ESBN). The performance of ESBN is validated by both synthetic data and real EEG data during motor tasks. The results suggest that the supervised ESBN outperforms the traditional numerical methods in synthetic data and the unsupervised fine-tuning provides more focal and accurate localizations in real data. Our proposed deep learning framework can be extended to account for other source priors, and the real-time property of ESBN can facilitate the applications of EEG in brain-computer interfaces and clinics.