A Long Short-Term Memory Network for Sparse Spatiotemporal EEG Source Imaging

Abstract

EEG inverse problem is generally underdetermined, which poses a long standing challenge in Neuroimaging. The combination of source-imaging and analysis of the cortical directional networks enables us to noninvasively explore the underlying neural processes. However, existing EEG source imaging approaches mainly focus on performing the direct inverse operation for source estimation, which will be inevitably influenced by noise and the strategy used to find the inverse solution as well. In current work, we develop a new source imaging technique, Deep Brain Neural Network (DeepBraiNNet) for robust sparse spatiotemporal EEG source estimation. In DeepBraiNNet, considering that Recurrent Neural Network (RNN) are usually "deep" in temporal dimension and thus suitable for time sequence modelling, the RNN with Long Short-Term Memory (LSTM) is utilized to approximate the inverse operation for the lead field matrix instead of performing the direct inverse operation, which avoids the possible effect of the direct inverse operation on the underdetermined lead field matrix prone to be influenced by the noise. The simulations on various source patterns and noise conditions confirmed that the proposed approach could actually recover the spatiotemporal sources well, outperforming the existing state of-the-art methods. Furthermore, DeepBraiNNet also estimated sparse MI related activation patterns when it was applied to a real Motor Imagery dataset, consistent with other findings based on both EEG and fMRI. Moreover, based on the spatiotemporal sources estimated from DeepBraiNNet, we further constructed the MI related cortical neural networks, which clearly exhibited the strong contralateral network patterns for the two MI tasks. Consequently, DeepBraiNNet may provide an alternative way different from the conventional approaches for spatiotemporal EEG source imaging.

A Graph Fourier Transform Based Bidirectional Long Short-Term Memory Neural Network for Electrophysiological Source Imaging

“…To solve the ESI problem, deep learning frameworks have also been proposed in the past years, but with only a few existing works available. For example, Bore et al (2021) introduced an RNN with LSTM units for spatiotemporal EEG source imaging and the proposed approach achieved good performance against the benchmark algorithms. Hecker et al (2021) constructed a novel CNN-based structure, named ConvDip, to detect multiple sources, and this architecture is shown to outperform state-of-the-art methods.…”

Spatiotemporal Rhythmic Seizure Sources Can be Imaged by means of Biophysically Constrained Deep Neural Networks

“…These methods are capable of implicitly learn the source distributions through data instead of explicitly formulating the regularization terms to constrain the solution space, which means more complex source models can be incorporated into the solution to achieve a more accurate and robust source estimate. There have been several recent attempts to image brain activities using deep neural networks [26][27][28][29][30][31]. They have shown excellent performance in computer simulations, demonstrating the power of DL-based ESI methods.…”

Personalized Deep Learning based Source Imaging Framework Improves the Imaging of Epileptic Sources from MEG Interictal Spikes

“…Deep learning methods have the advantage of implicitly learning the source distributions instead of explicitly formulating the regularization terms, providing opportunities for a more accurate and robust ESI estimate. There have been several attempts recently to image brain activities using deep neural networks [55][56][57][58][59][60]. They have shown excellent performance in computer simulations, demonstrating the power of DL-based ESI methods.…”