eCite Digital Repository

A long short-term memory network for sparse spatiotemporal EEG source imaging

Citation

Bore, JC and Li, P and Jiang, L and Ayedh, WMA and Chen, C and Harmah, DJ and Yao, D and Cao, Z and Xu, P, A long short-term memory network for sparse spatiotemporal EEG source imaging, IEEE Transactions on Medical Imaging ISSN 0278-0062 (In Press) [Refereed Article]


Preview
PDF (Accepted version)
1Mb
  

Copyright Statement

Copyright 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

Official URL: https://ieeexplore.ieee.org/document/9488247

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.

Item Details

Item Type:Refereed Article
Keywords:cortical neural networks, Long Short-Term MeCao, Z, source localization
Research Division:Information and Computing Sciences
Research Group:Artificial intelligence
Research Field:Planning and decision making
Objective Division:Information and Communication Services
Objective Group:Information systems, technologies and services
Objective Field:Artificial intelligence
UTAS Author:Cao, Z (Dr Zehong Cao)
ID Code:144665
Year Published:In Press
Deposited By:Information and Communication Technology
Deposited On:2021-06-03
Last Modified:2021-09-28
Downloads:0

Repository Staff Only: item control page