EEG source localization using spatio-temporal neural network

Source localization of focal electrical activity from scalp electroencephalogram (sEEG) signal is generally modeled as an inverse problem that is highly ill-posed. In this paper, a novel source localization method is proposed to model the EEG inverse problem using spatio-temporal long-short term memory recurrent neural networks (LSTM). The network model consists of two parts, sEEG encoding and source decoding, to model the sEEG signal and receive the regression of source location. As there does not exist enough annotated sEEG signals correspond to specific source locations, simulated data is generated with forward model using finite element method (FEM) to act as a part of training signals. A framework for source localization is proposed to estimate the source position based on simulated training data. Experiments are done on simulated testing data. The results on simulated data exhibit good robustness on noise signal, and the proposed network solves the EEG inverse problem with spatio-temporal deep network. The result show that the proposed method overcomes the highly ill-posed linear inverse problem with data driven learning.

[1]  J.C. Mosher,et al.  Multiple dipole modeling and localization from spatio-temporal MEG data , 1992, IEEE Transactions on Biomedical Engineering.

[2]  G Van Hoey,et al.  EEG dipole source localization using artificial neural networks. , 2000, Physics in medicine and biology.

[3]  Barak A. Pearlmutter,et al.  Fast accurate MEG source localization using a multilayer perceptron trained with real brain noise. , 2002, Physics in medicine and biology.

[4]  Chun-Liang Li,et al.  One Network to Solve Them All — Solving Linear Inverse Problems Using Deep Projection Models , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[5]  Deirel Paz-Linares,et al.  Spatio Temporal EEG Source Imaging with the Hierarchical Bayesian Elastic Net and Elitist Lasso Models , 2017, Front. Neurosci..

[6]  Rolando J. Biscay-Lirio,et al.  Assessing interactions in the brain with exact low-resolution electromagnetic tomography , 2011, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[7]  Wei Wu,et al.  Bayesian electromagnetic spatio-temporal imaging of extended sources with Markov Random Field and temporal basis expansion , 2016, NeuroImage.

[8]  Diego Clonda,et al.  Bayesian spatio-temporal approach for EEG source reconstruction: conciliating ECD and distributed models , 2006, IEEE Transactions on Biomedical Engineering.

[9]  R D Pascual-Marqui,et al.  Standardized low-resolution brain electromagnetic tomography (sLORETA): technical details. , 2002, Methods and findings in experimental and clinical pharmacology.

[10]  G Castellanos-Dominguez,et al.  Reconstruction of Neural Activity from EEG Data Using Dynamic Spatiotemporal Constraints , 2016, Int. J. Neural Syst..

[11]  Robert Oostenveld,et al.  FieldTrip: Open Source Software for Advanced Analysis of MEG, EEG, and Invasive Electrophysiological Data , 2010, Comput. Intell. Neurosci..

[12]  Jonas Adler,et al.  Solving ill-posed inverse problems using iterative deep neural networks , 2017, ArXiv.

[13]  Toshimitsu Musha,et al.  Electric Dipole Tracing in the Brain by Means of the Boundary Element Method and Its Accuracy , 1987, IEEE Transactions on Biomedical Engineering.

[14]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[15]  R. Ilmoniemi,et al.  Interpreting magnetic fields of the brain: minimum norm estimates , 2006, Medical and Biological Engineering and Computing.

[16]  Sylvain Baillet,et al.  A Bayesian approach to introducing anatomo-functional priors in the EEG/MEG inverse problem , 1997, IEEE Transactions on Biomedical Engineering.

[17]  Lei Ding,et al.  Sparse source imaging in electroencephalography with accurate field modeling , 2008, Human brain mapping.

[18]  Wei Wu,et al.  STRAPS: A Fully Data-Driven Spatio-Temporally Regularized Algorithm for M/EEG Patch Source Imaging , 2015, Int. J. Neural Syst..

[19]  Bin He,et al.  Electrophysiological Source Imaging: A Noninvasive Window to Brain Dynamics. , 2018, Annual review of biomedical engineering.

[20]  D. Lehmann,et al.  Low resolution electromagnetic tomography: a new method for localizing electrical activity in the brain. , 1994, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[21]  Jan Geelen,et al.  Modelling motor cortex stimulation for chronic pain control: Electrical potential field, activating functions and responses of simple nerve fibre models , 2005, Medical and Biological Engineering and Computing.

[22]  Emery N. Brown,et al.  A spatiotemporal dynamic distributed solution to the MEG inverse problem , 2011, NeuroImage.

[23]  Barak A. Pearlmutter,et al.  Fast robust subject‐independent magnetoencephalographic source localization using an artificial neural network , 2005, Human brain mapping.

[24]  David P. Wipf,et al.  A unified Bayesian framework for MEG/EEG source imaging , 2009, NeuroImage.

[25]  R. W. Lau,et al.  The dielectric properties of biological tissues: II. Measurements in the frequency range 10 Hz to 20 GHz. , 1996, Physics in medicine and biology.

[26]  Jing Qin,et al.  Task-Related EEG Source Localization via Graph Regularized Low-Rank Representation Model , 2018, bioRxiv.

[27]  A. Dale,et al.  Improved Localizadon of Cortical Activity by Combining EEG and MEG with MRI Cortical Surface Reconstruction: A Linear Approach , 1993, Journal of Cognitive Neuroscience.