TY - JOUR
T1 - A Graph Fourier Transform Based Bidirectional Long Short-Term Memory Neural Network for Electrophysiological Source Imaging
AU - Jiao, Meng
AU - Wan, Guihong
AU - Guo, Yaxin
AU - Wang, Dongqing
AU - Liu, Hang
AU - Xiang, Jing
AU - Liu, Feng
N1 - Publisher Copyright:
Copyright © 2022 Jiao, Wan, Guo, Wang, Liu, Xiang and Liu.
PY - 2022/4/13
Y1 - 2022/4/13
N2 - Electrophysiological source imaging (ESI) refers to the process of reconstructing underlying activated sources on the cortex given the brain signal measured by Electroencephalography (EEG) or Magnetoencephalography (MEG). Due to the ill-posed nature of ESI, solving ESI requires the design of neurophysiologically plausible regularization or priors to guarantee a unique solution. Recovering focally extended sources is more challenging, and traditionally uses a total variation regularization to promote spatial continuity of the activated sources. In this paper, we propose to use graph Fourier transform (GFT) based bidirectional long-short term memory (BiLSTM) neural network to solve the ESI problem. The GFT delineates the 3D source space into spatially high, medium and low frequency subspaces spanned by corresponding eigenvectors. The low frequency components can naturally serve as a spatially low-band pass filter to reconstruct extended areas of source activation. The BiLSTM is adopted to learn the mapping relationship between the projection of low-frequency graph space and the recorded EEG. Numerical results show the proposed GFT-BiLSTM outperforms other benchmark algorithms in synthetic data under varied signal-to-noise ratios (SNRs). Real data experiments also demonstrate its capability of localizing the epileptogenic zone of epilepsy patients with good accuracy.
AB - Electrophysiological source imaging (ESI) refers to the process of reconstructing underlying activated sources on the cortex given the brain signal measured by Electroencephalography (EEG) or Magnetoencephalography (MEG). Due to the ill-posed nature of ESI, solving ESI requires the design of neurophysiologically plausible regularization or priors to guarantee a unique solution. Recovering focally extended sources is more challenging, and traditionally uses a total variation regularization to promote spatial continuity of the activated sources. In this paper, we propose to use graph Fourier transform (GFT) based bidirectional long-short term memory (BiLSTM) neural network to solve the ESI problem. The GFT delineates the 3D source space into spatially high, medium and low frequency subspaces spanned by corresponding eigenvectors. The low frequency components can naturally serve as a spatially low-band pass filter to reconstruct extended areas of source activation. The BiLSTM is adopted to learn the mapping relationship between the projection of low-frequency graph space and the recorded EEG. Numerical results show the proposed GFT-BiLSTM outperforms other benchmark algorithms in synthetic data under varied signal-to-noise ratios (SNRs). Real data experiments also demonstrate its capability of localizing the epileptogenic zone of epilepsy patients with good accuracy.
KW - BiLSTM
KW - electroencephalography
KW - graph Fourier transform
KW - inverse problem
KW - source localization
UR - http://www.scopus.com/inward/record.url?scp=85128961018&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85128961018&partnerID=8YFLogxK
U2 - 10.3389/fnins.2022.867466
DO - 10.3389/fnins.2022.867466
M3 - Article
AN - SCOPUS:85128961018
SN - 1662-4548
VL - 16
JO - Frontiers in Neuroscience
JF - Frontiers in Neuroscience
M1 - 867466
ER -