TY - GEN
T1 - EEG Source Imaging using GANs with Deep Image Prior
AU - Guo, Yaxin
AU - Jiao, Meng
AU - Wan, Guihong
AU - Xiang, Jing
AU - Wang, Shouyi
AU - Liu, Feng
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Brain source localization from electroencephalogram (EEG) signals is an challenging problem for noninvasively localizing the brain activity. Conventional methods use handcrafted regularization terms based on neural-physiological assumptions by exploiting the spatial-temporal structure on the source signals. In recent years, deep learning frameworks have demonstrated superior performance for solving the inverse problems in the natural and medical imaging field. This study proposes a novel unsupervised learning training-free framework based on Generative Adversarial Networks and deep image prior (GANs-DIP) as a generative model simulating spatially structured source signal. The proposed framework can faithfully recover extended source patches activation patterns of the brain in an unsupervised manner. Numerical experiments on a realistic brain model are performed under different levels of signal-to-noise ratio (SNR). The proposed model shows satisfactory performance in recovering the underlying source activation.
AB - Brain source localization from electroencephalogram (EEG) signals is an challenging problem for noninvasively localizing the brain activity. Conventional methods use handcrafted regularization terms based on neural-physiological assumptions by exploiting the spatial-temporal structure on the source signals. In recent years, deep learning frameworks have demonstrated superior performance for solving the inverse problems in the natural and medical imaging field. This study proposes a novel unsupervised learning training-free framework based on Generative Adversarial Networks and deep image prior (GANs-DIP) as a generative model simulating spatially structured source signal. The proposed framework can faithfully recover extended source patches activation patterns of the brain in an unsupervised manner. Numerical experiments on a realistic brain model are performed under different levels of signal-to-noise ratio (SNR). The proposed model shows satisfactory performance in recovering the underlying source activation.
KW - Deep Image Prior
KW - EEG Source Imaging
KW - Generative Adversarial Networks
KW - Inverse Problem
UR - http://www.scopus.com/inward/record.url?scp=85138127610&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85138127610&partnerID=8YFLogxK
U2 - 10.1109/EMBC48229.2022.9871172
DO - 10.1109/EMBC48229.2022.9871172
M3 - Conference contribution
C2 - 36083924
AN - SCOPUS:85138127610
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 572
EP - 575
BT - 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022
T2 - 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022
Y2 - 11 July 2022 through 15 July 2022
ER -