UnEBOLT: A Unified Model for EEG-to-BOLD Translation and Functional Connectivity Reconstruction

Yamin Li, Ange Lou, Chang Li, Shiyu Wang, Haatef Pourmotabbed, Ziyuan Xu, Shengchao Zhang, Dario J. Englot, Soheil Kolouri, Daniel Moyer, Roza G. Bayrak, Catie Chang
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:2338-2351, 2026.

Abstract

Functional magnetic resonance imaging (fMRI) provides high-resolution, whole-brain dynamic information, but is costly and immobile, limiting its utility in low-resource settings. EEG-to-fMRI translation via deep learning offers a promising alternative, enabling access to deep brain activity from scalp EEG signals in naturalistic settings. However, current state-of-the-art methods for EEG-to-fMRI translation require training separate models for each brain region, limiting efficiency and scalability. Here, we introduce UnEBOLT, a Unified model for EEG-to-BOLD Translation. UnEBOLT is an end-to-end framework that predicts whole-brain fMRI time series from EEG by adaptive multi-region decoding within a single model. This approach enables efficient and comprehensive inference while also reconstructing subject-specific functional connectivity matrices, a representation that provides insight into neuronal interactions and which has been successfully utilized for clinical biomarkers. Our results show that UnEBOLT achieves comparable performance to dedicated ROI-specific models while scaling to multi-region prediction. Additionally, the reconstructed fMRI time series enable functional connectivity estimation, which may have broad applications in neuroscience.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-li26g, title = {UnEBOLT: A Unified Model for EEG-to-BOLD Translation and Functional Connectivity Reconstruction}, author = {Li, Yamin and Lou, Ange and Li, Chang and Wang, Shiyu and Pourmotabbed, Haatef and Xu, Ziyuan and Zhang, Shengchao and Englot, Dario J. and Kolouri, Soheil and Moyer, Daniel and Bayrak, Roza G. and Chang, Catie}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {2338--2351}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/li26g/li26g.pdf}, url = {https://proceedings.mlr.press/v315/li26g.html}, abstract = {Functional magnetic resonance imaging (fMRI) provides high-resolution, whole-brain dynamic information, but is costly and immobile, limiting its utility in low-resource settings. EEG-to-fMRI translation via deep learning offers a promising alternative, enabling access to deep brain activity from scalp EEG signals in naturalistic settings. However, current state-of-the-art methods for EEG-to-fMRI translation require training separate models for each brain region, limiting efficiency and scalability. Here, we introduce UnEBOLT, a Unified model for EEG-to-BOLD Translation. UnEBOLT is an end-to-end framework that predicts whole-brain fMRI time series from EEG by adaptive multi-region decoding within a single model. This approach enables efficient and comprehensive inference while also reconstructing subject-specific functional connectivity matrices, a representation that provides insight into neuronal interactions and which has been successfully utilized for clinical biomarkers. Our results show that UnEBOLT achieves comparable performance to dedicated ROI-specific models while scaling to multi-region prediction. Additionally, the reconstructed fMRI time series enable functional connectivity estimation, which may have broad applications in neuroscience.} }
Endnote
%0 Conference Paper %T UnEBOLT: A Unified Model for EEG-to-BOLD Translation and Functional Connectivity Reconstruction %A Yamin Li %A Ange Lou %A Chang Li %A Shiyu Wang %A Haatef Pourmotabbed %A Ziyuan Xu %A Shengchao Zhang %A Dario J. Englot %A Soheil Kolouri %A Daniel Moyer %A Roza G. Bayrak %A Catie Chang %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-li26g %I PMLR %P 2338--2351 %U https://proceedings.mlr.press/v315/li26g.html %V 315 %X Functional magnetic resonance imaging (fMRI) provides high-resolution, whole-brain dynamic information, but is costly and immobile, limiting its utility in low-resource settings. EEG-to-fMRI translation via deep learning offers a promising alternative, enabling access to deep brain activity from scalp EEG signals in naturalistic settings. However, current state-of-the-art methods for EEG-to-fMRI translation require training separate models for each brain region, limiting efficiency and scalability. Here, we introduce UnEBOLT, a Unified model for EEG-to-BOLD Translation. UnEBOLT is an end-to-end framework that predicts whole-brain fMRI time series from EEG by adaptive multi-region decoding within a single model. This approach enables efficient and comprehensive inference while also reconstructing subject-specific functional connectivity matrices, a representation that provides insight into neuronal interactions and which has been successfully utilized for clinical biomarkers. Our results show that UnEBOLT achieves comparable performance to dedicated ROI-specific models while scaling to multi-region prediction. Additionally, the reconstructed fMRI time series enable functional connectivity estimation, which may have broad applications in neuroscience.
APA
Li, Y., Lou, A., Li, C., Wang, S., Pourmotabbed, H., Xu, Z., Zhang, S., Englot, D.J., Kolouri, S., Moyer, D., Bayrak, R.G. & Chang, C.. (2026). UnEBOLT: A Unified Model for EEG-to-BOLD Translation and Functional Connectivity Reconstruction. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:2338-2351 Available from https://proceedings.mlr.press/v315/li26g.html.

Related Material