# EEG-to-fMRI synthesis of task-evoked and spontaneous brain activity: addressing issues of statistical significance and generalizability

arXiv: https://arxiv.org/abs/2504.10752 · HTML: https://mlsanity.com/paper/2504.10752/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 64 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Builds on (most cited first, 12 of 12)

- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [CATD: Unified Representation Learning for EEG-to-fMRI Cross-Modal Generation](https://mlsanity.com/paper/2408.00777/) (2024)
- [NeuroBOLT: Resting-state EEG-to-fMRI Synthesis with Multi-dimensional Feature Mapping](https://mlsanity.com/paper/2410.05341/) (2024)
- [EEG to fMRI Synthesis: Is Deep Learning a candidate?](https://mlsanity.com/paper/2009.14133/) (2020)
- [EEG to fMRI Synthesis Benefits from Attentional Graphs of Electrode Relationships](https://mlsanity.com/paper/2203.03481/) (2022)
- [Leveraging sinusoidal representation networks to predict fMRI signals from EEG](https://mlsanity.com/paper/2311.04234/) (2023)
- [fMRI from EEG is only Deep Learning away: the use of interpretable DL to unravel EEG-fMRI relationships](https://mlsanity.com/paper/2211.02024/) (2022)
- [From Brainwaves to Brain Scans: A Robust Neural Network for EEG-to-fMRI Synthesis](https://mlsanity.com/paper/2502.08025/) (2025)
- [Latent Representation Learning for Multimodal Brain Activity Translation](https://mlsanity.com/paper/2409.18462/) (2024)
- [Latent neural source recovery via transcoding of simultaneous EEG-fMRI](https://mlsanity.com/paper/2010.02167/) (2020)
- [NeuXus: A Biosignal Processing and Classification Pipeline for Real-Time Brain-Computer Interaction](https://mlsanity.com/paper/2012.12794/) (2020)
- [Inferring latent neural sources via deep transcoding of simultaneously acquired EEG and fMRI](https://mlsanity.com/paper/2212.02226/) (2022)

## Abstract (arXiv)

A growing interest has developed in the problem of training models of EEG features to predict brain activity measured using fMRI, i.e. the problem of EEG-to-fMRI synthesis. Despite some reported success, the statistical significance and generalizability of EEG-to-fMRI predictions remains to be fully demonstrated. Here, we investigate the predictive power of EEG for both task-evoked and spontaneous activity of the somatomotor network measured by fMRI, based on data collected from healthy subjects in two different sessions. We trained subject-specific distributed-lag linear models of time-varying, multi-channel EEG spectral power using Sparse Group LASSO regularization, and we showed that learned models outperformed conventional EEG somatomotor rhythm predictors as well as massive univariate correlation models. Furthermore, we showed that learned models were statistically significantly better than appropriate null models in most subjects and conditions, although less frequently for spontaneous compared to task-evoked activity. Critically, predictions improved significantly when training and testing on data acquired in the same session relative to across sessions, highlighting the importance of temporally separating the collection of train and test data to avoid data leakage and optimistic bias in model generalization. In sum, while we demonstrate that EEG models can provide fMRI predictions with statistical significance, we also show that predictive power is impaired for spontaneous fluctuations in brain activity and for models trained on data acquired in a different session. Our findings highlight the need to explicitly consider these often overlooked issues in the growing literature of EEG-to-fMRI synthesis.