From Brainwaves to Brain Scans: A Robust Neural Network for EEG-to-fMRI Synthesis
This work addresses the problem of high operational costs and infrastructural demands of fMRI for neuroimaging, providing a solution for researchers and clinicians who require accurate brain activity localization.
The authors tackled the problem of synthesizing fMRI images from low-cost EEG data and achieved state-of-the-art results, outperforming existing methods with their proposed E2fNet model. The model demonstrated promising performance across three public datasets, showing potential as a cost-effective solution for enhancing neuroimaging capabilities.
While functional magnetic resonance imaging (fMRI) offers valuable insights into brain activity, it is limited by high operational costs and significant infrastructural demands. In contrast, electroencephalography (EEG) provides millisecond-level precision in capturing electrical activity but lacks the spatial fidelity necessary for precise neural localization. To bridge these gaps, we propose E2fNet, a simple yet effective deep learning model for synthesizing fMRI images from low-cost EEG data. E2fNet is an encoder-decoder network specifically designed to capture and translate meaningful multi-scale features from EEG across electrode channels into accurate fMRI representations. Extensive evaluations across three public datasets demonstrate that E2fNet consistently outperforms existing CNN- and transformer-based methods, achieving state-of-the-art results in terms of the structural similarity index measure (SSIM). These results demonstrate that E2fNet is a promising, cost-effective solution for enhancing neuroimaging capabilities. The code is available at https://github.com/kgr20/E2fNet.