# MEG Source Localization via Deep Learning

arXiv: https://arxiv.org/abs/2012.00588 · HTML: https://mlsanity.com/paper/2012.00588/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2020.

## Built on by (most cited first, 5 of 5)

- [Edge Sparse Basis Network: A Deep Learning Framework for EEG Source Localization](https://mlsanity.com/paper/2102.09188/) (2021)
- [Enhancing Brain Source Reconstruction by Initializing 3D Neural Networks with Physical Inverse Solutions](https://mlsanity.com/paper/2411.00143/) (2024)
- [Structure-Preserving Correction Learning for Sparse Bayesian Inference in Brain Source Imaging](https://mlsanity.com/paper/2606.07196/) (2026)
- [Current Source Localization Using Deep Prior with Depth Weighting](https://mlsanity.com/paper/2203.13981/) (2022)
- [Virtual iEEG from Scalp EEG: Charting the Landscape of Source Imaging, Intracranial Inference and Reconstruction](https://mlsanity.com/paper/2608.26998/) (2026)

## Abstract (arXiv)

We present a deep learning solution to the problem of localization of magnetoencephalography (MEG) brain signals. The proposed deep model architectures are tuned for single and multiple time point MEG data, and can estimate varying numbers of dipole sources. Results from simulated MEG data on the cortical surface of a real human subject demonstrated improvements against the popular RAP-MUSIC localization algorithm in specific scenarios with varying SNR levels, inter-source correlation values, and number of sources. Importantly, the deep learning models had robust performance to forward model errors and a significant reduction in computation time, to a fraction of 1 ms, paving the way to real-time MEG source localization.