Magnetoencephalographic source localization and reconstruction via deep learning

Within this manuscript a deep learning algorithm designed to achieve both spatial and temporal source reconstruction based on signals captured by MEG devices is introduced. Brain signal estimation at source level is a significant challenge in magnetoencephalographic (MEG) data processing. Traditiona...

Full description

Saved in:
Bibliographic Details
Main Authors: Stefano Franceschini, Michele Ambrosanio, Maria Maddalena Autorino, Sohail Maqsood, Fabio Baselice
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Neuroscience
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fnins.2025.1578473/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849404606484840448
author Stefano Franceschini
Michele Ambrosanio
Maria Maddalena Autorino
Sohail Maqsood
Fabio Baselice
author_facet Stefano Franceschini
Michele Ambrosanio
Maria Maddalena Autorino
Sohail Maqsood
Fabio Baselice
author_sort Stefano Franceschini
collection DOAJ
description Within this manuscript a deep learning algorithm designed to achieve both spatial and temporal source reconstruction based on signals captured by MEG devices is introduced. Brain signal estimation at source level is a significant challenge in magnetoencephalographic (MEG) data processing. Traditional algorithms offer excellent temporal resolution but are limited in spatial resolution due to the inherent ill-posed nature of the problem. Nevertheless, many applications require precise localization of pathological tissues to provide reliable information for clinicians. In this context, deep learning solutions emerge as promising candidates for high resolution signals estimations. The proposed approach, termed “Deep-MEG,” employs a hybrid neural network architecture capable of extracting both temporal and spatial information from signals captured by MEG sensors. The algorithm is capable to handling the entire brain and, therefore, is not limited to cortical sources imaging. To validate its efficacy, the Authors conducted simulations involving multiple active sources using a realistic forward model, and subsequently compared the results with those obtained using various state-of-the-art reconstruction algorithms. Finally Deep-MEG has been tested also with real MEG data.
format Article
id doaj-art-0ff7a43e5bb6422f99665e2f8fba6e22
institution Kabale University
issn 1662-453X
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neuroscience
spelling doaj-art-0ff7a43e5bb6422f99665e2f8fba6e222025-08-20T03:36:57ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2025-07-011910.3389/fnins.2025.15784731578473Magnetoencephalographic source localization and reconstruction via deep learningStefano Franceschini0Michele Ambrosanio1Maria Maddalena Autorino2Sohail Maqsood3Fabio Baselice4Department of Engineering, University of Naples Parthenope, Naples, ItalyDepartment of Economics, Law, Cybersecurity and Sports Sciences (DiSEGIM), University of Naples Parthenope, Naples, ItalyDepartment of Engineering, University of Naples Parthenope, Naples, ItalyDepartment of Engineering, University of Naples Parthenope, Naples, ItalyDepartment of Engineering, University of Naples Parthenope, Naples, ItalyWithin this manuscript a deep learning algorithm designed to achieve both spatial and temporal source reconstruction based on signals captured by MEG devices is introduced. Brain signal estimation at source level is a significant challenge in magnetoencephalographic (MEG) data processing. Traditional algorithms offer excellent temporal resolution but are limited in spatial resolution due to the inherent ill-posed nature of the problem. Nevertheless, many applications require precise localization of pathological tissues to provide reliable information for clinicians. In this context, deep learning solutions emerge as promising candidates for high resolution signals estimations. The proposed approach, termed “Deep-MEG,” employs a hybrid neural network architecture capable of extracting both temporal and spatial information from signals captured by MEG sensors. The algorithm is capable to handling the entire brain and, therefore, is not limited to cortical sources imaging. To validate its efficacy, the Authors conducted simulations involving multiple active sources using a realistic forward model, and subsequently compared the results with those obtained using various state-of-the-art reconstruction algorithms. Finally Deep-MEG has been tested also with real MEG data.https://www.frontiersin.org/articles/10.3389/fnins.2025.1578473/fullbeamformingbrain signal estimationbrain source reconstructionneural networksmagnetoencephalography
spellingShingle Stefano Franceschini
Michele Ambrosanio
Maria Maddalena Autorino
Sohail Maqsood
Fabio Baselice
Magnetoencephalographic source localization and reconstruction via deep learning
Frontiers in Neuroscience
beamforming
brain signal estimation
brain source reconstruction
neural networks
magnetoencephalography
title Magnetoencephalographic source localization and reconstruction via deep learning
title_full Magnetoencephalographic source localization and reconstruction via deep learning
title_fullStr Magnetoencephalographic source localization and reconstruction via deep learning
title_full_unstemmed Magnetoencephalographic source localization and reconstruction via deep learning
title_short Magnetoencephalographic source localization and reconstruction via deep learning
title_sort magnetoencephalographic source localization and reconstruction via deep learning
topic beamforming
brain signal estimation
brain source reconstruction
neural networks
magnetoencephalography
url https://www.frontiersin.org/articles/10.3389/fnins.2025.1578473/full
work_keys_str_mv AT stefanofranceschini magnetoencephalographicsourcelocalizationandreconstructionviadeeplearning
AT micheleambrosanio magnetoencephalographicsourcelocalizationandreconstructionviadeeplearning
AT mariamaddalenaautorino magnetoencephalographicsourcelocalizationandreconstructionviadeeplearning
AT sohailmaqsood magnetoencephalographicsourcelocalizationandreconstructionviadeeplearning
AT fabiobaselice magnetoencephalographicsourcelocalizationandreconstructionviadeeplearning