Calibration-free Ocular artifact reduction in EEG signals using a montage-independent deep learning model

Producción Científica

Detalhes bibliográficos
Autores: Marcos Martínez, Diego, Pérez Velasco, Sergio, Martínez Cagigal, Víctor, SantaMaría Vazquez, Eduardo, Hornero Sánchez, Roberto
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:España
Recursos:Universidad de Valladolid
Repositorio:UVaDOC. Repositorio Documental de la Universidad de Valladolid
OAI Identifier:oai:uvadoc.uva.es:10324/78224
Acesso em linha:https://doi.org/10.1016/j.bspc.2025.108147
https://uvadoc.uva.es/handle/10324/78224
Access Level:acceso abierto
Palavra-chave:Deep learning
Ocular artifacts
Electroencephalography
Brain–computer interfaces
Electrooculography
32 Ciencias Médicas
33 Ciencias Tecnológicas
id ES_35bd2ac1e1fb633aa45ba49ae73d45cf
oai_identifier_str oai:uvadoc.uva.es:10324/78224
network_acronym_str ES
network_name_str España
repository_id_str
spelling Calibration-free Ocular artifact reduction in EEG signals using a montage-independent deep learning modelMarcos Martínez, DiegoPérez Velasco, SergioMartínez Cagigal, VíctorSantaMaría Vazquez, EduardoHornero Sánchez, RobertoDeep learningOcular artifactsElectroencephalographyBrain–computer interfacesElectrooculography32 Ciencias Médicas33 Ciencias TecnológicasProducción CientíficaOcular artifacts (OA) are the most common artifacts in electroencephalography (EEG), significantly affecting signal quality and analysis. Common approaches like indepentent component analysis (ICA) or regression-based methods address this problem but require several minutes of subject-specific EEG and electrooculography (EOG) calibration, making them impractical for real-time applications like brain–computer interfaces (BCI). In this study, we introduce EEGOAR-Net, a deep learning architecture designed to reduce OA in EEG. It address these issues while also providing flexibility across various EEG montages. Based on U-Net architecture, EEGOAR-Net was trained with contaminated EEG signals in order to reconstruct them with OA attenuated, using SGEYESUB as the reference method. In addition, a novel training methodology based on masking signals from different channels was applied to make EEGOAR-Net independent of the EEG montage used. A cross- validation analysis was conducted to assess EEGOAR-Net’s performance, demonstrating its ability to reduce EEG-EOG correlations to chance levels across most brain regions with minimal information loss. Thus, the performance of EEGOAR-Net is comparable to that of the reference method without the need for subject- specific calibration or EOG channels. Furthermore, validation on an additional dataset confirmed effective blink reduction and superior preservation of neural information compared to the state-of-the-art models: 1D- ResCNN and IC-U-Net. EEGOAR-Net’s performance across datasets and versatility across montages prove it to be a reliable and practical solution for EEG-based research and BCI applications, ensuring a notable reduction of OA on signal while maintaining the integrity of neural information.Esta publicación forma parte del proyecto TED2021-129915B-I00, financiado por MICIU/AEI/10.13039/501100011033 y el programa NextGenerationEU/PRTR de la Unión Europea.Este trabajo contó con el apoyo de los proyectos 0124_EUROAGE_MAS_4_E, cofinanciado por la Unión Europea a través del Programa Interreg VI-A España-Portugal (POCTEP) 2021-2027, y VA140P2 de la Federación Europea.Consejería de Educación de la Junta de Castilla y León: contrato predoctoral de Diego Marcos MartínezElsevier2025info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://doi.org/10.1016/j.bspc.2025.108147https://uvadoc.uva.es/handle/10324/78224reponame:UVaDOC. Repositorio Documental de la Universidad de Valladolidinstname:Universidad de ValladolidIngléshttps://www.sciencedirect.com/science/article/pii/S1746809425006585info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc/4.0/oai:uvadoc.uva.es:10324/782242026-06-13T12:44:47Z
dc.title.none.fl_str_mv Calibration-free Ocular artifact reduction in EEG signals using a montage-independent deep learning model
title Calibration-free Ocular artifact reduction in EEG signals using a montage-independent deep learning model
spellingShingle Calibration-free Ocular artifact reduction in EEG signals using a montage-independent deep learning model
Marcos Martínez, Diego
Deep learning
Ocular artifacts
Electroencephalography
Brain–computer interfaces
Electrooculography
32 Ciencias Médicas
33 Ciencias Tecnológicas
title_short Calibration-free Ocular artifact reduction in EEG signals using a montage-independent deep learning model
title_full Calibration-free Ocular artifact reduction in EEG signals using a montage-independent deep learning model
title_fullStr Calibration-free Ocular artifact reduction in EEG signals using a montage-independent deep learning model
title_full_unstemmed Calibration-free Ocular artifact reduction in EEG signals using a montage-independent deep learning model
title_sort Calibration-free Ocular artifact reduction in EEG signals using a montage-independent deep learning model
dc.creator.none.fl_str_mv Marcos Martínez, Diego
Pérez Velasco, Sergio
Martínez Cagigal, Víctor
SantaMaría Vazquez, Eduardo
Hornero Sánchez, Roberto
author Marcos Martínez, Diego
author_facet Marcos Martínez, Diego
Pérez Velasco, Sergio
Martínez Cagigal, Víctor
SantaMaría Vazquez, Eduardo
Hornero Sánchez, Roberto
author_role author
author2 Pérez Velasco, Sergio
Martínez Cagigal, Víctor
SantaMaría Vazquez, Eduardo
Hornero Sánchez, Roberto
author2_role author
author
author
author
dc.subject.none.fl_str_mv Deep learning
Ocular artifacts
Electroencephalography
Brain–computer interfaces
Electrooculography
32 Ciencias Médicas
33 Ciencias Tecnológicas
topic Deep learning
Ocular artifacts
Electroencephalography
Brain–computer interfaces
Electrooculography
32 Ciencias Médicas
33 Ciencias Tecnológicas
description Producción Científica
publishDate 2025
dc.date.none.fl_str_mv 2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://doi.org/10.1016/j.bspc.2025.108147
https://uvadoc.uva.es/handle/10324/78224
url https://doi.org/10.1016/j.bspc.2025.108147
https://uvadoc.uva.es/handle/10324/78224
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv https://www.sciencedirect.com/science/article/pii/S1746809425006585
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc/4.0/
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc/4.0/
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:UVaDOC. Repositorio Documental de la Universidad de Valladolid
instname:Universidad de Valladolid
instname_str Universidad de Valladolid
reponame_str UVaDOC. Repositorio Documental de la Universidad de Valladolid
collection UVaDOC. Repositorio Documental de la Universidad de Valladolid
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869405907913277440
score 15,81155

Registos relacionados