Contribution of low-level image statistics to EEG decoding of semantic content in multivariate and univariate models with feature optimization

Autores
Lützow Holm, Eric; Fernández Slezak, Diego; Tagliazucchi, Enzo Rodolfo
Año de publicación
2024
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Spatio-temporal patterns of evoked brain activity contain information that can be used to decode and categorize the semantic content of visual stimuli. However, this procedure can be biased by low-level image features independently of the semantic content present in the stimuli, prompting the need to understand the robustness of different models regarding these confounding factors. In this study, we trained machine learning models to distinguish between concepts included in the publicly available THINGS-EEG dataset using electroencephalography (EEG) data acquired during a rapid serial visual presentation paradigm. We investigated the contribution of low-level image features to decoding accuracy in a multivariate model, utilizing broadband data from all EEG channels. Additionally, we explored a univariate model obtained through data-driven feature selection applied to the spatial and frequency domains. While the univariate models exhibited better decoding accuracy, their predictions were less robust to the confounding effect of low-level image statistics. Notably, some of the models maintained their accuracy even after random replacement of the training dataset with semantically unrelated samples that presented similar low-level content. In conclusion, our findings suggest that model optimization impacts sensitivity to confounding factors, regardless of the resulting classification performance. Therefore, the choice of EEG features for semantic decoding should ideally be informed by criteria beyond classifier performance, such as the neurobiological mechanisms under study.
Fil: Lützow Holm, Eric. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación; Argentina
Fil: Fernández Slezak, Diego. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación; Argentina
Fil: Tagliazucchi, Enzo Rodolfo. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física de Buenos Aires. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física de Buenos Aires; Argentina
Materia
NEUROCIENCIA
NEURIMAGENES
DECODING
NACHINE LEARNING
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/265079

id CONICETDig_7be0a2b06273d403ebd0d4a294e5266a
oai_identifier_str oai:ri.conicet.gov.ar:11336/265079
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Contribution of low-level image statistics to EEG decoding of semantic content in multivariate and univariate models with feature optimizationLützow Holm, EricFernández Slezak, DiegoTagliazucchi, Enzo RodolfoNEUROCIENCIANEURIMAGENESDECODINGNACHINE LEARNINGhttps://purl.org/becyt/ford/1.3https://purl.org/becyt/ford/1Spatio-temporal patterns of evoked brain activity contain information that can be used to decode and categorize the semantic content of visual stimuli. However, this procedure can be biased by low-level image features independently of the semantic content present in the stimuli, prompting the need to understand the robustness of different models regarding these confounding factors. In this study, we trained machine learning models to distinguish between concepts included in the publicly available THINGS-EEG dataset using electroencephalography (EEG) data acquired during a rapid serial visual presentation paradigm. We investigated the contribution of low-level image features to decoding accuracy in a multivariate model, utilizing broadband data from all EEG channels. Additionally, we explored a univariate model obtained through data-driven feature selection applied to the spatial and frequency domains. While the univariate models exhibited better decoding accuracy, their predictions were less robust to the confounding effect of low-level image statistics. Notably, some of the models maintained their accuracy even after random replacement of the training dataset with semantically unrelated samples that presented similar low-level content. In conclusion, our findings suggest that model optimization impacts sensitivity to confounding factors, regardless of the resulting classification performance. Therefore, the choice of EEG features for semantic decoding should ideally be informed by criteria beyond classifier performance, such as the neurobiological mechanisms under study.Fil: Lützow Holm, Eric. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación; ArgentinaFil: Fernández Slezak, Diego. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación; ArgentinaFil: Tagliazucchi, Enzo Rodolfo. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física de Buenos Aires. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física de Buenos Aires; ArgentinaElsevier2024-06info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/265079Lützow Holm, Eric; Fernández Slezak, Diego; Tagliazucchi, Enzo Rodolfo; Contribution of low-level image statistics to EEG decoding of semantic content in multivariate and univariate models with feature optimization; Elsevier; Journal Neuroimag; 293; 6-2024; 1-131053-8119CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://linkinghub.elsevier.com/retrieve/pii/S1053811924001216info:eu-repo/semantics/altIdentifier/doi/10.1016/j.neuroimage.2024.120626info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:15:09Zoai:ri.conicet.gov.ar:11336/265079instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 10:15:09.998CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Contribution of low-level image statistics to EEG decoding of semantic content in multivariate and univariate models with feature optimization
title Contribution of low-level image statistics to EEG decoding of semantic content in multivariate and univariate models with feature optimization
spellingShingle Contribution of low-level image statistics to EEG decoding of semantic content in multivariate and univariate models with feature optimization
Lützow Holm, Eric
NEUROCIENCIA
NEURIMAGENES
DECODING
NACHINE LEARNING
title_short Contribution of low-level image statistics to EEG decoding of semantic content in multivariate and univariate models with feature optimization
title_full Contribution of low-level image statistics to EEG decoding of semantic content in multivariate and univariate models with feature optimization
title_fullStr Contribution of low-level image statistics to EEG decoding of semantic content in multivariate and univariate models with feature optimization
title_full_unstemmed Contribution of low-level image statistics to EEG decoding of semantic content in multivariate and univariate models with feature optimization
title_sort Contribution of low-level image statistics to EEG decoding of semantic content in multivariate and univariate models with feature optimization
dc.creator.none.fl_str_mv Lützow Holm, Eric
Fernández Slezak, Diego
Tagliazucchi, Enzo Rodolfo
author Lützow Holm, Eric
author_facet Lützow Holm, Eric
Fernández Slezak, Diego
Tagliazucchi, Enzo Rodolfo
author_role author
author2 Fernández Slezak, Diego
Tagliazucchi, Enzo Rodolfo
author2_role author
author
dc.subject.none.fl_str_mv NEUROCIENCIA
NEURIMAGENES
DECODING
NACHINE LEARNING
topic NEUROCIENCIA
NEURIMAGENES
DECODING
NACHINE LEARNING
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.3
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Spatio-temporal patterns of evoked brain activity contain information that can be used to decode and categorize the semantic content of visual stimuli. However, this procedure can be biased by low-level image features independently of the semantic content present in the stimuli, prompting the need to understand the robustness of different models regarding these confounding factors. In this study, we trained machine learning models to distinguish between concepts included in the publicly available THINGS-EEG dataset using electroencephalography (EEG) data acquired during a rapid serial visual presentation paradigm. We investigated the contribution of low-level image features to decoding accuracy in a multivariate model, utilizing broadband data from all EEG channels. Additionally, we explored a univariate model obtained through data-driven feature selection applied to the spatial and frequency domains. While the univariate models exhibited better decoding accuracy, their predictions were less robust to the confounding effect of low-level image statistics. Notably, some of the models maintained their accuracy even after random replacement of the training dataset with semantically unrelated samples that presented similar low-level content. In conclusion, our findings suggest that model optimization impacts sensitivity to confounding factors, regardless of the resulting classification performance. Therefore, the choice of EEG features for semantic decoding should ideally be informed by criteria beyond classifier performance, such as the neurobiological mechanisms under study.
Fil: Lützow Holm, Eric. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación; Argentina
Fil: Fernández Slezak, Diego. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación; Argentina
Fil: Tagliazucchi, Enzo Rodolfo. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Física de Buenos Aires. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Física de Buenos Aires; Argentina
description Spatio-temporal patterns of evoked brain activity contain information that can be used to decode and categorize the semantic content of visual stimuli. However, this procedure can be biased by low-level image features independently of the semantic content present in the stimuli, prompting the need to understand the robustness of different models regarding these confounding factors. In this study, we trained machine learning models to distinguish between concepts included in the publicly available THINGS-EEG dataset using electroencephalography (EEG) data acquired during a rapid serial visual presentation paradigm. We investigated the contribution of low-level image features to decoding accuracy in a multivariate model, utilizing broadband data from all EEG channels. Additionally, we explored a univariate model obtained through data-driven feature selection applied to the spatial and frequency domains. While the univariate models exhibited better decoding accuracy, their predictions were less robust to the confounding effect of low-level image statistics. Notably, some of the models maintained their accuracy even after random replacement of the training dataset with semantically unrelated samples that presented similar low-level content. In conclusion, our findings suggest that model optimization impacts sensitivity to confounding factors, regardless of the resulting classification performance. Therefore, the choice of EEG features for semantic decoding should ideally be informed by criteria beyond classifier performance, such as the neurobiological mechanisms under study.
publishDate 2024
dc.date.none.fl_str_mv 2024-06
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/265079
Lützow Holm, Eric; Fernández Slezak, Diego; Tagliazucchi, Enzo Rodolfo; Contribution of low-level image statistics to EEG decoding of semantic content in multivariate and univariate models with feature optimization; Elsevier; Journal Neuroimag; 293; 6-2024; 1-13
1053-8119
CONICET Digital
CONICET
url http://hdl.handle.net/11336/265079
identifier_str_mv Lützow Holm, Eric; Fernández Slezak, Diego; Tagliazucchi, Enzo Rodolfo; Contribution of low-level image statistics to EEG decoding of semantic content in multivariate and univariate models with feature optimization; Elsevier; Journal Neuroimag; 293; 6-2024; 1-13
1053-8119
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://linkinghub.elsevier.com/retrieve/pii/S1053811924001216
info:eu-repo/semantics/altIdentifier/doi/10.1016/j.neuroimage.2024.120626
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844614085976522752
score 13.070432