Assessing the Potential of Data Augmentation in EEG Functional Connectivity for Early Detection of Alzheimer’s Disease

Autores
Jia, Hao; Huang, Zihao; Caiafa, César Federico; Duan, Feng; Zhang, Yu; Sun, Zhe; Solé Casals, Jordi
Año de publicación
2023
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Electroencephalographic (EEG) signals are acquired non-invasively from electrodes placed on the scalp. Experts in the field can use EEG signals to distinguish between patients with Alzheimer’s disease (AD) and normal control (NC) subjects using classification models. However, the training of deep learning or machine learning models requires a large number of trials. Datasets related to Alzheimer’s disease are typically small in size due to the lack of AD patient samples. The lack of data samples required for the training process limits the use of deep learning techniques for further development in clinical settings. We propose to increase the number of trials in the training set by means of a decomposition–recombination system consisting of three steps. Firstly, the original signals from the training set are decomposed into multiple intrinsic mode functions via multivariate empirical mode decomposition. Next, these intrinsic mode functions are randomly recombined across trials. Finally, the recombined intrinsic mode functions are added together as artificial trials, which are used for training the models. We evaluated the decomposition–recombination system on a small dataset using each subject’s functional connectivity matrices as inputs. Three different neural networks, including ResNet, BrainNet CNN, and EEGNet, were used. Overall, the system helped improve ResNet training in both the mild AD dataset, with an increase of 5.24%, and in the mild cognitive impairment dataset, with an increase of 4.50%. The evaluation of the proposed data augmentation system shows that the performance of neural networks can be improved by enhancing the training set with data augmentation. This work shows the need for data augmentation on the training of neural networks in the case of small-size AD datasets.
Fil: Jia, Hao. Universitat de Vic; España. Nankai University; China
Fil: Huang, Zihao. Nankai University; China
Fil: Caiafa, César Federico. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; Argentina
Fil: Duan, Feng. Nankai University; China
Fil: Zhang, Yu. Lehigh University; Estados Unidos
Fil: Sun, Zhe. Juntendo University; China
Fil: Solé Casals, Jordi. Universitat de Vic; España
Materia
EEG
Alzheimer disease
Data augmentation
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/221800

id CONICETDig_5173c68457f4d81bfeb828d76709bcc3
oai_identifier_str oai:ri.conicet.gov.ar:11336/221800
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Assessing the Potential of Data Augmentation in EEG Functional Connectivity for Early Detection of Alzheimer’s DiseaseJia, HaoHuang, ZihaoCaiafa, César FedericoDuan, FengZhang, YuSun, ZheSolé Casals, JordiEEGAlzheimer diseaseData augmentationhttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1Electroencephalographic (EEG) signals are acquired non-invasively from electrodes placed on the scalp. Experts in the field can use EEG signals to distinguish between patients with Alzheimer’s disease (AD) and normal control (NC) subjects using classification models. However, the training of deep learning or machine learning models requires a large number of trials. Datasets related to Alzheimer’s disease are typically small in size due to the lack of AD patient samples. The lack of data samples required for the training process limits the use of deep learning techniques for further development in clinical settings. We propose to increase the number of trials in the training set by means of a decomposition–recombination system consisting of three steps. Firstly, the original signals from the training set are decomposed into multiple intrinsic mode functions via multivariate empirical mode decomposition. Next, these intrinsic mode functions are randomly recombined across trials. Finally, the recombined intrinsic mode functions are added together as artificial trials, which are used for training the models. We evaluated the decomposition–recombination system on a small dataset using each subject’s functional connectivity matrices as inputs. Three different neural networks, including ResNet, BrainNet CNN, and EEGNet, were used. Overall, the system helped improve ResNet training in both the mild AD dataset, with an increase of 5.24%, and in the mild cognitive impairment dataset, with an increase of 4.50%. The evaluation of the proposed data augmentation system shows that the performance of neural networks can be improved by enhancing the training set with data augmentation. This work shows the need for data augmentation on the training of neural networks in the case of small-size AD datasets.Fil: Jia, Hao. Universitat de Vic; España. Nankai University; ChinaFil: Huang, Zihao. Nankai University; ChinaFil: Caiafa, César Federico. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; ArgentinaFil: Duan, Feng. Nankai University; ChinaFil: Zhang, Yu. Lehigh University; Estados UnidosFil: Sun, Zhe. Juntendo University; ChinaFil: Solé Casals, Jordi. Universitat de Vic; EspañaSpringer2023-11info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/221800Jia, Hao; Huang, Zihao; Caiafa, César Federico; Duan, Feng; Zhang, Yu; et al.; Assessing the Potential of Data Augmentation in EEG Functional Connectivity for Early Detection of Alzheimer’s Disease; Springer; Cognitive Computation; 11-20231866-99561866-9964CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/doi/10.1007/s12559-023-10188-7info:eu-repo/semantics/altIdentifier/url/https://link.springer.com/article/10.1007/s12559-023-10188-7info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:06:00Zoai:ri.conicet.gov.ar:11336/221800instacron: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 10:06:00.481CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Assessing the Potential of Data Augmentation in EEG Functional Connectivity for Early Detection of Alzheimer’s Disease
title Assessing the Potential of Data Augmentation in EEG Functional Connectivity for Early Detection of Alzheimer’s Disease
spellingShingle Assessing the Potential of Data Augmentation in EEG Functional Connectivity for Early Detection of Alzheimer’s Disease
Jia, Hao
EEG
Alzheimer disease
Data augmentation
title_short Assessing the Potential of Data Augmentation in EEG Functional Connectivity for Early Detection of Alzheimer’s Disease
title_full Assessing the Potential of Data Augmentation in EEG Functional Connectivity for Early Detection of Alzheimer’s Disease
title_fullStr Assessing the Potential of Data Augmentation in EEG Functional Connectivity for Early Detection of Alzheimer’s Disease
title_full_unstemmed Assessing the Potential of Data Augmentation in EEG Functional Connectivity for Early Detection of Alzheimer’s Disease
title_sort Assessing the Potential of Data Augmentation in EEG Functional Connectivity for Early Detection of Alzheimer’s Disease
dc.creator.none.fl_str_mv Jia, Hao
Huang, Zihao
Caiafa, César Federico
Duan, Feng
Zhang, Yu
Sun, Zhe
Solé Casals, Jordi
author Jia, Hao
author_facet Jia, Hao
Huang, Zihao
Caiafa, César Federico
Duan, Feng
Zhang, Yu
Sun, Zhe
Solé Casals, Jordi
author_role author
author2 Huang, Zihao
Caiafa, César Federico
Duan, Feng
Zhang, Yu
Sun, Zhe
Solé Casals, Jordi
author2_role author
author
author
author
author
author
dc.subject.none.fl_str_mv EEG
Alzheimer disease
Data augmentation
topic EEG
Alzheimer disease
Data augmentation
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Electroencephalographic (EEG) signals are acquired non-invasively from electrodes placed on the scalp. Experts in the field can use EEG signals to distinguish between patients with Alzheimer’s disease (AD) and normal control (NC) subjects using classification models. However, the training of deep learning or machine learning models requires a large number of trials. Datasets related to Alzheimer’s disease are typically small in size due to the lack of AD patient samples. The lack of data samples required for the training process limits the use of deep learning techniques for further development in clinical settings. We propose to increase the number of trials in the training set by means of a decomposition–recombination system consisting of three steps. Firstly, the original signals from the training set are decomposed into multiple intrinsic mode functions via multivariate empirical mode decomposition. Next, these intrinsic mode functions are randomly recombined across trials. Finally, the recombined intrinsic mode functions are added together as artificial trials, which are used for training the models. We evaluated the decomposition–recombination system on a small dataset using each subject’s functional connectivity matrices as inputs. Three different neural networks, including ResNet, BrainNet CNN, and EEGNet, were used. Overall, the system helped improve ResNet training in both the mild AD dataset, with an increase of 5.24%, and in the mild cognitive impairment dataset, with an increase of 4.50%. The evaluation of the proposed data augmentation system shows that the performance of neural networks can be improved by enhancing the training set with data augmentation. This work shows the need for data augmentation on the training of neural networks in the case of small-size AD datasets.
Fil: Jia, Hao. Universitat de Vic; España. Nankai University; China
Fil: Huang, Zihao. Nankai University; China
Fil: Caiafa, César Federico. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; Argentina
Fil: Duan, Feng. Nankai University; China
Fil: Zhang, Yu. Lehigh University; Estados Unidos
Fil: Sun, Zhe. Juntendo University; China
Fil: Solé Casals, Jordi. Universitat de Vic; España
description Electroencephalographic (EEG) signals are acquired non-invasively from electrodes placed on the scalp. Experts in the field can use EEG signals to distinguish between patients with Alzheimer’s disease (AD) and normal control (NC) subjects using classification models. However, the training of deep learning or machine learning models requires a large number of trials. Datasets related to Alzheimer’s disease are typically small in size due to the lack of AD patient samples. The lack of data samples required for the training process limits the use of deep learning techniques for further development in clinical settings. We propose to increase the number of trials in the training set by means of a decomposition–recombination system consisting of three steps. Firstly, the original signals from the training set are decomposed into multiple intrinsic mode functions via multivariate empirical mode decomposition. Next, these intrinsic mode functions are randomly recombined across trials. Finally, the recombined intrinsic mode functions are added together as artificial trials, which are used for training the models. We evaluated the decomposition–recombination system on a small dataset using each subject’s functional connectivity matrices as inputs. Three different neural networks, including ResNet, BrainNet CNN, and EEGNet, were used. Overall, the system helped improve ResNet training in both the mild AD dataset, with an increase of 5.24%, and in the mild cognitive impairment dataset, with an increase of 4.50%. The evaluation of the proposed data augmentation system shows that the performance of neural networks can be improved by enhancing the training set with data augmentation. This work shows the need for data augmentation on the training of neural networks in the case of small-size AD datasets.
publishDate 2023
dc.date.none.fl_str_mv 2023-11
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/11336/221800
Jia, Hao; Huang, Zihao; Caiafa, César Federico; Duan, Feng; Zhang, Yu; et al.; Assessing the Potential of Data Augmentation in EEG Functional Connectivity for Early Detection of Alzheimer’s Disease; Springer; Cognitive Computation; 11-2023
1866-9956
1866-9964
CONICET Digital
CONICET
url http://hdl.handle.net/11336/221800
identifier_str_mv Jia, Hao; Huang, Zihao; Caiafa, César Federico; Duan, Feng; Zhang, Yu; et al.; Assessing the Potential of Data Augmentation in EEG Functional Connectivity for Early Detection of Alzheimer’s Disease; Springer; Cognitive Computation; 11-2023
1866-9956
1866-9964
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1007/s12559-023-10188-7
info:eu-repo/semantics/altIdentifier/url/https://link.springer.com/article/10.1007/s12559-023-10188-7
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
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_ 1844613903268446208
score 13.070432