Cargando…

Automatic Seizure Classification Based on Domain-Invariant Deep Representation of EEG

Accurate identification of the type of seizure is very important for the treatment plan and drug prescription of epileptic patients. Artificial intelligence has shown considerable potential in the fields of automated EEG analysis and seizure classification. However, the highly personalized represent...

Descripción completa

Detalles Bibliográficos
Autores principales: Cao, Xincheng, Yao, Bin, Chen, Binqiang, Sun, Weifang, Tan, Guowei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8555879/
https://www.ncbi.nlm.nih.gov/pubmed/34720869
http://dx.doi.org/10.3389/fnins.2021.760987
_version_ 1784592066994503680
author Cao, Xincheng
Yao, Bin
Chen, Binqiang
Sun, Weifang
Tan, Guowei
author_facet Cao, Xincheng
Yao, Bin
Chen, Binqiang
Sun, Weifang
Tan, Guowei
author_sort Cao, Xincheng
collection PubMed
description Accurate identification of the type of seizure is very important for the treatment plan and drug prescription of epileptic patients. Artificial intelligence has shown considerable potential in the fields of automated EEG analysis and seizure classification. However, the highly personalized representation of epileptic seizures in EEG has led to many research results that are not satisfactory in clinical applications. In order to improve the clinical adaptability of the algorithm, this paper proposes an adversarial learning-driven domain-invariant deep feature representation method, which enables the hybrid deep networks (HDN) to reliably identify seizure types. In the train phase, we first use the labeled multi-lead EEG short samples to train squeeze-and-excitation networks (SENet) to extract short-term features, and then use the compressed samples to train the long short-term memory networks (LSTM) to extract long-time features and construct a classifier. In the inference phase, we first adjust the feature mapping of LSTM through the adversarial learning between LSTM and clustering subnet so that the EEG of the target patient and the EEG in the database obey the same distribution in the deep feature space. Finally, we use the adjusted classifier to identify the type of seizure. Experiments were carried out based on the TUH EEG Seizure Corpus and CHB-MIT seizure database. The experimental results show that the proposed domain adaptive deep feature representation improves the classification accuracy of the hybrid deep model in the target set by 5%. It is of great significance for the clinical application of EEG automatic analysis equipment.
format Online
Article
Text
id pubmed-8555879
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-85558792021-10-30 Automatic Seizure Classification Based on Domain-Invariant Deep Representation of EEG Cao, Xincheng Yao, Bin Chen, Binqiang Sun, Weifang Tan, Guowei Front Neurosci Neuroscience Accurate identification of the type of seizure is very important for the treatment plan and drug prescription of epileptic patients. Artificial intelligence has shown considerable potential in the fields of automated EEG analysis and seizure classification. However, the highly personalized representation of epileptic seizures in EEG has led to many research results that are not satisfactory in clinical applications. In order to improve the clinical adaptability of the algorithm, this paper proposes an adversarial learning-driven domain-invariant deep feature representation method, which enables the hybrid deep networks (HDN) to reliably identify seizure types. In the train phase, we first use the labeled multi-lead EEG short samples to train squeeze-and-excitation networks (SENet) to extract short-term features, and then use the compressed samples to train the long short-term memory networks (LSTM) to extract long-time features and construct a classifier. In the inference phase, we first adjust the feature mapping of LSTM through the adversarial learning between LSTM and clustering subnet so that the EEG of the target patient and the EEG in the database obey the same distribution in the deep feature space. Finally, we use the adjusted classifier to identify the type of seizure. Experiments were carried out based on the TUH EEG Seizure Corpus and CHB-MIT seizure database. The experimental results show that the proposed domain adaptive deep feature representation improves the classification accuracy of the hybrid deep model in the target set by 5%. It is of great significance for the clinical application of EEG automatic analysis equipment. Frontiers Media S.A. 2021-10-15 /pmc/articles/PMC8555879/ /pubmed/34720869 http://dx.doi.org/10.3389/fnins.2021.760987 Text en Copyright © 2021 Cao, Yao, Chen, Sun and Tan. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Cao, Xincheng
Yao, Bin
Chen, Binqiang
Sun, Weifang
Tan, Guowei
Automatic Seizure Classification Based on Domain-Invariant Deep Representation of EEG
title Automatic Seizure Classification Based on Domain-Invariant Deep Representation of EEG
title_full Automatic Seizure Classification Based on Domain-Invariant Deep Representation of EEG
title_fullStr Automatic Seizure Classification Based on Domain-Invariant Deep Representation of EEG
title_full_unstemmed Automatic Seizure Classification Based on Domain-Invariant Deep Representation of EEG
title_short Automatic Seizure Classification Based on Domain-Invariant Deep Representation of EEG
title_sort automatic seizure classification based on domain-invariant deep representation of eeg
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8555879/
https://www.ncbi.nlm.nih.gov/pubmed/34720869
http://dx.doi.org/10.3389/fnins.2021.760987
work_keys_str_mv AT caoxincheng automaticseizureclassificationbasedondomaininvariantdeeprepresentationofeeg
AT yaobin automaticseizureclassificationbasedondomaininvariantdeeprepresentationofeeg
AT chenbinqiang automaticseizureclassificationbasedondomaininvariantdeeprepresentationofeeg
AT sunweifang automaticseizureclassificationbasedondomaininvariantdeeprepresentationofeeg
AT tanguowei automaticseizureclassificationbasedondomaininvariantdeeprepresentationofeeg