Evaluating CNN Methods for Epileptic Seizure Type Classification Using EEG Data

Epilepsy impacts around 6.38 per 1,000 people globally, presenting diagnostic challenges due to the complexity of seizures. Accurate classification of seizure types via Electroencephalogram (EEG) is critical for effective treatment and enhancing patient quality of life. However, the intricate charac...

Full description

Bibliographic Details
Authors: Rivera, MJ, Sanchis, J, Corcho, O, Teruel, MA, Trujillo, J
Format: article
Status:Published version
Publication Date:2024
Country:España
Institution:Instituto de Investigación Biomédica y Sanitaria de Alicante (ISABIAL)
Repository:r-ISABIAL. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica y Sanitaria de Alicante
OAI Identifier:oai:isabial.fundanetsuite.com:p10139
Online Access:https://isabial.portalinvestigacion.com/publicaciones10139
https://ieeexplore.ieee.org/document/10540033
Access Level:Open access
Keyword:Electroencephalography
Convolutional neural networks
Epilepsy
Brain modeling
Feature extraction
Support vector machines
Deep learning
deep learning
electroencephalography
epileptic seizure
separable convolutions
id ES_332d5a1aba3be3caaa4b06650d9fb91f
oai_identifier_str oai:isabial.fundanetsuite.com:p10139
network_acronym_str ES
network_name_str España
repository_id_str
spelling Evaluating CNN Methods for Epileptic Seizure Type Classification Using EEG DataRivera, MJSanchis, JCorcho, OTeruel, MATrujillo, JElectroencephalographyConvolutional neural networksEpilepsyBrain modelingFeature extractionSupport vector machinesDeep learningdeep learningelectroencephalographyepileptic seizureseparable convolutionsEpilepsy impacts around 6.38 per 1,000 people globally, presenting diagnostic challenges due to the complexity of seizures. Accurate classification of seizure types via Electroencephalogram (EEG) is critical for effective treatment and enhancing patient quality of life. However, the intricate characteristics of EEG data necessitate expert interpretation, a process that is both time-intensive and susceptible to human error. Recent advancements in Deep Learning (DL) have shown promise in EEG analysis, offering new avenues for seizure type classification. This study introduces two innovative deep learning architectures designed for seizure type classification within a seven-class framework: Network 1D Raw, which applies 1D Convolutions to Raw EEG signals, and Network 2D Conv, utilizing 2D convolutions on pre-computed spectrograms. Both architectures employ Separable Convolutions to enhance feature extraction efficiency, with the Network 1D Raw also incorporating a dilation rate technique for expanded analysis. Tested on the Temple University Hospital Seizure (TUSZ) dataset, these methods are evaluated using inter-patient 3-fold cross-validation. The Network 1D Raw achieved a weighted f1-score of $0.611 \pm 0.037$ , while the Network 2D Conv reached $0.599 \pm 0.052$ , both surpassing existing benchmarks. The Network 1D Raw demonstrated superior classification for Absence Seizure (ABSZ), Focal Non-specific Seizures (FNSZ), and Generalized Non-specific Seizures types (GNSZ) with AUPRs of $0.9400 \pm 0.0500$ , $0.8100\pm 0.0300$ , and $0.5500\pm 0.1800$ , with Network 2D Conv excelling in FNSZ Seizures and GNSZ classes with AUPRs of $0.8100 \pm 0.1100$ and $0.4000 \pm 0.0200$ . Our DL models advance seizure type classification, blending efficiency with accuracy. Network 1D Raw's compact design suits low-resource environments, aiding quick, precise diagnoses. Future work will focus on expanding dataset diversity, particularly for underrepresented seizure types, to further refine classification performance.IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2024info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttps://isabial.portalinvestigacion.com/publicaciones10139https://ieeexplore.ieee.org/document/10540033IEEE AccessISSN: 21693536reponame:r-ISABIAL. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica y Sanitaria de Alicanteinstname:Instituto de Investigación Biomédica y Sanitaria de Alicante (ISABIAL)Inglésinfo:eu-repo/semantics/openAccessoai:isabial.fundanetsuite.com:p101392026-06-12T10:20:37Z
dc.title.none.fl_str_mv Evaluating CNN Methods for Epileptic Seizure Type Classification Using EEG Data
title Evaluating CNN Methods for Epileptic Seizure Type Classification Using EEG Data
spellingShingle Evaluating CNN Methods for Epileptic Seizure Type Classification Using EEG Data
Rivera, MJ
Electroencephalography
Convolutional neural networks
Epilepsy
Brain modeling
Feature extraction
Support vector machines
Deep learning
deep learning
electroencephalography
epileptic seizure
separable convolutions
title_short Evaluating CNN Methods for Epileptic Seizure Type Classification Using EEG Data
title_full Evaluating CNN Methods for Epileptic Seizure Type Classification Using EEG Data
title_fullStr Evaluating CNN Methods for Epileptic Seizure Type Classification Using EEG Data
title_full_unstemmed Evaluating CNN Methods for Epileptic Seizure Type Classification Using EEG Data
title_sort Evaluating CNN Methods for Epileptic Seizure Type Classification Using EEG Data
dc.creator.none.fl_str_mv Rivera, MJ
Sanchis, J
Corcho, O
Teruel, MA
Trujillo, J
author Rivera, MJ
author_facet Rivera, MJ
Sanchis, J
Corcho, O
Teruel, MA
Trujillo, J
author_role author
author2 Sanchis, J
Corcho, O
Teruel, MA
Trujillo, J
author2_role author
author
author
author
dc.subject.none.fl_str_mv Electroencephalography
Convolutional neural networks
Epilepsy
Brain modeling
Feature extraction
Support vector machines
Deep learning
deep learning
electroencephalography
epileptic seizure
separable convolutions
topic Electroencephalography
Convolutional neural networks
Epilepsy
Brain modeling
Feature extraction
Support vector machines
Deep learning
deep learning
electroencephalography
epileptic seizure
separable convolutions
description Epilepsy impacts around 6.38 per 1,000 people globally, presenting diagnostic challenges due to the complexity of seizures. Accurate classification of seizure types via Electroencephalogram (EEG) is critical for effective treatment and enhancing patient quality of life. However, the intricate characteristics of EEG data necessitate expert interpretation, a process that is both time-intensive and susceptible to human error. Recent advancements in Deep Learning (DL) have shown promise in EEG analysis, offering new avenues for seizure type classification. This study introduces two innovative deep learning architectures designed for seizure type classification within a seven-class framework: Network 1D Raw, which applies 1D Convolutions to Raw EEG signals, and Network 2D Conv, utilizing 2D convolutions on pre-computed spectrograms. Both architectures employ Separable Convolutions to enhance feature extraction efficiency, with the Network 1D Raw also incorporating a dilation rate technique for expanded analysis. Tested on the Temple University Hospital Seizure (TUSZ) dataset, these methods are evaluated using inter-patient 3-fold cross-validation. The Network 1D Raw achieved a weighted f1-score of $0.611 \pm 0.037$ , while the Network 2D Conv reached $0.599 \pm 0.052$ , both surpassing existing benchmarks. The Network 1D Raw demonstrated superior classification for Absence Seizure (ABSZ), Focal Non-specific Seizures (FNSZ), and Generalized Non-specific Seizures types (GNSZ) with AUPRs of $0.9400 \pm 0.0500$ , $0.8100\pm 0.0300$ , and $0.5500\pm 0.1800$ , with Network 2D Conv excelling in FNSZ Seizures and GNSZ classes with AUPRs of $0.8100 \pm 0.1100$ and $0.4000 \pm 0.0200$ . Our DL models advance seizure type classification, blending efficiency with accuracy. Network 1D Raw's compact design suits low-resource environments, aiding quick, precise diagnoses. Future work will focus on expanding dataset diversity, particularly for underrepresented seizure types, to further refine classification performance.
publishDate 2024
dc.date.none.fl_str_mv 2024
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://isabial.portalinvestigacion.com/publicaciones10139
https://ieeexplore.ieee.org/document/10540033
url https://isabial.portalinvestigacion.com/publicaciones10139
https://ieeexplore.ieee.org/document/10540033
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
publisher.none.fl_str_mv IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.source.none.fl_str_mv IEEE Access
ISSN: 21693536
reponame:r-ISABIAL. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica y Sanitaria de Alicante
instname:Instituto de Investigación Biomédica y Sanitaria de Alicante (ISABIAL)
instname_str Instituto de Investigación Biomédica y Sanitaria de Alicante (ISABIAL)
reponame_str r-ISABIAL. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica y Sanitaria de Alicante
collection r-ISABIAL. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica y Sanitaria de Alicante
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869405729825226752
score 15.812429