Automatic seizure detection based on imaged-EEG signals through fully convolutional networks

Abstract Seizure detection is a routine process in epilepsy units requiring manual intervention of well-trained specialists. This process could be extensive, inefficient and time-consuming, especially for long term recordings. We proposed an automatic method to detect epileptic seizures using an ima...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Catalina Gómez, Pablo Arbeláez, Miguel Navarrete, Catalina Alvarado-Rojas, Michel Le Van Quyen, Mario Valderrama
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2020
Materias:
R
Q
Acceso en línea:https://doaj.org/article/4a95fabc477b4360a5315b71e255c900
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:4a95fabc477b4360a5315b71e255c900
record_format dspace
spelling oai:doaj.org-article:4a95fabc477b4360a5315b71e255c9002021-12-02T16:18:05ZAutomatic seizure detection based on imaged-EEG signals through fully convolutional networks10.1038/s41598-020-78784-32045-2322https://doaj.org/article/4a95fabc477b4360a5315b71e255c9002020-12-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-78784-3https://doaj.org/toc/2045-2322Abstract Seizure detection is a routine process in epilepsy units requiring manual intervention of well-trained specialists. This process could be extensive, inefficient and time-consuming, especially for long term recordings. We proposed an automatic method to detect epileptic seizures using an imaged-EEG representation of brain signals. To accomplish this, we analyzed EEG signals from two different datasets: the CHB-MIT Scalp EEG database and the EPILEPSIAE project that includes scalp and intracranial recordings. We used fully convolutional neural networks to automatically detect seizures. For our best model, we reached average accuracy and specificity values of 99.3% and 99.6%, respectively, for the CHB-MIT dataset, and corresponding values of 98.0% and 98.3% for the EPILEPSIAE patients. For these patients, the inclusion of intracranial electrodes together with scalp ones increased the average accuracy and specificity values to 99.6% and 58.3%, respectively. Regarding the other metrics, our best model reached average precision of 62.7%, recall of 58.3%, F-measure of 59.0% and AP of 54.5% on the CHB-MIT recordings, and comparatively lowers performances for the EPILEPSIAE dataset. For both databases, the number of false alarms per hour reached values less than 0.5/h for 92% of the CHB-MIT patients and less than 1.0/h for 80% of the EPILEPSIAE patients. Compared to recent studies, our lightweight approach does not need any estimation of pre-selected features and demonstrates high performances with promising possibilities for the introduction of such automatic methods in the clinical practice.Catalina GómezPablo ArbeláezMiguel NavarreteCatalina Alvarado-RojasMichel Le Van QuyenMario ValderramaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-13 (2020)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Catalina Gómez
Pablo Arbeláez
Miguel Navarrete
Catalina Alvarado-Rojas
Michel Le Van Quyen
Mario Valderrama
Automatic seizure detection based on imaged-EEG signals through fully convolutional networks
description Abstract Seizure detection is a routine process in epilepsy units requiring manual intervention of well-trained specialists. This process could be extensive, inefficient and time-consuming, especially for long term recordings. We proposed an automatic method to detect epileptic seizures using an imaged-EEG representation of brain signals. To accomplish this, we analyzed EEG signals from two different datasets: the CHB-MIT Scalp EEG database and the EPILEPSIAE project that includes scalp and intracranial recordings. We used fully convolutional neural networks to automatically detect seizures. For our best model, we reached average accuracy and specificity values of 99.3% and 99.6%, respectively, for the CHB-MIT dataset, and corresponding values of 98.0% and 98.3% for the EPILEPSIAE patients. For these patients, the inclusion of intracranial electrodes together with scalp ones increased the average accuracy and specificity values to 99.6% and 58.3%, respectively. Regarding the other metrics, our best model reached average precision of 62.7%, recall of 58.3%, F-measure of 59.0% and AP of 54.5% on the CHB-MIT recordings, and comparatively lowers performances for the EPILEPSIAE dataset. For both databases, the number of false alarms per hour reached values less than 0.5/h for 92% of the CHB-MIT patients and less than 1.0/h for 80% of the EPILEPSIAE patients. Compared to recent studies, our lightweight approach does not need any estimation of pre-selected features and demonstrates high performances with promising possibilities for the introduction of such automatic methods in the clinical practice.
format article
author Catalina Gómez
Pablo Arbeláez
Miguel Navarrete
Catalina Alvarado-Rojas
Michel Le Van Quyen
Mario Valderrama
author_facet Catalina Gómez
Pablo Arbeláez
Miguel Navarrete
Catalina Alvarado-Rojas
Michel Le Van Quyen
Mario Valderrama
author_sort Catalina Gómez
title Automatic seizure detection based on imaged-EEG signals through fully convolutional networks
title_short Automatic seizure detection based on imaged-EEG signals through fully convolutional networks
title_full Automatic seizure detection based on imaged-EEG signals through fully convolutional networks
title_fullStr Automatic seizure detection based on imaged-EEG signals through fully convolutional networks
title_full_unstemmed Automatic seizure detection based on imaged-EEG signals through fully convolutional networks
title_sort automatic seizure detection based on imaged-eeg signals through fully convolutional networks
publisher Nature Portfolio
publishDate 2020
url https://doaj.org/article/4a95fabc477b4360a5315b71e255c900
work_keys_str_mv AT catalinagomez automaticseizuredetectionbasedonimagedeegsignalsthroughfullyconvolutionalnetworks
AT pabloarbelaez automaticseizuredetectionbasedonimagedeegsignalsthroughfullyconvolutionalnetworks
AT miguelnavarrete automaticseizuredetectionbasedonimagedeegsignalsthroughfullyconvolutionalnetworks
AT catalinaalvaradorojas automaticseizuredetectionbasedonimagedeegsignalsthroughfullyconvolutionalnetworks
AT michellevanquyen automaticseizuredetectionbasedonimagedeegsignalsthroughfullyconvolutionalnetworks
AT mariovalderrama automaticseizuredetectionbasedonimagedeegsignalsthroughfullyconvolutionalnetworks
_version_ 1718384165945081856