Cargando…

Expert and deep learning model identification of iEEG seizures and seizure onset times

Hundreds of 90-s iEEG records are typically captured from each NeuroPace RNS System patient between clinic visits. While these records provide invaluable information about the patient’s electrographic seizure and interictal activity patterns, manually classifying them into electrographic seizure/non...

Descripción completa

Detalles Bibliográficos
Autores principales: Arcot Desai, Sharanya, Afzal, Muhammad Furqan, Barry, Wade, Kuo, Jonathan, Benard, Shawna, Traner, Christopher, Tcheng, Thomas, Seale, Cairn, Morrell, Martha
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10354337/
https://www.ncbi.nlm.nih.gov/pubmed/37476840
http://dx.doi.org/10.3389/fnins.2023.1156838
_version_ 1785074905283297280
author Arcot Desai, Sharanya
Afzal, Muhammad Furqan
Barry, Wade
Kuo, Jonathan
Benard, Shawna
Traner, Christopher
Tcheng, Thomas
Seale, Cairn
Morrell, Martha
author_facet Arcot Desai, Sharanya
Afzal, Muhammad Furqan
Barry, Wade
Kuo, Jonathan
Benard, Shawna
Traner, Christopher
Tcheng, Thomas
Seale, Cairn
Morrell, Martha
author_sort Arcot Desai, Sharanya
collection PubMed
description Hundreds of 90-s iEEG records are typically captured from each NeuroPace RNS System patient between clinic visits. While these records provide invaluable information about the patient’s electrographic seizure and interictal activity patterns, manually classifying them into electrographic seizure/non-seizure activity, and manually identifying the seizure onset channels and times is an extremely time-consuming process. A convolutional neural network based Electrographic Seizure Classifier (ESC) model was developed in an earlier study. In this study, the classification model is tested against iEEG annotations provided by three expert reviewers board certified in epilepsy. The three experts individually annotated 3,874 iEEG channels from 36, 29, and 35 patients with leads in the mesiotemporal (MTL), neocortical (NEO), and MTL + NEO regions, respectively. The ESC model’s seizure/non-seizure classification scores agreed with the three reviewers at 88.7%, 89.6%, and 84.3% which was similar to how reviewers agreed with each other (92.9%–86.4%). On iEEG channels with all 3 experts in agreement (83.2%), the ESC model had an agreement score of 93.2%. Additionally, the ESC model’s certainty scores reflected combined reviewer certainty scores. When 0, 1, 2 and 3 (out of 3) reviewers annotated iEEG channels as electrographic seizures, the ESC model’s seizure certainty scores were in the range: [0.12–0.19], [0.32–0.42], [0.61–0.70], and [0.92–0.95] respectively. The ESC model was used as a starting-point model for training a second Seizure Onset Detection (SOD) model. For this task, seizure onset times were manually annotated on a relatively small number of iEEG channels (4,859 from 50 patients). Experiments showed that fine-tuning the ESC models with augmented data (30,768 iEEG channels) resulted in a better validation performance (on 20% of the manually annotated data) compared to training with only the original data (3.1s vs 4.4s median absolute error). Similarly, using the ESC model weights as the starting point for fine-tuning instead of other model weight initialization methods provided significant advantage in SOD model validation performance (3.1s vs 4.7s and 3.5s median absolute error). Finally, on iEEG channels where three expert annotations of seizure onset times were within 1.5 s, the SOD model’s seizure onset time prediction was within 1.7 s of expert annotation.
format Online
Article
Text
id pubmed-10354337
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-103543372023-07-20 Expert and deep learning model identification of iEEG seizures and seizure onset times Arcot Desai, Sharanya Afzal, Muhammad Furqan Barry, Wade Kuo, Jonathan Benard, Shawna Traner, Christopher Tcheng, Thomas Seale, Cairn Morrell, Martha Front Neurosci Neuroscience Hundreds of 90-s iEEG records are typically captured from each NeuroPace RNS System patient between clinic visits. While these records provide invaluable information about the patient’s electrographic seizure and interictal activity patterns, manually classifying them into electrographic seizure/non-seizure activity, and manually identifying the seizure onset channels and times is an extremely time-consuming process. A convolutional neural network based Electrographic Seizure Classifier (ESC) model was developed in an earlier study. In this study, the classification model is tested against iEEG annotations provided by three expert reviewers board certified in epilepsy. The three experts individually annotated 3,874 iEEG channels from 36, 29, and 35 patients with leads in the mesiotemporal (MTL), neocortical (NEO), and MTL + NEO regions, respectively. The ESC model’s seizure/non-seizure classification scores agreed with the three reviewers at 88.7%, 89.6%, and 84.3% which was similar to how reviewers agreed with each other (92.9%–86.4%). On iEEG channels with all 3 experts in agreement (83.2%), the ESC model had an agreement score of 93.2%. Additionally, the ESC model’s certainty scores reflected combined reviewer certainty scores. When 0, 1, 2 and 3 (out of 3) reviewers annotated iEEG channels as electrographic seizures, the ESC model’s seizure certainty scores were in the range: [0.12–0.19], [0.32–0.42], [0.61–0.70], and [0.92–0.95] respectively. The ESC model was used as a starting-point model for training a second Seizure Onset Detection (SOD) model. For this task, seizure onset times were manually annotated on a relatively small number of iEEG channels (4,859 from 50 patients). Experiments showed that fine-tuning the ESC models with augmented data (30,768 iEEG channels) resulted in a better validation performance (on 20% of the manually annotated data) compared to training with only the original data (3.1s vs 4.4s median absolute error). Similarly, using the ESC model weights as the starting point for fine-tuning instead of other model weight initialization methods provided significant advantage in SOD model validation performance (3.1s vs 4.7s and 3.5s median absolute error). Finally, on iEEG channels where three expert annotations of seizure onset times were within 1.5 s, the SOD model’s seizure onset time prediction was within 1.7 s of expert annotation. Frontiers Media S.A. 2023-07-05 /pmc/articles/PMC10354337/ /pubmed/37476840 http://dx.doi.org/10.3389/fnins.2023.1156838 Text en Copyright © 2023 Arcot Desai, Afzal, Barry, Kuo, Benard, Traner, Tcheng, Seale and Morrell. 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
Arcot Desai, Sharanya
Afzal, Muhammad Furqan
Barry, Wade
Kuo, Jonathan
Benard, Shawna
Traner, Christopher
Tcheng, Thomas
Seale, Cairn
Morrell, Martha
Expert and deep learning model identification of iEEG seizures and seizure onset times
title Expert and deep learning model identification of iEEG seizures and seizure onset times
title_full Expert and deep learning model identification of iEEG seizures and seizure onset times
title_fullStr Expert and deep learning model identification of iEEG seizures and seizure onset times
title_full_unstemmed Expert and deep learning model identification of iEEG seizures and seizure onset times
title_short Expert and deep learning model identification of iEEG seizures and seizure onset times
title_sort expert and deep learning model identification of ieeg seizures and seizure onset times
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10354337/
https://www.ncbi.nlm.nih.gov/pubmed/37476840
http://dx.doi.org/10.3389/fnins.2023.1156838
work_keys_str_mv AT arcotdesaisharanya expertanddeeplearningmodelidentificationofieegseizuresandseizureonsettimes
AT afzalmuhammadfurqan expertanddeeplearningmodelidentificationofieegseizuresandseizureonsettimes
AT barrywade expertanddeeplearningmodelidentificationofieegseizuresandseizureonsettimes
AT kuojonathan expertanddeeplearningmodelidentificationofieegseizuresandseizureonsettimes
AT benardshawna expertanddeeplearningmodelidentificationofieegseizuresandseizureonsettimes
AT tranerchristopher expertanddeeplearningmodelidentificationofieegseizuresandseizureonsettimes
AT tchengthomas expertanddeeplearningmodelidentificationofieegseizuresandseizureonsettimes
AT sealecairn expertanddeeplearningmodelidentificationofieegseizuresandseizureonsettimes
AT morrellmartha expertanddeeplearningmodelidentificationofieegseizuresandseizureonsettimes