Application of deconvolutional networks for feature interpretability in epilepsy detection

IntroductionScalp electroencephalography (EEG) is commonly used to assist in epilepsy detection. Even automated detection algorithms are already available to assist clinicians in reviewing EEG data, many algorithms used for seizure detection in epilepsy fail to account for the contributions of diffe...

Full description

Saved in:
Bibliographic Details
Main Authors: Sihao Shao, Yu Zhou, Ruiheng Wu, Aiping Yang, Qiang Li
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-01-01
Series:Frontiers in Neuroscience
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fnins.2024.1539580/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832589823709282304
author Sihao Shao
Yu Zhou
Ruiheng Wu
Aiping Yang
Qiang Li
author_facet Sihao Shao
Yu Zhou
Ruiheng Wu
Aiping Yang
Qiang Li
author_sort Sihao Shao
collection DOAJ
description IntroductionScalp electroencephalography (EEG) is commonly used to assist in epilepsy detection. Even automated detection algorithms are already available to assist clinicians in reviewing EEG data, many algorithms used for seizure detection in epilepsy fail to account for the contributions of different channels. The Fully Convolutional Network (FCN) can provide the model’s interpretability but has not been applied in seizure detection.MethodsTo address these challenges, a novel convolutional neural network (CNN) model, combining SE (Squeeze-and-Excitation) modules, was proposed on top of the FCN. The epilepsy detection performance for patient-independent was evaluated on the CHB-MIT dataset. Then, the SE module was removed from the model and integrated the model with Inception, ResNet, and CBAM modules separately.ResultsThe method showed superior advancement, stability, and reliability compared to the other three methods. The method demonstrated a G-Mean of 82.7% for sensitivity (SEN) and specificity (SPE) on the CHB-MIT dataset. In addition, The contributions of each channel to the seizure detection task have also been quantified, which led us to find that the FZ, CZ, PZ, FT9, FT10, and T8 brain regions have a more pronounced impact on epileptic seizures.DiscussionThis article presents a novel algorithm for epilepsy detection that accurately identifies seizures in different patients and enhances the model’s interpretability.
format Article
id doaj-art-246304d2bff54479be27bd29bb7f0267
institution Kabale University
issn 1662-453X
language English
publishDate 2025-01-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neuroscience
spelling doaj-art-246304d2bff54479be27bd29bb7f02672025-01-24T07:13:28ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2025-01-011810.3389/fnins.2024.15395801539580Application of deconvolutional networks for feature interpretability in epilepsy detectionSihao Shao0Yu Zhou1Ruiheng Wu2Aiping Yang3Qiang Li4School of Microelectronics, Tianjin University, Tianjin, ChinaCollege of Medical Technology and Engineering, Henan University of Science and Technology, Luoyang, ChinaDepartment of Electronic and Electrical Engineering, Brunel University London, Uxbridge, United KingdomSchool of Electrical and Information Engineering, Tianjin University, Tianjin, ChinaSchool of Microelectronics, Tianjin University, Tianjin, ChinaIntroductionScalp electroencephalography (EEG) is commonly used to assist in epilepsy detection. Even automated detection algorithms are already available to assist clinicians in reviewing EEG data, many algorithms used for seizure detection in epilepsy fail to account for the contributions of different channels. The Fully Convolutional Network (FCN) can provide the model’s interpretability but has not been applied in seizure detection.MethodsTo address these challenges, a novel convolutional neural network (CNN) model, combining SE (Squeeze-and-Excitation) modules, was proposed on top of the FCN. The epilepsy detection performance for patient-independent was evaluated on the CHB-MIT dataset. Then, the SE module was removed from the model and integrated the model with Inception, ResNet, and CBAM modules separately.ResultsThe method showed superior advancement, stability, and reliability compared to the other three methods. The method demonstrated a G-Mean of 82.7% for sensitivity (SEN) and specificity (SPE) on the CHB-MIT dataset. In addition, The contributions of each channel to the seizure detection task have also been quantified, which led us to find that the FZ, CZ, PZ, FT9, FT10, and T8 brain regions have a more pronounced impact on epileptic seizures.DiscussionThis article presents a novel algorithm for epilepsy detection that accurately identifies seizures in different patients and enhances the model’s interpretability.https://www.frontiersin.org/articles/10.3389/fnins.2024.1539580/fullseizure detectionEEGdeconvolution networkinterpretability analysisdeep learning
spellingShingle Sihao Shao
Yu Zhou
Ruiheng Wu
Aiping Yang
Qiang Li
Application of deconvolutional networks for feature interpretability in epilepsy detection
Frontiers in Neuroscience
seizure detection
EEG
deconvolution network
interpretability analysis
deep learning
title Application of deconvolutional networks for feature interpretability in epilepsy detection
title_full Application of deconvolutional networks for feature interpretability in epilepsy detection
title_fullStr Application of deconvolutional networks for feature interpretability in epilepsy detection
title_full_unstemmed Application of deconvolutional networks for feature interpretability in epilepsy detection
title_short Application of deconvolutional networks for feature interpretability in epilepsy detection
title_sort application of deconvolutional networks for feature interpretability in epilepsy detection
topic seizure detection
EEG
deconvolution network
interpretability analysis
deep learning
url https://www.frontiersin.org/articles/10.3389/fnins.2024.1539580/full
work_keys_str_mv AT sihaoshao applicationofdeconvolutionalnetworksforfeatureinterpretabilityinepilepsydetection
AT yuzhou applicationofdeconvolutionalnetworksforfeatureinterpretabilityinepilepsydetection
AT ruihengwu applicationofdeconvolutionalnetworksforfeatureinterpretabilityinepilepsydetection
AT aipingyang applicationofdeconvolutionalnetworksforfeatureinterpretabilityinepilepsydetection
AT qiangli applicationofdeconvolutionalnetworksforfeatureinterpretabilityinepilepsydetection