A Lightweight Convolutional Neural Network-Reformer Model for Efficient Epileptic Seizure Detection.

International journal of neural systems Pub Date : 2024-12-01 Epub Date: 2024-09-30 DOI:10.1142/S0129065724500655
Haozhou Cui, Xiangwen Zhong, Haotian Li, Chuanyu Li, Xingchen Dong, Dezan Ji, Landi He, Weidong Zhou
{"title":"A Lightweight Convolutional Neural Network-Reformer Model for Efficient Epileptic Seizure Detection.","authors":"Haozhou Cui, Xiangwen Zhong, Haotian Li, Chuanyu Li, Xingchen Dong, Dezan Ji, Landi He, Weidong Zhou","doi":"10.1142/S0129065724500655","DOIUrl":null,"url":null,"abstract":"<p><p>A real-time and reliable automatic detection system for epileptic seizures holds significant value in assisting physicians with rapid diagnosis and treatment of epilepsy. Aiming to address this issue, a novel lightweight model called Convolutional Neural Network-Reformer (CNN-Reformer) is proposed for seizure detection on long-term EEG. The CNN-Reformer consists of two main parts: the Data Reshaping (DR) module and the Efficient Attention and Concentration (EAC) module. This framework reduces network parameters while retaining effective feature extraction of multi-channel EEGs, thereby improving model computational efficiency and real-time performance. Initially, the raw EEG signals undergo Discrete Wavelet Transform (DWT) for signal filtering, and then fed into the DR module for data compression and reshaping while preserving local features. Subsequently, these local features are sent to the EAC module to extract global features and perform categorization. Post-processing involving sliding window averaging, thresholding, and collar techniques is further deployed to reduce the false detection rate (FDR) and improve detection performance. On the CHB-MIT scalp EEG dataset, our method achieves an average sensitivity of 97.57%, accuracy of 98.09%, and specificity of 98.11% at segment-based level, and a sensitivity of 96.81%, along with FDR of 0.27/h, and latency of 17.81 s at the event-based level. On the SH-SDU dataset we collected, our method yielded segment-based sensitivity of 94.51%, specificity of 92.83%, and accuracy of 92.81%, along with event-based sensitivity of 94.11%. The average testing time for 1[Formula: see text]h of multi-channel EEG signals is 1.92[Formula: see text]s. The excellent results and fast computational speed of the CNN-Reformer model demonstrate its potential for efficient seizure detection.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2450065"},"PeriodicalIF":0.0000,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International journal of neural systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1142/S0129065724500655","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/9/30 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

A real-time and reliable automatic detection system for epileptic seizures holds significant value in assisting physicians with rapid diagnosis and treatment of epilepsy. Aiming to address this issue, a novel lightweight model called Convolutional Neural Network-Reformer (CNN-Reformer) is proposed for seizure detection on long-term EEG. The CNN-Reformer consists of two main parts: the Data Reshaping (DR) module and the Efficient Attention and Concentration (EAC) module. This framework reduces network parameters while retaining effective feature extraction of multi-channel EEGs, thereby improving model computational efficiency and real-time performance. Initially, the raw EEG signals undergo Discrete Wavelet Transform (DWT) for signal filtering, and then fed into the DR module for data compression and reshaping while preserving local features. Subsequently, these local features are sent to the EAC module to extract global features and perform categorization. Post-processing involving sliding window averaging, thresholding, and collar techniques is further deployed to reduce the false detection rate (FDR) and improve detection performance. On the CHB-MIT scalp EEG dataset, our method achieves an average sensitivity of 97.57%, accuracy of 98.09%, and specificity of 98.11% at segment-based level, and a sensitivity of 96.81%, along with FDR of 0.27/h, and latency of 17.81 s at the event-based level. On the SH-SDU dataset we collected, our method yielded segment-based sensitivity of 94.51%, specificity of 92.83%, and accuracy of 92.81%, along with event-based sensitivity of 94.11%. The average testing time for 1[Formula: see text]h of multi-channel EEG signals is 1.92[Formula: see text]s. The excellent results and fast computational speed of the CNN-Reformer model demonstrate its potential for efficient seizure detection.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
用于高效癫痫发作检测的轻量级卷积神经网络-重构器模型
一个实时可靠的癫痫发作自动检测系统在协助医生快速诊断和治疗癫痫方面具有重要价值。为了解决这一问题,我们提出了一种名为卷积神经网络-变形器(CNN-Reformer)的新型轻量级模型,用于长期脑电图的癫痫发作检测。CNN-Reformer 由两个主要部分组成:数据重塑(DR)模块和高效注意力与集中(EAC)模块。该框架在减少网络参数的同时,保留了多通道脑电图的有效特征提取,从而提高了模型的计算效率和实时性。最初,原始脑电信号经过离散小波变换(DWT)进行信号过滤,然后送入 DR 模块进行数据压缩和重塑,同时保留局部特征。随后,这些局部特征被传送到 EAC 模块,以提取全局特征并进行分类。后期处理包括滑动窗口平均、阈值和领圈技术,以降低误检率(FDR)并提高检测性能。在 CHB-MIT 头皮脑电图数据集上,我们的方法在基于片段的水平上实现了平均 97.57% 的灵敏度、98.09% 的准确度和 98.11% 的特异性,在基于事件的水平上实现了 96.81% 的灵敏度、0.27/h 的 FDR 和 17.81 秒的延迟。在我们收集的 SH-SDU 数据集上,我们的方法获得了基于分段的灵敏度 94.51%、特异度 92.83%、准确度 92.81%,以及基于事件的灵敏度 94.11%。1[公式:见正文]小时多通道脑电信号的平均测试时间为 1.92[公式:见正文]秒。CNN-Reformer 模型的出色结果和快速计算速度证明了它在高效癫痫发作检测方面的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
A Hardware-Efficient Novelty-Aware Spike Sorting Approach for Brain-Implantable Microsystems. Author Index Volume 34 (2024). Precise Localization for Anatomo-Physiological Hallmarks of the Cervical Spine by Using Neural Memory Ordinary Differential Equation. The 2024 Hojjat Adeli Award for Outstanding Contributions in Neural Systems. Referring Image Segmentation with Multi-Modal Feature Interaction and Alignment Based on Convolutional Nonlinear Spiking Neural Membrane Systems.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1