Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Apr 25;41(2):253-261.
doi: 10.7507/1001-5515.202307030.

[Automatic epilepsy detection with an attention-based multiscale residual network]

[Article in Chinese]
Xingqi Wang  1 , Ming'ai Li  1   2   3
Affiliations

[Automatic epilepsy detection with an attention-based multiscale residual network]

[Article in Chinese]
Xingqi Wang et al. Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. .

Abstract
in English, Chinese

The deep learning-based automatic detection of epilepsy electroencephalogram (EEG), which can avoid the artificial influence, has attracted much attention, and its effectiveness mainly depends on the deep neural network model. In this paper, an attention-based multi-scale residual network (AMSRN) was proposed in consideration of the multiscale, spatio-temporal characteristics of epilepsy EEG and the information flow among channels, and it was combined with multiscale principal component analysis (MSPCA) to realize the automatic epilepsy detection. Firstly, MSPCA was used for noise reduction and feature enhancement of original epilepsy EEG. Then, we designed the structure and parameters of AMSRN. Among them, the attention module (AM), multiscale convolutional module (MCM), spatio-temporal feature extraction module (STFEM) and classification module (CM) were applied successively to signal reexpression with attention weighted mechanism as well as extraction, fusion and classification for multiscale and spatio-temporal features. Based on the Children's Hospital Boston-Massachusetts Institute of Technology (CHB-MIT) public dataset, the AMSRN model achieved good results in sensitivity (98.56%), F1 score (98.35%), accuracy (98.41%) and precision (98.43%). The results show that AMSRN can make good use of brain network information flow caused by seizures to enhance the difference among channels, and effectively capture the multiscale and spatio-temporal features of EEG to improve the performance of epilepsy detection.

基于深度学习的癫痫脑电自动检测方法，能避免人为因素的影响而倍受关注，而其有效性主要取决于深度神经网络模型。为此，本研究将根据癫痫脑电的多尺度、时空特点及导联间的信息流动特征，设计一种基于注意力的多尺度残差网络（AMSRN），并与多尺度主元分析法（MSPCA）相结合，实现癫痫的自动检测。首先，利用MSPCA对原始癫痫脑电信号进行去噪和特征增强；进而，设计AMSRN模型结构与参数。其中，注意力模块（AM）、多尺度卷积模块（MCM）、时空特征提取模块（STFEM）和分类模块（CM）相继完成基于注意力加权机制的信号重表达以及多尺度-时空特征的提取、融合与分类。基于麻省理工学院的波士顿儿童医院（CHB-MIT）公共数据集进行5折交叉验证实验研究，AMSRN模型在灵敏度（98.56%）、F1分数（98.35%）、准确度（98.41%）及精确度（98.43%）等方面均取得了较好结果。结果表明，AMSRN模型能够很好地利用癫痫发作引起的脑网络信息流动强化导联间差异性，并有效捕获癫痫脑电的多尺度和时空特征，有利于改善癫痫检测性能。.

Keywords: Brain networks; Deep learning; Electroencephalogram signal; Multi-scale principal component analysis (MSPCA); Seizure detection.

PubMed Disclaimer

Conflict of interest statement

利益冲突声明：本文全体作者均声明不存在利益冲突。

Figures

图 1
图 1
AMSRN model structure AMSRN模型结构
图 2
图 2
Experimental results of denoising based on MSPCA 基于MSPCA的去噪实验结果
图 3
图 3
Experimental results of model ablation 模型消融实验结果
图 4
图 4
Amplitude characteristics of the attention layer under different periods of epilepsy 癫痫不同时期下的注意力层的幅值特征
图 5
图 5
Amplitude characteristics of the scale feature layer under different periods of epilepsy 癫痫不同时期的尺度特征层的幅值特征
图 6
图 6
Amplitude characteristics of the spatio-temporal feature layer under different periods of epilepsy 癫痫不同时期时空特征层的幅值特征
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. 张瑞, 宋江玲, 胡文凤 癫痫脑电的特征提取方法综述. 西北大学学报(自然科学版) 2016;46(6):781–788,794.
    1. Sharma R, Pachori R B Classification of epileptic seizures in EEG signals based on phase space representation of intrinsic mode functions. Expert Syst Appl. 2015;42(3):1106–1117.
    1. Zabihi M, Kiranyaz S, Jäntti V, et al Patient-specific seizure detection using nonlinear dynamics and nullclines. IEEE J Biomed Health Inform. 2019;24(2):543–555. - PubMed
    1. Jaffino G, Jose J P, Kumar K S Expectation-maximization extreme machine learning classifier for epileptic seizure detection// 2021 International Conference on Forensics, Analytics, Big Data, Security (FABS) Bengaluru: IEEE. 2021;1:1–5.
    1. 徐嘉阳, 杨婷婷, 李雯, 等 基于自适应多尺度脑功能连接的局灶性癫痫发作检测方法研究. 中国生物医学工程学报. 2022;41(4):393–401.

Publication types