Epileptic Spike Detection Using Neural Networks with Linear-Phase Convolutions

Epileptic Spike Detection Using Neural Networks with Linear-Phase Convolutions
复制标题

使用具有线性相位卷积的神经网络进行癫痫尖峰检测

DOI:
10.1109/jbhi.2021.3102247
复制
发表时间:
2021
期刊:
IEEE J Biomed Health Inform.
影响因子:
--
通讯作者:
Tanaka T
Tanaka T
中科院分区:
--
文献类型:
--
作者:
Fukumori K;Yoshida N;Sugano H;Nakajima M;Tanaka T

文献摘要

参考文献

被引文献

相似文献

为了科普缺乏高技能专业人员的问题,具有适当信号处理的机器学习是建立自动诊断辅助技术的关键,用于进行癫痫脑电图(EEG)测试。特别是,频率滤波与适当的通带是必不可少的,以提高生物标志物-如癫痫棘波-这是在EEG中指出。本文介绍了一类新的神经网络(NN),在第一层有一个银行的线性相位有限脉冲响应滤波器作为预处理器,可以作为带通滤波器,提取生物标志物,而不破坏波形,因为线性相位条件。此外,滤波器的参数也是数据驱动的。该神经网络采用大量临床脑电数据进行训练,包括50例患者记录的15 833个癫痫棘波波形,并由专家标注其标签。在实验中,我们比较了第一层的三种情况:无预处理、离散小波变换和提出的数据驱动滤波器。实验结果表明,经过监督学习的数据驱动滤波器组具有多带通滤波器的特性。特别地,训练的滤波器通过大约10-30 Hz的频带。此外,所提出的方法检测到癫痫棘波,在50个受试者间验证的平均值为0.967的接收器工作特征曲线下的面积。
To cope with the lack of highly skilled professionals, machine learning with proper signal processing is key for establishing automated diagnostic-aid technologies with which to conduct epileptic electroencephalogram (EEG) testing. In particular, frequency filtering with the appropriate passbands is essential for enhancing the biomarkers—such as epileptic spike waves—that are noted in the EEG. This paper introduces a novel class of neural networks (NNs) that have a bank of linear-phase finite impulse response filters at the first layer as a preprocessor that can behave as bandpass filters that extract biomarkers without destroying waveforms because of a linear-phase condition. Besides, the parameters of the filters are also data-driven. The proposed NNs were trained with a large amount of clinical EEG data, including 15 833 epileptic spike waveforms recorded from 50 patients, and their labels were annotated by specialists. In the experiments, we compared three scenarios for the first layer: no preprocessing, discrete wavelet transform, and the proposed data-driven filters. The experimental results show that the trained data-driven filter bank with supervised learning behaves like multiple bandpass filters. In particular, the trained filter passed a frequency band of approximately 10–30 Hz. Moreover, the proposed method detected epileptic spikes, with the area under the receiver operating characteristic curve of 0.967 in the mean of 50 intersubject validations.
使用小波变换和神经网络检测脑电图信号中的癫痫发作
DOI: 10.1007/978-3-319-06764-3_33
发表时间: 2015
期刊: --
影响因子: --
作者:
E. Juárez;V. Alarcón;P. Gómez
通讯作者: P. Gómez
Lucashn/Peakutils:V1.1.0
DOI: 10.5281/zenodo.887916
发表时间: 2017
期刊: --
影响因子: --
作者:
Lucas Hermann Negri;Christophe Vestri
通讯作者: Christophe Vestri
小波变换脑电图信号分量的能量分布
DOI: --
发表时间: 2012
期刊:
影响因子: --
作者:
I. Omerhodžić;S. Avdakovic;A. Nuhanovic;K. Dizdarevic;K. Rotim
通讯作者: K. Rotim
DOI: 10.1016/s1350-4533(01)00096-0
发表时间: 2001-11-01
影响因子: 2.2
作者:
Gutiérrez, J;Alcántara, R;Medina, V
通讯作者: Medina, V
使用小波变换提取脑电信号特征进行自闭症分类
DOI: --
发表时间: 2015
影响因子: --
作者:
Chuin Cheong Lung;R. Sudirman;S. S. Hussin
通讯作者: S. S. Hussin