当前位置: X-MOL 学术Int. J. Neural Syst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Epileptic EEG Classification by Using Time-Frequency Images for Deep Learning
International Journal of Neural Systems ( IF 6.6 ) Pub Date : 2021-05-26 , DOI: 10.1142/s012906572150026x
Mehmet Akif Ozdemir 1 , Ozlem Karabiber Cura 1 , Aydin Akan 2
Affiliation  

Epilepsy is one of the most common brain disorders worldwide. The most frequently used clinical tool to detect epileptic events and monitor epilepsy patients is the EEG recordings. There have been proposed many computer-aided diagnosis systems using EEG signals for the detection and prediction of seizures. In this study, a novel method based on Fourier-based Synchrosqueezing Transform (SST), which is a high-resolution time-frequency (TF) representation, and Convolutional Neural Network (CNN) is proposed to detect and predict seizure segments. SST is based on the reassignment of signal components in the TF plane which provides highly localized TF energy distributions. Epileptic seizures cause sudden energy discharges which are well represented in the TF plane by using the SST method. The proposed SST-based CNN method is evaluated using the IKCU dataset we collected, and the publicly available CHB-MIT dataset. Experimental results demonstrate that the proposed approach yields high average segment-based seizure detection precision and accuracy rates for both datasets (IKCU: 98.99% PRE and 99.06% ACC; CHB-MIT: 99.81% PRE and 99.63% ACC). Additionally, SST-based CNN approach provides significantly higher segment-based seizure prediction performance with 98.54% PRE and 97.92% ACC than similar approaches presented in the literature using the CHB-MIT dataset.

中文翻译:

使用时频图像进行深度学习的癫痫脑电图分类

癫痫是全世界最常见的脑部疾病之一。检测癫痫事件和监测癫痫患者最常用的临床工具是脑电图记录。已经提出了许多使用 EEG 信号来检测和预测癫痫发作的计算机辅助诊断系统。在这项研究中,提出了一种基于傅里叶同步压缩变换(SST)的新方法,它是一种高分辨率的时频(TF)表示,以及卷积神经网络(CNN)来检测和预测癫痫发作片段。SST 基于 TF 平面中信号分量的重新分配,提供高度局部化的 TF 能量分布。癫痫发作导致突然的能量放电,使用 SST 方法在 TF 平面中很好地表现出来。使用我们收集的 IKCU 数据集和公开可用的 CHB-MIT 数据集对所提出的基于 SST 的 CNN 方法进行评估。实验结果表明,所提出的方法对两个数据集(IKCU:98.99% PRE 和 99.06% ACC;CHB-MIT:99.81% PRE 和 99.63% ACC)产生了较高的基于分段的平均癫痫检测精度和准确率。此外,与文献中使用 CHB-MIT 数据集的类似方法相比,基于 SST 的 CNN 方法提供了显着更高的基于片段的癫痫发作预测性能,具有 98.54% 的 PRE 和 97.92% 的 ACC。81% PRE 和 99.63% ACC)。此外,与文献中使用 CHB-MIT 数据集的类似方法相比,基于 SST 的 CNN 方法提供了显着更高的基于片段的癫痫发作预测性能,具有 98.54% 的 PRE 和 97.92% 的 ACC。81% PRE 和 99.63% ACC)。此外,与文献中使用 CHB-MIT 数据集的类似方法相比,基于 SST 的 CNN 方法提供了显着更高的基于片段的癫痫发作预测性能,具有 98.54% 的 PRE 和 97.92% 的 ACC。
更新日期:2021-05-26
down
wechat
bug