一维卷积神经网络的自编码癫痫发作异常检测模型  

An autoencoder model based on one-dimensional neural network for epileptic EEG anomaly detection

作　　者：欧嘉志 詹长安[1] 杨丰[1] OU Jiazhi;ZHAN Chang'an;YANG Feng(School of Biomedical Engineering,Southern Medical University,Guangzhou 510515,China)

机构地区：[1]南方医科大学生物医学工程学院,广东广州510515

出　　处：《南方医科大学学报》2024年第9期1796-1804,共9页Journal of Southern Medical University

基　　金：国家自然科学基金(61771233)。

摘　　要：目的将一维卷积神经网络(1DCNN)作为自编码模型的特征提取网络,利用1DCNN对头皮脑电信号(EEG)局部特征的感知能力来提高自编码模型(AE)在低维特征空间的表达能力,提出一种简单高效的癫痫异常检测模型。方法癫痫发作后会出现标志性的EEG波形变化,通过1DCNN的局部特征提取能力,捕捉正常信号的局部信息;利用正常数据训练自编码器,学习正常EEG数据在低维特征空间的表达,作为异常数据的癫痫EEG数据会脱离正常数据的低维特征空间,从而自编码模型无法有效地实现癫痫异常信号的重构;首先将输入和输出的差值作为异常分数值,然后通过ROC曲线的最优平衡点确定阈值,超过阈值的EEG信号被诊断为癫痫发作数据。利用公开数据集CHB-MIT脑电数据集和TUH脑电数据集,评估本文所提出的1DCNN-AE癫痫检测模型。结果从AUC值和癫痫事件检测两个任务来看,1DCNN-AE模型在患者平均水平下的AUC值分别达到了CHB-MIT的0.890和TUH的0.686,癫痫检测率达到了0.974和0.893,其结果优于最新癫痫异常检测模型LSTM-VAE和模型GRU-VAE。对于模型参数量而言,与LSTM-VAE的47.4M和GRU-VAE的36.9M等模型参数量相比,1DCNN模型的参数量Params达到了58.5M,处于同一个量级;但1DCNN-AE模型计算量FLOPs为0.377G,远远小于LSTM-VAE的21.6G和GRU-VAE的16.2G。结论1DCNN的自编码模型能有效地实现癫痫发作异常检测。Objective We propose an autoencoder model based on a one-dimensional convolutional neural network(1DCNN)as the feature extraction network for efficient detection of epileptic EEG anomalies.Methods The local information of normal EEG signals was captured by utilizing the local feature extraction ability of 1DCNN for training of an autoencoder to learn the expression of normal EEG data in low dimensional feature space.With the difference between the input and output as the anomaly score,the threshold was determined by the optimal equilibrium point of the ROC curve,and the EEG signals exceeding the threshold were diagnosed as the seizure data.The performance of the 1DCNN-AE epilepsy detection model was evaluated using the publicly available CHB-MIT scalp EEG dataset and TUH scalp EEG dataset.Results The AUC of the 1DCNN-AE model reached 0.890 of CHB-MIT and 0.686 of TUH under the average level of patients,and the epilepsy detection rate reached 0.974 and 0.893,and these results were better than the latest epilepsy anomaly detection models LSTM-VAE and GRU-VAE.The 1DCNN model had a parameter quantity of 58.5M,which was at the same level with LSTM-VAE(47.4 M)and GRU-VAE(36.9 M)but with much smaller FLOPs(0.377 G)than LSTM-VAE(21.6 G)and GRU-VAE(16.2 G).Conclusion The autoencoder model based one-dimensional convolutional neural network can effectively detect abnormal EEG signals in epileptic seizure.

关 键 词：自编码器 深度学习 癫痫检测 异常检测 一维卷积神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] R742.1[自动化与计算机技术—控制科学与工程]