卷积神经网络在癫痫脑电图分析中的应用进展:从发作检测到临床智能分析

doi:10.19854/j.cnki.1008-2425.2026.03.0009

摘要/Abstract

摘要： 癫痫是一种常见的神经系统疾病,全球患者已超过5000万。脑电图(Electroencephalography,EEG)因具有高时间分辨率和无创性,在癫痫的辅助诊断、发作检测及发作预测中发挥着重要作用。但EEG信号具有非平稳性、易受伪影干扰且数据规模庞大,临床判读依赖经验,限制了其分析效率。随着深度学习的发展,卷积神经网络(Convolutional neural network,CNN)因具备自动特征提取能力,逐渐应用于癫痫脑电分析,并在发作检测、预测及耐药性评估等任务中取得良好效果。本文系统综述CNN在癫痫EEG分析中的研究进展,重点梳理数据预处理与特征提取方法,并分析当前在数据集质量、模型泛化能力、可解释性及临床转化方面存在的主要问题。在此基础上,对多中心数据整合、多模态融合、轻量化模型设计及可解释人工智能的发展方向进行了讨论。

关键词: 癫痫, 卷积神经网络, 脑电图分析, 发作检测, 发作预测

中图分类号:

R742.1

张鹏飞, 杨瑞金. 卷积神经网络在癫痫脑电图分析中的应用进展:从发作检测到临床智能分析[J]. 立体定向和功能性神经外科杂志, 2026, 39(3): 186-192.

参考文献

[1] Saxena S,Li SC.Defeating epilepsy:A global public health commitment[J].Epilepsia Open,2017,2(2):153-155.
[2] Fisher R S,Acevedo C,Arzimanoglou A,et al.ILAE official report:a practical clinical definition of epilepsy[J].Epilepsia,2014,55(4):475-482.
[3] Scheffer I E,Berkovic S,Capovilla G,et al.ILAE classification of the epilepsies:position paper of the ILAE Commission for Classification and Terminology[J].J Jpn Epilepsy Soc,2019,37(1):6-14.
[4] Thijs R D,Surges R,O’Brien TJ,et al.Epilepsy in adults[J].Lancet,2019,393(10172):689-701.
[5] Ein Shoka A A,Dessouky MM,El-Sayed A,et al.EEG seizure detection:concepts,techniques,challenges,and future trends[J].Multimed Tools Appl,2023,82(27):42021-42051.
[6] Cao XS,Zheng SJ,Zhang JC,et al.A hybrid CNN-Bi-LSTM model with feature fusion for accurate epilepsy seizure detection[J].BMC Med Inform Decis Mak,2025,25:6.
[7] Tveit J,Aurlien H,Plis S,et al.Automated interpretation of clinical electroencephalograms using artificial intelligence[J].JAMA Neurol,2023,80(8):805-812.
[8] Lisgaras C P,De la Prida L M,Bertram E,et al.The role of electroencephalography in epilepsy research-from seizures to interictal activity and comorbidities[J].Epilepsia,2025,66(5):1374-1393.
[9] Kadam S D,D’Ambrosio R,Duveau V,et al.Methodological standards and interpretation of video- electroencephalography in adult control rodents.A TASK1-WG1 report of the AES/ILAE translational task force of the ILAE[J].Epilepsia,2017,58(Suppl 4):10-27.
[10] Hubel DH,Wiesel TN.Receptive fields,binocular interaction and functional architecture in the cat’s visual cortex[J]. J Physiol,1962,160(1):106-154.
[11] Fukushima K.Neocognitron:A self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J].Biol Cybern,1980,36(4):193-202.
[12] Voulodimos A,Doulamis N,Doulamis A,et al.Deep learning for computer vision:a brief review[J].Comput Intell Neurosci,2018,2018:7068349.
[13] Lecun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J].Proc IEEE,1998,86(11):2278-2324.
[14] Krizhevsky A,Sutskever I,Hinton G E.ImageNet classification with deep convolutional neural networks[J].Commun.ACM,2017,60(6):84-90.
[15] Simonyan K,Zisserman A.Very deep convolutional networks for large-scale image recognition[M].arXiv,2015.
[16] Shafiq M,Gu Z.Deep residual learning for image recognition:a survey[J].Applied Sciences,2022,12(18):8972.
[17] Roy Y,Banville H,Albuquerque I,et al.Deep learning-based electroencephalography analysis:a systematic review[J].J Neural Eng,2019,16(5):51001.
[18] Mormann F,Lehnertz K,David P,et al.Mean phase coherence as a measure for phase synchronization and its application to the EEG of epilepsy patients[J].Phys D:Nonlinear Phenom,2000,144(3-4):358-369.
[19] Delorme A,Makeig S.EEGLAB:an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis[J].J Neurosci Meth,2004,134(1):9-21.
[20] Teng C L,Zhang Y Y,Wang W,et al.A novel method based on combination of independent component analysis and ensemble empirical mode decomposition for removing electrooculogram artifacts from multichannel electroencephalogram signals[J].Front Neurosci,2021,15:729403.
[21] Ravi S,Radhakrishnan A.A hybrid 1D CNN-BiLSTM model for epileptic seizure detection using multichannel EEG feature fusion[J].Biomed Phys Eng Express,2024,10(3):035040.
[22] Truong N D,Nguyen A D,Kuhlmann L,et al.Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram[J].Neural Networks,2018,105:104-111.
[23] Shen MK,Yang F,Wen P,et al.A real-time epilepsy seizure detection approach based on EEG using short-time fourier transform and Google-net convolutional neural network[J].Heliyon,2024,10(11):e31827.
[24] Wei BX,Xu L,Zhang JC.A compact graph convolutional network with adaptive functional connectivity for seizure prediction[J].IEEE Trans Neural Syst Rehabil Eng,2024,32:3531-3542.
[25] Wan ST,Dong F,Zhang X,et al.Fault voiceprint signal diagnosis method of power transformer based on mixup data enhancement[J].Sensors,2023,23(6):3341.
[26] Ru YD,Wei Z,An GY,et al.Combining data augmentation and deep learning for improved epilepsy detection[J].Front Neurol,2024,15:1378076.
[27] Kwan P,Arzimanoglou A,Berg A T,et al.Definition of drug resistant epilepsy:consensus proposal by the ad hoc task force of the ILAE commission on therapeutic strategies[J].Epilepsia,2010,51(6):1069-1077.
[28] Yang SJ,Li SS,Wang HL,et al.Early prediction of drug-resistant epilepsy using clinical and EEG features based on convolutional neural network[J].Seizure:Eur J Epilepsy,2024,114:98-104.
[29] Gong YW,Zhang Z,Yang YZ,et al.Prediction of pharmacoresistance in drug-naïve temporal lobe epilepsy using ictal EEGs based on convolutional neural network[J].Neurosci Bull,2025,41(5):791-804.
[30] 努尔比亚·阿不拉江,阿地力江·阿布力米提,祖木来提·司马义,等.脑电图信号多维度特性分析在癫痫病发作预测中的应用[J].生命科学仪器,2024,22(1):11-13.
[31] Zhang Y,Guo Y,Yang P,et al.Epilepsy seizure prediction on EEG using common spatial pattern and convolutional neural network[J].IEEE J Biomed Health Inform,2020,24(2):465-474.
[32] Liu S,Wang J,Li SS,et al.Multi-dimensional hybrid bilinear CNN-LSTM models for epileptic seizure detection and prediction using EEG signals[J].J Neural Eng,2024,21(6):066045.
[33] Zhang YF,Xiao TT,Wang ZW,et al.Hybrid network for patient-specific seizure prediction from EEG data[J].Int J Neur Syst,2023,33(11):2350056.
[34] Zhang F,Zhang BY,Guo SY,et al.MFCC-CNN:A patient-independent seizure prediction model[J].Neurol Sci,2024,45(12):5897-5908.
[35] Yang Y,Luan TY,Yu ZJ,et al.Technological vanguard:the outstanding performance of the LTY-CNN model for the early prediction of epileptic seizures[J].J Transl Med,2024,22(1):162.
[36] Bandarabadi M,Rasekhi J,Teixeira CA,et al.On the proper selection of preictal period for seizure prediction[J].Epilepsy Behav,2015,46:158-166.
[37] Huang ZT,Yang YY,Ma YH,et al.EEG detection and recognition model for epilepsy based on dual attention mechanism[J].Sci Rep,2025,15(1):9404.
[38] 于永强,刘健,孙仁诚,等.基于多特征多关系图卷积神经网络的癫痫脑电分类[J].中国医学物理学杂志,2023,40(5):595-601.
[39] Chen WN,Wang YX,Ren YH,et al.An automated detection of epileptic seizures EEG using CNN classifier based on feature fusion with high accuracy[J].BMC Med Inform Decis Mak,2023,23(1):96.
[40] Tjoa E,Guan CT.A survey on explainable artificial intelligence (XAI):toward medical XAI[J].IEEE Trans Neural Networks Learning Syst,2021,32(11):4793-4813.
[41] Linardatos P,Papastefanopoulos V,Kotsiantis S.Explainable AI:a review of machine learning interpretability methods[J].Entropy,2020,23(1):18.