CNN-based classification of epileptic states for seizure prediction using combined temporal and spectral features

被引:28
作者
Assali, Ines [1 ,2 ]
Blaiech, Ahmed Ghazi [1 ,3 ]
Ben Abdallah, Asma [1 ,4 ]
Ben Khalifa, Khaled [1 ]
Carrere, Marcel [5 ]
Bedoui, Mohamed Hedi [1 ]
机构
[1] Fac Medecine Monastir, Lab Technol & Imagerie Medicale, Monastir 5019, Tunisia
[2] Univ Monastir, Fac Sci Monastir, Monastir 1002, Tunisia
[3] Inst Super Sci Appl & Technol Sousse, Monastir 4003, Tunisia
[4] Univ Monastir, Inst Super informat & Math, Monastir 5019, Tunisia
[5] Marseille Univ, Inst Neurosci Syst, Fac Med, Inserm UMR1106 Aix, 27 Blvd Jean Moulin, F-13005 Marseille, France
关键词
Epileptic state classification; Stability index; EEG signal; Deep learning; EEG; NETWORK; SIGNALS;
D O I
10.1016/j.bspc.2022.104519
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Reliable prediction of epileptic seizures is of paramount importance in reducing the serious consequences of seizures by detecting their onset and warning patients early enough to take prompt and effective intervention measures, thereby ensuring the safety of patients who cannot be treated with pharmaceutical treatments or surgery. Indeed, the classification of epileptic states by deep learning methods based on electroencephalography (EEG) signals has attracted much attention in recent years. Nevertheless, the performance of classification of these states is strongly related to the preprocessing phase. The study of stability and detection of transitions between epileptic states is paramount to improve prediction algorithms. In this work, a stability index (SI) based on multivariate autoregressive modeling, capable of quantifying the phenomena observed during transitions between epileptic states and indicating the stability state of the epileptic neural system, is computed and fed to a convolutional neural network model among other known features in order to improve the learning performance of high-level features of the EEG signal and thus the classification of epileptic states. The experimental results highlight that the integration of the SI can stabilize the implemented learning model, satisfactorily improve the classification of epileptic states and permit our model to be competitive, based on many performance measures, to the state-of-the-art studies. Regarding the distinction between preictal and interictal states, our proposed model achieved an average accuracy of 90.1% to 94.5% and an average sensitivity of 88.6% to 92.8% for preictal interval durations of 30 and 60 min, respectively, on the CHB-MIT data set.
引用
收藏
页数:11
相关论文
共 38 条
[1]  
Abbaszadeh B, 2019, IEEE ENG MED BIO, P3442, DOI [10.1109/EMBC.2019.8856286, 10.1109/embc.2019.8856286]
[2]   AUTOMATIC IDENTIFICATION OF EPILEPTIC EEG SIGNALS USING NONLINEAR PARAMETERS [J].
Acharya, U. Rajendra ;
Chua, Chua Kuang ;
Lim, Teik-Cheng ;
Dorithy ;
Suri, Jasjit S. .
JOURNAL OF MECHANICS IN MEDICINE AND BIOLOGY, 2009, 9 (04) :539-553
[3]   Epileptic Seizure Prediction Using CSP and LDA for Scalp EEG Signals [J].
Alotaiby, Turky N. ;
Alshebeili, Saleh A. ;
Alotaibi, Faisal M. ;
Alrshoud, Saud R. .
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2017, 2017
[4]   Interpretation of Entropy Algorithms in the Context of Biomedical Signal Analysis and Their Application to EEG Analysis in Epilepsy [J].
Amarantidis, Lampros Chrysovalantis ;
Abasolo, Daniel .
ENTROPY, 2019, 21 (09)
[5]   Multivariate autoregressive models for classification of spontaneous electroencephalographic signals during mental tasks [J].
Anderson, CW ;
Stolz, EA ;
Shamsunder, S .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 1998, 45 (03) :277-286
[6]  
Anwar A., 2015, IOSR Journal of Computer Engineering, V17, P47
[7]   Comparison by multivariate auto-regressive method of seizure prediction for real patients and virtual patients [J].
Assali, Ines ;
Jlassi, Ines ;
Aissi, Mouna ;
Blaiech, Ahmed Ghazi ;
Carrere, Marcel ;
Bedoui, Mohamed Hedi .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2021, 68
[8]  
Bengio Y., 2007, LARGE SCALE KERNEL M
[9]   Hilbert Vibration Decomposition-based epileptic seizure prediction with neural network [J].
Buyukcakir, Barkin ;
Elmaz, Furkan ;
Mutlu, Ali Yener .
COMPUTERS IN BIOLOGY AND MEDICINE, 2020, 119
[10]   EEG-Based Prediction of Epileptic Seizures Using Phase Synchronization Elicited from Noise-Assisted Multivariate Empirical Mode Decomposition [J].
Cho, Dongrae ;
Min, Beomjun ;
Kim, Jongin ;
Lee, Boreom .
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2017, 25 (08) :1309-1318