Volume 19, Issue 4 (3-2023)
JSDP 2023, 19(4): 149-172 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Tajadini B, Seydnejad S, Rezakhani S. Prediction of Epileptic Seizures in Patients with Temporal Lobe Epilepsy (TLE) based on Cepstrum analysis and AR model of EEG signal. JSDP 2023; 19 (4) : 11
URL: http://jsdp.rcisp.ac.ir/article-1-1177-en.html
URL: http://jsdp.rcisp.ac.ir/article-1-1177-en.html
Abstract: (1036 Views)
Epilepsy is a chronic disorder of brain function caused by abnormal and excessive electrical neurons discharge in the brain. Seizures cause disturbances in consciousness that occur without prior notice, so their prediction ability, based on EEG data, can reduce stress and improve quality of life. An epileptic patient EEG data consists of five parts: Ictal, Inter-Ictal, pre-Ictal, Post-Ictal, and IT (seconds before Ictal onset). The purpose of predicting an attack is to detect the period of pre-ictal or IT to create warnings for medical procedures that are actually determined hours or minutes before ictal and do not necessarily mean the exact time of ictal [4]. The aim of many studies has been to identify the pre-ictal period based on EEG data. However, the problem of reliable prediction of epileptic seizures remains largely unsolved [5].
EEG and IEEG data types are used in detection and predicting methods. Due to the fact that artifacts and noises have a greater effect on EEG than IEEG, if there is IEEG, it has been tried to use it [6, 7]. Seizure warning methods that have a clinical application are generally based on the use on EEG [8].
Numerous studies have been performed to detect and predict seizures. The methods of signal processing and feature extraction are same in detection and prediction, but the difference is that, in detection, ictal and inter-ictal periods are compared, while in prediction, pre-ictal or IT and inter-ictal periods are being compared. Some algorithms use data modeling to extract features. References [13, 14], the coefficients AR model for the EEG data is obtained with least squares estimator, then the model coefficients are classified by SVM binary classification. In the article [15] the non-Gaussian EEG is considered using the ARIMA model (Autoregressive integrated moving average). In references [16, 17], predictions are performed based on the dynamic model with hidden variable and the sparse LVAR model, respectively. Also other features such as Mean Phase Coherency [18-20], Lag Synchronization Index to compare phase Synchronization between irregular oscillations [8,21], eigenspectra of space-delay correlation and covariance matrices [22], Largest Lyapunov Exponent [23, 25], decorrelation time, Hjorth parameters such as mobility and complexity, power spectrum in frequency bands, spectral edge frequency, the four statistical moments: mean, variance, kurtosis, skewness and there are features based on entropy and probability [6, 26-29]. Empirical mode decomposition (EMD) and wavelet transform methods have also been used to extract the feature [2, 30, 31, 37]. In articles [32, 33], the Cepstrum method has been used on short time multi channels EEG and IEEG in different patient states. Cepstrum is used to extract slow and periodic changes in speech that can be used to detect the ictal period from the inter-ictal, and has also been used to linearize the EEG [34]. In the paper [33], Cepstrum coefficients of multi-channel EEG are calculated and the 9 first coefficients are considered, then calculates the velocity and acceleration of the desired coefficients and uses a neural network to detect an epileptic seizure. The method of this paper was improved in 2014. In this way, first the signal energy and coefficients of Cepstrum are calculated and then the same process is followed. The accuracy values of velocity and acceleration coefficients in this study were 89.7% - 98.7% and 98.9% - 99.9%, respectively [32].
In this study, the period of IT was detected in patients with temporal lobe epilepsy (TLE), which is the most common type of epilepsy [38]. For this purpose, two long term EEG channels LTM (long term monitoring) with a sampling rate 256, which are facing each other have been used. First, the desired signal is considered by the moving window with a length if 5 seconds and 80% overlap. The desired signal is normalized and its linear trend is removed and band-pass filtered (220 order FIR filter, cutoff at 6-20 Hz). Then the filtered date will de decomposed using discrete wavelet transform with 6-levels and Daubechies4 mother wavelet. In this step we will have 12 outputs. Next, by windowing of 500 samples and 75% overlap, the AR model with 8 order is applied to outputs. Cepstrum method can be used to detect regular and periodic changes in the ictal period of the EEG signal. According to this feature, the Cepstrum coefficients of the data window are calculated and the first coefficient of each window is considered. By applying a median filter to the 12 outputs of the previous stage, the current period of the first channel is compared to the background period of the same channel and the second channel, and the same is done for the second channel. This method reduces artifact error and inter-attack discharges. Finally, the signal is averaged by the moving window and the positive envelope of the curve is calculated. Given that we will eventually have 12 outputs, 12 threshold values are obtained for a patient’s training data, then these values are checked on the test data.
The proposed method was reviewed on a proposed model of adult epilepsy as well as 10 patients with long-term EEG data without artifact removal. Accuracy and average prediction time were 92% and 18.5 seconds, respectively. The algorithm performed better than other methods. Another advantage of the algorithm is the ability to reduce artifacts, while many studies have used short-term data without artifacts. Artifacts are located at different frequencies, which frequency analysis is performed by wavelet transform. Because two channel artifacts are unequal at the same time and in the same channel at different times, the artifacts are reduced by comparing the channels to each other. Algorithm testing on more patients is recommended to confirm the performance of the algorithm clinically.
EEG and IEEG data types are used in detection and predicting methods. Due to the fact that artifacts and noises have a greater effect on EEG than IEEG, if there is IEEG, it has been tried to use it [6, 7]. Seizure warning methods that have a clinical application are generally based on the use on EEG [8].
Numerous studies have been performed to detect and predict seizures. The methods of signal processing and feature extraction are same in detection and prediction, but the difference is that, in detection, ictal and inter-ictal periods are compared, while in prediction, pre-ictal or IT and inter-ictal periods are being compared. Some algorithms use data modeling to extract features. References [13, 14], the coefficients AR model for the EEG data is obtained with least squares estimator, then the model coefficients are classified by SVM binary classification. In the article [15] the non-Gaussian EEG is considered using the ARIMA model (Autoregressive integrated moving average). In references [16, 17], predictions are performed based on the dynamic model with hidden variable and the sparse LVAR model, respectively. Also other features such as Mean Phase Coherency [18-20], Lag Synchronization Index to compare phase Synchronization between irregular oscillations [8,21], eigenspectra of space-delay correlation and covariance matrices [22], Largest Lyapunov Exponent [23, 25], decorrelation time, Hjorth parameters such as mobility and complexity, power spectrum in frequency bands, spectral edge frequency, the four statistical moments: mean, variance, kurtosis, skewness and there are features based on entropy and probability [6, 26-29]. Empirical mode decomposition (EMD) and wavelet transform methods have also been used to extract the feature [2, 30, 31, 37]. In articles [32, 33], the Cepstrum method has been used on short time multi channels EEG and IEEG in different patient states. Cepstrum is used to extract slow and periodic changes in speech that can be used to detect the ictal period from the inter-ictal, and has also been used to linearize the EEG [34]. In the paper [33], Cepstrum coefficients of multi-channel EEG are calculated and the 9 first coefficients are considered, then calculates the velocity and acceleration of the desired coefficients and uses a neural network to detect an epileptic seizure. The method of this paper was improved in 2014. In this way, first the signal energy and coefficients of Cepstrum are calculated and then the same process is followed. The accuracy values of velocity and acceleration coefficients in this study were 89.7% - 98.7% and 98.9% - 99.9%, respectively [32].
In this study, the period of IT was detected in patients with temporal lobe epilepsy (TLE), which is the most common type of epilepsy [38]. For this purpose, two long term EEG channels LTM (long term monitoring) with a sampling rate 256, which are facing each other have been used. First, the desired signal is considered by the moving window with a length if 5 seconds and 80% overlap. The desired signal is normalized and its linear trend is removed and band-pass filtered (220 order FIR filter, cutoff at 6-20 Hz). Then the filtered date will de decomposed using discrete wavelet transform with 6-levels and Daubechies4 mother wavelet. In this step we will have 12 outputs. Next, by windowing of 500 samples and 75% overlap, the AR model with 8 order is applied to outputs. Cepstrum method can be used to detect regular and periodic changes in the ictal period of the EEG signal. According to this feature, the Cepstrum coefficients of the data window are calculated and the first coefficient of each window is considered. By applying a median filter to the 12 outputs of the previous stage, the current period of the first channel is compared to the background period of the same channel and the second channel, and the same is done for the second channel. This method reduces artifact error and inter-attack discharges. Finally, the signal is averaged by the moving window and the positive envelope of the curve is calculated. Given that we will eventually have 12 outputs, 12 threshold values are obtained for a patient’s training data, then these values are checked on the test data.
The proposed method was reviewed on a proposed model of adult epilepsy as well as 10 patients with long-term EEG data without artifact removal. Accuracy and average prediction time were 92% and 18.5 seconds, respectively. The algorithm performed better than other methods. Another advantage of the algorithm is the ability to reduce artifacts, while many studies have used short-term data without artifacts. Artifacts are located at different frequencies, which frequency analysis is performed by wavelet transform. Because two channel artifacts are unequal at the same time and in the same channel at different times, the artifacts are reduced by comparing the channels to each other. Algorithm testing on more patients is recommended to confirm the performance of the algorithm clinically.
Article number: 11
Keywords: Epileptic Seizure Prediction, Temporal Lobe Epilepsy, Wavelet Transform, AR Model, Cepstrum, Median Filter, Positive Envelope of the Curve, Adult Epileptic Model.
Type of Study: Research |
Subject:
Paper
Received: 2020/09/19 | Accepted: 2022/09/24 | Published: 2023/03/20 | ePublished: 2023/03/20
Received: 2020/09/19 | Accepted: 2022/09/24 | Published: 2023/03/20 | ePublished: 2023/03/20
References
1. [1] S. Engelborghs, R. D'hooge, and P. De Deyn, "Pathophysiology of epilepsy," Acta neurologica belgica, vol.100, pp. 201-213, .2000
2. [2] E. Alickovic, J. Kevric, and A. Subasi, "Performance evaluation of empirical mode decomposition, discrete wavelet transform, and wavelet packed decomposition for automated epileptic seizure detection and prediction," Biomedical signal processing and control, vol. 39, pp. 94-102, .2018 [DOI:10.1016/j.bspc.2017.07.022]
3. [3] E. B. Assi, D. K. Nguyen, S. Rihana, and M. Sawan, "Towards accurate prediction of epileptic seizures: A review," Biomedical Signal Processing and Control, vol. 34, pp. 144-157, .2017 [DOI:10.1016/j.bspc.2017.02.001]
4. [4] H. O. Luders, "Textbook of epilepsy surgery: CRC Press", 2008 [DOI:10.3109/9780203091708]
5. [5] A. S. Zandi, R. Tafreshi, M. Javidan, and G. A. Dumont, "Predicting epileptic seizures in scalp EEG based on a variational Bayesian Gaussian mixture model of zero-crossing intervals," IEEE Transactions on Biomedical Engineering, vol. 60, pp. 1401-1413, 2013. [DOI:10.1109/TBME.2012.2237399] [PMID]
6. [6] C. Teixeira, B. Direito, H. Feldwisch-Drentrup, M. Valderrama, R. Costa, C. Alvarado-Rojas, et al., "EPILAB: A software package for studies on the prediction of epileptic seizures," Journal of Neuroscience Methods, vol. 200, pp. 257-271, .2011 [DOI:10.1016/j.jneumeth.2011.07.002] [PMID]
7. [7] H. G. Daoud, A. M. Abdelhameed, and M. Bayoumi, "Automatic epileptic seizure detection based on empirical mode decomposition and deep neural network," in 2018 IEEE 14th International Colloquium on Signal Processing & Its Applications (CSPA), pp. 182-186, 2018 [DOI:10.1109/CSPA.2018.8368709]
8. [8] M. Winterhalder, B. Schelter, T. Maiwald, A. Brandt, A. Schad, A. Schulze-Bonhage, et al., "Spatio-temporal patient-individual assessment of synchronization changes for epileptic seizure prediction," Clinical neurophysiology, vol. 117, pp. 2399-2413, .2006 [DOI:10.1016/j.clinph.2006.07.312] [PMID]
9. [9] C. Guerrero-Mosquera, A. M. Trigueros, and A. Navia-Vazquez, "EEG signal processing for epilepsy," in Epilepsy-Histological, electroencephalographic and psychological aspects, ed: IntechOpen, .2012 [DOI:10.5772/31609]
10. [10] J. Gotman and P. Gloor, "Automatic recognition and quantification of interictal epileptic activity in the human scalp EEG," Electroencephalography and clinical neurophysiology, vol. 41, pp. 513-529, .1976 [DOI:10.1016/0013-4694(76)90063-8] [PMID]
11. [11] J. Gotman, "Automatic recognition of epileptic seizures in the EEG," Electroencephalography and clinical Neurophysiology, vol. 54, pp. 530-540, .1982 [DOI:10.1016/0013-4694(82)90038-4] [PMID]
12. [12] G. Harding, "An automated seizure monitoring system for patients with indwelling recording electrodes," Electroencephalography and clinical Neurophysiology, vol. 86, pp. 428- 437, .1993 [DOI:10.1016/0013-4694(93)90138-L] [PMID]
13. [13] S. Mousavi, M. Niknazar, and B. V. Vahdat, "Epileptic seizure detection using AR model on EEG signals," in 2008 Cairo International Biomedical Engineering Conference, 2008, pp. 1-4 [DOI:10.1109/CIBEC.2008.4786067] [PMID]
14. [14] L. Chisci, A. Mavino, G. Perferi, M. Sciandrone, C. Anile, G. Colicchio, et al., "Real-time epileptic seizure prediction using AR models and support vector machines," IEEE Transactions on Biomedical Engineering, vol. 57, pp. 1124-1132, .2010 [DOI:10.1109/TBME.2009.2038990] [PMID]
15. [15] S. Mohamadi, H. Amindavar, and S. A. T. Hosseini, "ARIMA-GARCH modeling for epileptic seizure prediction," in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, pp. .994-998 [DOI:10.1109/ICASSP.2017.7952305]
16. [16] M. Bozek-Juzmicki, D. Colella, and G. M. Jacyna, "Feature-based epileptic seizure detection and prediction from ECoG recordings," in Proceedings of IEEE-SP International Symposium on Time-Frequency and Time-Scale Analysis, 1994, pp. 564-567
17. [17] P.-N. Yu, S. A. Naiini, C. N. Heck, C. Y. Liu, D. Song, and T. W. Berger, "A sparse Laguerre-Volterra autoregressive model for seizure prediction in temporal lobe epilepsy," in 2016 38 th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. .1664-1667, 2016
18. [18] S. Nesaei, AR. Sharafat, " Epileptic seizure prediction based on phase synchronization analysis in time-frequency domain," in 2011 19th Iranian Conference on Electric Engineering (ICEE), pp. 3364-3369, 2011
19. [19] F. Mormann, K. Lehnertz, P. David, and C. E. Elger, "Mean phase coherence as a measure for phase synchronization and its application to the EEG of epilepsy patients," Physica D: Nonlinear Phenomena, vol. 144, pp. 358-369, .2000 [DOI:10.1016/S0167-2789(00)00087-7]
20. [20] M. Le Van Quyen, J. Soss, V. Navarro, R. Robertson, M. Chavez, M. Baulac, et al., "Preictal state identification by synchronization changes in long-term intracranial EEG recordings," Clinical Neurophysiology, vol. 116, pp. 559-568, .2005 [DOI:10.1016/j.clinph.2004.10.014] [PMID]
21. [21] B. Schelter, M. Winterhalder, T. Maiwald, A. Brandt, A. Schad, A. Schulze-Bonhage, et al., "Testing statistical significance of multivariate time series analysis techniques for epileptic seizure prediction," Chaos: An Interdisciplinary Journal of Nonlinear Science, vol. 16, p. 013108, .2006 [DOI:10.1063/1.2137623] [PMID]
22. [22] J. R. Williamson, D. W. Bliss, D. W. Browne, and J. T. Narayanan, "Seizure prediction using EEG spatiotemporal correlation structure," Epilepsy & Behavior, vol. 25, pp. 230-238, .2012 [DOI:10.1016/j.yebeh.2012.07.007] [PMID]
23. [23] X. Huang, W. Wang, X. Sun, Y. Chen, L. Li, Y. Deng, et al., "Model research for epileptic prediction based on improved chaos operator of Lyapunov," in 2009 3rd International Conference on Bioinformatics and Biomedical Engineering, pp. .1-4, 2009 [DOI:10.1109/ICBBE.2009.5163064]
24. [24] L. Tong, W. Wang, N. Zhao, and X. Huang, "The method evaluation for preictal prediction of epilepsy with strong-noise EEG and simulation of automatic drug release system," in 2010 3rd International Conference on Biomedical Engineering and Informatics, pp. .1054-1058, 2010 [DOI:10.1109/BMEI.2010.5640543]
25. [25] S. Wang, W. A. Chaovalitwongse, and S. Wong, "A novel reinforcement learning framework for online adaptive seizure prediction," in 2010 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 499, 2010 [DOI:10.1109/BIBM.2010.5706617]
26. [26] C. A. Teixeira, B. Direito, M. Bandarabadi, M. Le Van Quyen, M. Valderrama, B. Schelter, et al., "Epileptic seizure predictors based on computational intelligence techniques: A comparative study with 278 patients," Computer methods and programs in biomedicine, vol. 114, pp. 324-336 , 2014 [DOI:10.1016/j.cmpb.2014.02.007] [PMID]
27. [27] B. Hjorth, "EEG analysis based on time domain properties," Electroencephalography and clinical neurophysiology, vol. 29, pp. 306-310, .504, 1970 [DOI:10.1016/0013-4694(70)90143-4] [PMID]
28. [28] C. Sudalaimani, S. Asha, K. Parvathy, T. E. Thomas, P. Devanand, P. Sasi, et al., "Use of electrographic seizures and interictal epileptiform discharges for improving performance in seizure prediction," in 2015 IEEE Recent Advances in Intelligent Computational Systems (RAICS), 2015, pp. .229-234 [DOI:10.1109/RAICS.2015.7488419]
29. [29] M. A. F. Harrison, I. Osorio, M. G. Frei, S. Asuri, and Y.-C. Lai, "Correlation dimension and integral do not predict epileptic seizures," Chaos: An Interdisciplinary Journal of Nonlinear Science, vol. 15, p. 033106, .2005 [DOI:10.1063/1.1935138] [PMID]
30. [30] L. Boubchir and B. Boashash, "Wavelet denoising based on the MAP estimation using the BKF prior with application to images and EEG signals," IEEE Transactions on signal processing, vol. 61, pp. 1880-1894, .2013 [DOI:10.1109/TSP.2013.2245657]
31. [31] A. K. Tafreshi, A. M. Nasrabadi, and A. H. Omidvarnia, "Empirical mode decomposition in epileptic seizure prediction," in 2008 IEEE International Symposium on Signal Processing and Information Technology, pp. .275-280, 2008 [DOI:10.1109/ISSPIT.2008.4775729]
32. [32] C. Kamath, "Automatic seizure detection based on Teager Energy Cepstrum and pattern recognition neural networks," QScience Connect, vol. 2014, p. 1, .2014 [DOI:10.5339/connect.2014.1]
33. [33] C. Kamath, "Comparison of baseline cepstral vector and composite vectors in the automatic seizure detection using probabilistic neural networks," ISRN Biomedical engineering, vol. 2013, .2013 [DOI:10.1155/2013/984864]
34. [34] H. Ren, J. Qu, Y. Chai, L. Huang, and Q. Tang, "Cepstrum Coefficient Analysis from Low-Frequency to High-Frequency Applied to Automatic Epileptic Seizure Detection with Bio-Electrical Signals," Applied Sciences, vol. 8, p. 1528, .2018 [DOI:10.3390/app8091528]
35. [35] I. Osorio, M. G. Frei, and S. B. Wilkinson, "Real‐time automated detection and quantitative analysis of seizures and short‐term prediction of clinical onset," Epilepsia, vol. 39, pp. 615-627, .1998 [DOI:10.1111/j.1528-1157.1998.tb01430.x] [PMID]
36. [36] P. Detti, G. Z. M. de Lara, R. Bruni, M. Pranzo, F. Sarnari, and G. Vatti, "A patient-specific approach for short-term epileptic seizures prediction through the analysis of EEG synchronization," IEEE Transactions on Biomedical Engineering, vol. 66, pp. 1494-1504, 2018. [DOI:10.1109/TBME.2018.2874716] [PMID]
37. [37] H. Daoud and M. A. Bayoumi, "Efficient epileptic seizure prediction based on deep learning," IEEE transactions on biomedical circuits and systems, vol. 13, pp. 804-813, 2019. [DOI:10.1109/TBCAS.2019.2929053] [PMID]
38. [38] C. Panayiotopoulos, "Epileptic syndromes and their treatment," Neonatal Seizures, pp. 185-206, .2007
39. [39] F. Shayegh, F. Ghasemi, R. Amirfattahi, S. Sadri, K. Ansariasl, " Online single-channel seizure prediction, based on seizure gensis model of depth-EEG signals using extended Kalman filter," JSDP, pp. 3-27, 2019 [DOI:10.29252/jsdp.15.1.3]
40. [40] L. Hao, R. Ghodadra, and N. V. Thakor, "Quantification of brain injury by EEG cepstral distance during transient global ischemia," in Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.'Magnificent Milestones and Emerging Opportunities in Medical Engineering'(Cat. No. 97CH36136), pp. .1205-1206, 1997
41. [41] M. Le Van Quyen, "Anticipating epileptic seizures: from mathematics to clinical applications," Comptes rendus biologies, vol. 328, pp. 187-198, .2005 [DOI:10.1016/j.crvi.2004.10.014] [PMID]
42. [42] P. Ong, Z. Zainuddin, and K. H. Lai, "A novel selection of optimal statistical features in the DWPT domain for discrimination of ictal and seizure-free electroencephalography signals," Pattern Analysis and Applications, vol. 21, pp. 515-527, .2018 [DOI:10.1007/s10044-017-0642-7]
43. [43] S. Haykin, "Adaptive filter theory," .2015
44. [44] L. R. Rabiner and R. W. Schafer, "Introduction to digital speech processing," Foundations and Trends® in Signal Processing, vol. 1, pp. 1-194, 2007. [DOI:10.1561/2000000001]
45. [45] M. Roessgen, A. M. Zoubir, and B. Boashash, "Modeling of newborn EEG data for seizure detection," in Advanced Signal Processing Algorithms, pp. .101-112, 1995
46. [46] P. Celka and P. Colditz, "Nonlinear nonstationary Wiener model of infant EEG seizures," IEEE Transactions on Biomedical Engineering, vol. 49, pp. 556-564, .2002 [DOI:10.1109/TBME.2002.1001970] [PMID]
47. [47] M. Roessgen, A. M. Zoubir, and B. Boashash, "Seizure detection of newborn EEG using a model-based approach," IEEE Transactions on Biomedical Engineering, vol. 45, pp. 673-685, .1998 [DOI:10.1109/10.678601] [PMID]
48. [48] d. S. F. Lopes, A. Hoeks, H. Smits, and L. Zetterberg, "Model of brain rhythmic activity. The alpha-rhythm of the thalamus," Kybernetik, vol. 15, p. 27, .1974 [DOI:10.1007/BF00270757] [PMID]
49. [49] T. Söderström and P. Stoica, "system identification," .2001
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
