:: Volume 9, Issue 1 (Winter 2020) ::
Shefaye Khatam 2020, 9(1): 110-119 Back to browse issues page
Epileptic Seizure Prediction from Spectral, Temporal, and Spatial Features of EEG Signals Using Deep Learning Algorithms
Nazanin Mohammadkhani Ghiasvand , Foad Ghaderi *
Human-Computer Interaction Lab, Faculty of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, Iran , fghaderi@modares.ac.ir
Abstract:   (3654 Views)
Introduction: Epilepsy is one of the most common brain disorders that greatly affect patients life. However, early detection of seizure attacks can significantly improve their quality of life. In this study, we evaluated a deep neural network to learn robust features from electroencephalography (EEG) signals to automatically detect and predict seizure attacks. Materials and Methods: The architecture consists of convolutional neural networks and long short-term memory networks. It is designed to simultaneously capture spectral, temporal, and spatial information. Moreover, the architecture does not rely on explicit channel selection algorithms. The method is applied to the Children's Hospital of Boston-Massachusetts Institute of Technology dataset (CHB-MIT). To evaluate the method, the proposed model is trained in the patient-specific approach. Results: The proposed architecture achieves a sensitivity of 90.7 ± 7.9 percent, a false prediction rate of 0.12/h, and a mean prediction time of 36.8 minutes. Moreover, in the cases of focal seizures, the proposed model estimates the seizure focus. Conclusion: The proposed model achieved a high capability in seizure prediction. Moreover, by using the automated feature selection of the deep learning algorithm, the patterns of the pre-ictal period in EEG signals were determined. Furthermore, by specifying the seizure focus, the model can help neurologists to take further curative actions.

Keywords: Patients, Deep Learning, Electroencephalography
Full-Text [PDF 997 kb]   (1246 Downloads)    
Type of Study: Research --- Open Access, CC-BY-NC | Subject: Neurology
References
1. Thijs RD, Surges R, O'brien TJ. Sander JW, "Epilepsy in adults. vol. 393, ed: The Lancet, 2019; p. 611-716. [DOI:10.1016/S0140-6736(18)32596-0]
2. Stafstrom CE, Carmant L. Seizures and epilepsy: An overview for neuroscientists." Cold Spring Harb Perspect Med, 2015. [DOI:10.1101/cshperspect.a022426]
3. Miller JW, Hakimian S. Surgical treatment of epilepsy. ed: CONTINUUM Lifelong Learning in Neurology, 2013. [DOI:10.1212/01.CON.0000431398.69594.97]
4. Sharif B, Jafari AH. Prediction of epileptic seizures from EEG using analysis of ictal rules on Poincaré plane," Computer Methods and Programs in Biomedicine. 2017; 11-22. [DOI:10.1016/j.cmpb.2017.04.001]
5. Aarabi A and He B. Seizure prediction in patients with focal hippocampal epilepsy. Clinical Neurophysiology, 2017; 7: 1299-307. [DOI:10.1016/j.clinph.2017.04.026]
6. Eftekhar A, Juffali W, El-Imad J, Constandinou TG, Toumazou C. Ngram-derived pattern recognition for the detection and prediction of epileptic seizures. PLoS ONE, 2014; 6. [DOI:10.1371/journal.pone.0096235]
7. Park Y, Luo L, Parhi KK, Netoff T.Seizure prediction with spectral power of EEG using cost-sensitive support vector machines. Epilepsia, 2011; 10: 1761-70. [DOI:10.1111/j.1528-1167.2011.03138.x]
8. Gadhoumi K, Lina JM, Gotman J. Seizure prediction in patients with mesial temporal lobe epilepsy using EEG measures of state similarity. Clinical Neurophysiology, 2013; 9: 1745-754. [DOI:10.1016/j.clinph.2013.04.006]
9. Rogowski Z, Gath I, Bental E. On the prediction of epileptic seizures. Biological Cybernetics, 1981; 1: 9-15 [DOI:10.1007/BF00335153]
10. Mirowski P, Madhavan D, Lecun Y, Kuzniecky R. Classification of patterns of EEG synchronization for seizure prediction. Clinical Neurophysiology, 2009; 11: 1927-940. [DOI:10.1016/j.clinph.2009.09.002]
11. Beniczky S, Aurlien H, Brøgger JC, Fuglsang-Frederiksen A, Martins-Da-Silva A, Trinka E et al. Standardized Computer-Based Organized Reporting of EEG: SCORE. Epilepsia, 2013; 6: 1112-24. [DOI:10.1111/epi.12135]
12. Winterhalder M, Schelter B, Maiwald T, Brandt A, Schad A, Schulze-Bonhage A et al. Spatio-temporal patient-individual assessment of synchronization changes for epileptic seizure prediction. Clinical Neurophysiology, 2006; 11: 2399-413. [DOI:10.1016/j.clinph.2006.07.312]
13. Alexandros T, Markos G, Dimitrios G, Evaggelos C, Astrakas L, Konitsiotis S et al. Automated Epileptic Seizure Detection Methods: A Review Study. in Epilepsy -Histological, Electroencephalographic and Psychological Aspects: InTech, 2012.
14. Shoeb AH. Application of machine learning to epileptic seizure onset detection and treatment. ed: Massachusetts Institute of Technology, 2009.
15. Panayiotopoulos CP. A Clinical Guide to Epileptic Syndromes and their Treatment. Springer-Verlag London, 2010. [DOI:10.1007/978-1-84628-644-5]
16. Zhang Z and Parhi KK. Low-Complexity Seizure Prediction From iEEG/sEEG Using Spectral Power and Ratios of Spectral Power. IEEE Transactions on Biomedical Circuits and Systems, 2016; 3: 693-706 [DOI:10.1109/TBCAS.2015.2477264]
17. Alickovic E, Kevric J, Subasi A. 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. 2018; 94-102. [DOI:10.1016/j.bspc.2017.07.022]
18. Khan H, Marcuse L, Fields M, Swann K, Yener B. Focal onset seizure prediction using convolutional networks. IEEE Transactions on Biomedical Engineering, 2018; 9: 2109-118. [DOI:10.1109/TBME.2017.2785401]
19. Truong ND, Nguyen AD, Kuhlmann L, Bonyadi MR, Yang J, Ippolito S et al. Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram. IEEE Transactions on Biomedical Engineering. 2018; 104-111. [DOI:10.1016/j.neunet.2018.04.018]
20. Thodoroff P, Pineau J, Lim A. Learning Robust Features using Deep Learning for Automatic Seizure Detection. Journal of Machine Learning Research, 2016.
21. Snyder JP. Map projections- a working manual in Geological Survey professional paper; 1395," U.S. Geological Survey professional paper 1395, 1987. [Online]. Available: http://pubs.usgs.gov/pp/1395/report.pdf [DOI:10.3133/pp1395]
22. Bashivan P, Rish I, Yeasin M, Codella N. Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks," presented at the ICLR 2016.
23. Guo N, Yang Z, Jia Y, Wang L. Model updating using correlation analysis of strain frequency response function. Mechanical Systems and Signal Processing, 2016; 284-99. [DOI:10.1016/j.ymssp.2015.09.036]

XML   Persian Abstract   Print

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Volume 9, Issue 1 (Winter 2020) Back to browse issues page