Links & Downloads
Res. Biomed. Eng. 2017; 33
10.1590/2446-4740.08616 doi: http://dx.doi.org/10.1590/2446-4740.08616
Abstract:Introduction: Early detection of epilepsy by the review of large electroencephalographic (EEG) recordings is very stressful, time-consuming, and subjective for neurologists. Several automatic seizure detection systems have been proposed in the literature to solve this problem. Methods: This study proposes two complementary wavelet-based approaches for detecting epileptiform paroxysms in EEG signals. First methodology applied the wavelet multiresolution analysis (MRA) to filter non-epileptiform activity in long-term EEG. Second methodology used the wavelet dyadic scalogram to analyze which scales were related to the epileptiform paroxysms. For tests, 65 wavelet functions were selected between daubechies, biorthogonal, symlets, reverse biorthogonal and coiflet wavelet families in order to evaluate their performance. Results: For MRA, it was noted a better performance by using the db4 function, by reaching 48.30% of energy with 8 wavelet coefficients, 0.717658 of correlation and 36.799 of root mean square error (RMSE). For wavelet dyadic scalograms, were chosen bior3.9 and rbio1.5 functions, by reaching 77.98% of sensitivity, 94.08% of specificity, 87.87% of efficiency and 0.9613 of area under the curve (AUC value) by using bior3.9. Conclusion: The presented approaches are highly complementary for a whole automatic seizure detection system by using the MRA as pre-processing stage to filter non-epileptiform activity, and wavelet dyadic scalogram for extracting desired features from filtered EEG signals.
Keywords:Epilepsy, EEG signal, Wavelet multiresolution analysis, Wavelet dyadic scalogram, Artificial neural network
Aarabi A, Fazel-Rezai R, Aghakhani Y. A fuzzy rule-based system for epileptic seizure detection in intracranial EEG. Clinical Neurophysiology. 2009; 120(9):1648-57. PMid:19632891. http://dx.doi.org/10.1016/j.clinph.2009.07.002.
Adeli H, Ghosh-Dastidar S, Dadmehr N. A wavelet-chaos methodology for analysis of EEGs and EEG subbands to detect seizure and epilepsy. IEEE Transactions on Biomedical Engineering. 2007; 54(2):205-11. PMid:17278577. http://dx.doi.org/10.1109/TBME.2006.886855.
Akansu AN, Haddad RA. Multiresolution signal decomposition: transforms, subbands, wavelets. 2nd ed. San Diego: Academic Press; 2001. 499 p.
Arunkumar N, Balaji VS, Ramesh S, Natarajan S, Likhita VR, Sundari S. Automatic detection of epileptic seizures using independent component analysis algorithm. In: Proceedings of the IEEE International Conference on Advances in Engineering, Science and Management (ICAESM); 2012 Mar 30-31; Nagapattinam, India. IEEE Publisher; 2012. p. 542-4.
Ayoubian L, Lacoma H, Gotman J. Automatic seizure detection in SEEG using high frequency activities in wavelet domain. Medical Engineering & Physics. 2013; 35(3):319-28. PMid:22647836. http://dx.doi.org/10.1016/j.medengphy.2012.05.005.
Boos CF, Azevedo FM, Scolaro GR, Pereira MCV. Automatic detection of paroxysms in EEG signals using morphological descriptors and artificial neural networks. In: Laskovski A, editor. Biomedical engineering trends in electronics, communications and software. Rijeka: InTech; 2011. p. 387-402.
Burrus CS, Gopinath RA, Guo H. Introduction to wavelets and wavelet transforms. Upper Saddle River: Prentice Hall; 1998. 268 p.
Chua ECP, Patel K, Fitzsimons M, Bleakley CJ. Improved patient specific seizure detection during pre-surgical evaluation. Clinical Neurophysiology. 2011; 122(4):672-9. PMid:21130030. http://dx.doi.org/10.1016/j.clinph.2010.10.002.
David VK, Rajasekaran S. Pattern recognition using neural and functional networks. Chennai: Springer; 2009. 184 p.
Fergus P, Hignett D, Hussain A, Al-Jumeily D, Abdel-Aziz K. Automatic epileptic seizure detection using scalp EEG and advanced artificial intelligence techniques. BioMed Research International. 2015; 2015:1-17. http://dx.doi.org/10.1155/2015/986736.
Gotman J, Gloor P. Automatic recognition and quantification of interictal epileptic activity in the human scalp EEG. Electroencephalography and Clinical Neurophysiology. 1976; 41(5):513-29. PMid:61855. http://dx.doi.org/10.1016/0013-4694(76)90063-8.
Graupe D. Principles of artificial neural networks. 2nd ed. Singapore: World Scientific Publishing; 2007. 303 p. (Advanced Series on Circuits and Systems).
Haydari Z, Zhang Y, Soltanian-Zadeh H. Semi-automatic epilepsy spike detection from EEG signal using genetic algorithm and wavelet transform. In: Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine Workshops (BIBMW); 2011 Nov 12-15; Atlanta. IEEE Publisher; 2011. p. 635-8. http://dx.doi.org/10.1109/BIBMW.2011.6112443.
Hramov AE, Koronovskii AA, Makarov VA, Pavlov AN, Sitnikova E. Wavelets in neuroscience. Berlin: Springer-Verlag; 2015. 331 p.
Hunyadi B, Vos M, Signoretto M, Suykens JAK, Paesschen WV, Huffel S van. Automatic seizure detection incorporating structural information. In: Proceedings of the 21th International Conference on Artificial Neural Networks (ICANN); 2011 Jun 14-17; Espoo, Finland. Berlin: Springer-Verlag; 2011. p. 233-40.
Jain AK, Mao J, Mohiuddin KM. Artificial neural network: a tutorial. Computer. 1996; 29(3):31-44. http://dx.doi.org/ 10.1109/2.485891.
Liu Y, Zhou W, Yuan Q, Chen S. Automatic seizure detection using wavelet transform and SVM in long-term intracranial EEG. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2012; 20(6):749-55. PMid:22868635. http://dx.doi.org/10.1109/TNSRE.2012.2206054.
Livingstone D. Artificial neural networks: methods and applications. Totowa: Humana Press Inc.; 2008. 254 p.
Lobato W, Boos CF, Azevedo F. Pattern recognition of epileptiform events in EEG signals using wavelet scalograms. In: Proceedings of the International Conference on BioSignal Analysis, Processing and Systems (ICBAPS); 2015 May 26-28; Kuala Lumpur, Malaysia. IEEE Publisher; 2015. p. 123-8. http://dx.doi.org/10.1109/ICBAPS.2015.7292231.
Olejarczyk E, Sobieszek A, Rudner R, Marciniak R, Wartak M, Stasiowski M, Jalowiecki P. Evaluation of the EEG-signal during volatile anaesthesia: methodological approach. Biocybernetics and Biomedical Engineering. 2009; 29(1):3-28.
Peker M, Sen B, Delen D. A novel method for automated diagnosis of epilepsy using complex-valued classifiers. IEEE Journal of Biomedical and Health Informatics. 2016; 20(1):108-18. PMid:25576585. http://dx.doi.org/10.1109/JBHI.2014.2387795.
Petersen KNH, Nielsen TN, Thomsenz CE, Soronsen HB. Automatic characterization of dynamics in absence epilepsy. In: Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); 2013 Jul 3-7; Osaka, Japan. IEEE Publisher; 2013. p. 4283-6. http://dx.doi.org/10.1109/EMBC.2013.6610492.
Ramgopal S, Thome-Souza S, Jackson M, Kadish NE, Sánches Fernándes I, Klehm J, Bosl W, Reinsberger C, Schachter S, Loddenkemper T. Seizure detection, seizure prediction, and closed-loop warning systems in epilepsy. Epilepsy & Behavior. 2014; 37:291-307. PMid:25174001. http://dx.doi.org/10.1016/j.yebeh.2014.06.023.
Scolaro GR, Azevedo FM, Boos CF, Walz R. Wavelet filter to attenuate the background activity and high frequencies in EEG signals applied in the automatic identification of epileptiform events. In: Andrade A, editor. Practical applications in biomedical engineering. Rijeka: InTech; 2012. p. 81-102. http://dx.doi.org/10.5772/53585.
Scolaro GR, Azevedo FM, Boos CF. Evaluation of different wavelet functions applied in the development of digital filters to attenuate the background activity in EEG signals. In: Proceedings of the World Congress on Medical Physics and Biomedical Engineering (IFMBE); 2012 May 26-31; Beijing, China. Berlin: Springer; 2013. p. 340-3. http://dx.doi.org/10.1007/978-3-642-29305-4_91.
Scolaro GR, Azevedo FM. Classification of epileptiform events in raw EEG signals using neural classifier. In: Proceedings of the 3rd IEEE International Conference on Computer Science and Information Technology (ICCSIT); 2010 Jul 9-11; Chengdu, China. IEEE Publisher; 2010. p. 368-72. http://dx.doi.org/10.1109/ICCSIT.2010.5563949.
Shoeb A, Clifford G. Wavelets; Multiscale activity in physiological signals short-time fourier transform. In: Najarian K, Splinter R, editor. Biomedical signal and image processing. MIT: Spring; 2006. 1-29 p.
Stevanovic D. Epilepsy: histological, electroencephalographic and psychological aspects. Rijeka: InTech; 2012. 276 p.
Tatum WO 4th, Kaplan PW, Jallon P. Epilepsy A to Z: a concise encyclopedia. 2nd ed. New york: Demos Medical Publishing; 2009. 377 p.
Wang F, Meng Q, Chen Y, Zhao Y. Feature extraction method for epileptic seizure detection based on cluster coefficient distribution of complex network. WSEAS Transactions on Computers. 2014; 13:351-60.