Automatic Detection of Interictal Epileptiform Discharges Based on the Similarity of Time-Series Sequence

Abstract:

In this paper, an effective digital signal processing method based on the merger of the increasing and decreasing time-series sequences (MIDS) is introduced. On the basis of the merging of EEG signals, a new IED (Interictal Epileptiform Discharges) detection method is proposed. The first step of this new method is to establish a database by selecting peaked wave fragments. Then, the similarity between pending test fragment and peaked wave samples in the database is calculated. When the maximum similarity is greater than a certain threshold, the fragment is judged to be a peaked wave. Finally, the wave type i.e. spike wave, sharp wave, spike-and-slow wave or sharp-and-slow wave can be determined by whether there is a subsequent slow wave or not. Continuous sharp wave can be viewed as spike rhythm. In this research, 92 IED fragments from 4 suspected epilepsy patients are collected to establish the sample database. The proposed method was tested on EEG recordings from other 31 suspected patients. The results show that 98.11% of the IED fragments marked by doctors were detected. The experimental results show that this method performs well at IED detection in the clinical EEG data. The similarity is measured based on the comparison between fragments of different time length and can be viewed as a novel approach for the detection of typical EEG waveform. This research draws two conclusions: (1) the waveform of individual peaked wave is stable during 24-hour EEG recording process; (2) the database containing a small number peaked wave samples can be used to detect IED fragments.

• Periodical: Applied Mechanics and Materials (Volumes 239-240)
• Pages: 921-931
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.239-240.921
• Online since: December 2012
• Authors: Jian Zhang, Jun Zhong Zou, Lan Lan Chen, Chen Jie Zhao, Gui Song Wang
• Keywords: Automatic Detection, Interictal Epileptiform Discharges (IED), Merger of Increasing and Decreasing Sequences (MIDS), Similarity of Time-Series Sequence

References

[1] Mark Quigg MD MSc, EEG Pearls. MOSBY, (2006).

[2] Wang Chunmei, Zou Junzhong, Zhang Jian. International conference on information and automation, 2009, 1~3: 1244~1248.

[3] Wang Chunmei, Zou Junzhong, Proceedings of the 2009 2nd international conference on biomedical engineering and informatics, 2009, 1~4: 560~564.

[4] Nuh M, Jazidie A, Muslim MA. in Proc. APCCAS (2), 2002, pp.483-486.

[5] He Sheng Liu; Tong Zhang; Fu Sheng Yang. Biomedical Engineering, IEEE Transactions on Volume: 49, Issue: 12, Part: 2, 2002, 1557-1566.

DOI: 10.1109/tbme.2002.805477

[6] Fernanda I. M. Argoud, Fernando M. De Azevedo, Jose´ Marino Neto, Eugeˆnio Grillo. Med Biol Eng Comput (2006) 44: 459–470.

[7] He Sheng Liu, Tong Zhang, Fu Sheng Yang. IEEE Transactions on biomedical engineering, vol. 49, No. 12, december (2002).

[8] Cui SY, Li XL, Ouyang GX. advances in neural networks, 2005, 3(3498): 445~450.

[9] Orosco, L.; Garcés Correa, A.; Laciar, E.;. Engineering in Medicine and Biology Society (EMBC), 2010 Annual International Conference of the IEEE, 2010, 951-954.

DOI: 10.1109/iembs.2010.5627564

[10] Pon LS, Sun MG, Sclabassi RJ. Proceedings of annual international conference of the IEEE engineering in medicine and biologysociety 2000, 1~4, 22: 1583~1585.

[11] Nicolás von Ellenrieder, Luciana P. Andrade-Valença, François Dubeau, Jean Gotman. Clinical Neurophysiology 123 (2012) 670–680.

DOI: 10.1016/j.clinph.2011.07.050

[12] Uchida S, Feinberg I, March J D et al. Physiol Behav, 1999, 67(1): 121~131.

[13] Uchida S, Matsuura M, Ogata S et al. J Neurosci Meth, 1996, 64(1): 1~12.

[14] Tan X, Campbell I G, Palagini L et al. Biol Psychiat, 2000, 48(10): 1010~1019.

[15] Honda M, Koga E, Ishikawa T et al. Psychiat Clin Neuros, 1997, 51(6): 387~392.

[16] Park H J, Oh J S, Jeong D U et al. Comput Biomed Res, 2000, 33(5): 330~349.