Volume 9, Issue 4 (2018)
JMBS 2018, 9(4): 653-658 |
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:
Tabanfar Z, Firoozabadi S, Khodakarami Z, Shankayi Z. Analysis of Electroencephalogram Data during Rest in Patients with Brain Tumor. JMBS 2018; 9 (4) :653-658
URL: http://biot.modares.ac.ir/article-22-13045-en.html
URL: http://biot.modares.ac.ir/article-22-13045-en.html
1- Bioelectronics Department, Electrical & Computer Engineering Faculty, Tarbiat Moderes University, Tehran, Iran
2- Medical Physics Department, Medical Sciences Faculty, Tarbiat Moderes University, Tehran, Iran, Medical Physics Department, Medical Sciences Faculty, Tarbiat Modares University, Nasr Bridge, Jalal-Al-Ahmad Highway, Tehran, Iran , pourmir@modares.ac.ir
3- Medical Physics Department, Medical Sciences Faculty, Tarbiat Moderes University, Tehran, Iran
2- Medical Physics Department, Medical Sciences Faculty, Tarbiat Moderes University, Tehran, Iran, Medical Physics Department, Medical Sciences Faculty, Tarbiat Modares University, Nasr Bridge, Jalal-Al-Ahmad Highway, Tehran, Iran , pourmir@modares.ac.ir
3- Medical Physics Department, Medical Sciences Faculty, Tarbiat Moderes University, Tehran, Iran
Abstract: (3694 Views)
Aims: Electroencephalogram (EEG) is an important clinical test for the diagnosis of many brain diseases. The aim of this study was the analysis of electroencephalogram data during rest in patients with brain tumor.
Materials and Methods: In the present analytic observational study, EEG data of 44 patients with brain tumor (tumoral group) and 31 healthy subjects (healthy group) during rest were used. After preprocessing, the linear temporal features, linear spectral features of different frequency bands, and non-linear features of fractal dimension and entropy were extracted. Then, the distinction between healthy and tumoral groups based on extracted features was investigated, using the Davis-Bouldin statistic method, linear discriminant analysis (LDA) and nonlinear K-Nearest Neighbor (KNN) classification.
Findings: There was no significant difference between the the fractal kutz dimension and the waveform length of the two healthy and tumoral groups. Among other features, the sample entropy with a significant reduction in the tumoral group made the most distinction between the two groups (0.69 for the healthy group and 0.53 for the tumoral group). The highest classification accuracy of the two groups was 84%, using the sample entropy and KNN classification.
Conclusion: EEG signals have the potential to distinct the patients with brain tumor and healthy subjects. Nonlinear entropy features with more adaptation to the nonlinear nature of the brain shows a higher accuracy in the representation of the tumoral group. The less entropy of the tumoral group indicates less complexity in the brain processing of this group than the healthy group.
Materials and Methods: In the present analytic observational study, EEG data of 44 patients with brain tumor (tumoral group) and 31 healthy subjects (healthy group) during rest were used. After preprocessing, the linear temporal features, linear spectral features of different frequency bands, and non-linear features of fractal dimension and entropy were extracted. Then, the distinction between healthy and tumoral groups based on extracted features was investigated, using the Davis-Bouldin statistic method, linear discriminant analysis (LDA) and nonlinear K-Nearest Neighbor (KNN) classification.
Findings: There was no significant difference between the the fractal kutz dimension and the waveform length of the two healthy and tumoral groups. Among other features, the sample entropy with a significant reduction in the tumoral group made the most distinction between the two groups (0.69 for the healthy group and 0.53 for the tumoral group). The highest classification accuracy of the two groups was 84%, using the sample entropy and KNN classification.
Conclusion: EEG signals have the potential to distinct the patients with brain tumor and healthy subjects. Nonlinear entropy features with more adaptation to the nonlinear nature of the brain shows a higher accuracy in the representation of the tumoral group. The less entropy of the tumoral group indicates less complexity in the brain processing of this group than the healthy group.
Subject:
Agricultural Biotechnology
Received: 2016/10/7 | Accepted: 2017/03/5 | Published: 2018/12/21
Received: 2016/10/7 | Accepted: 2017/03/5 | Published: 2018/12/21
References
1. Sharanreddy M, Kulkarni PK. Can EEG test helps in identifying brain tumor?. Int Sch Sci Res Innov. 2013;7(11):703-8. [Link]
2. Martino J, Honma SM, Findlay AM, Guggisberg AG, Owen JP, Kirsch HE, et al., Resting functional connectivity in patients with brain tumors in eloquent areas. Ann Neurol. 2011;69(3):521-32. [Link] [DOI:10.1002/ana.22167]
3. Jochmann T, Güllmar D, Haueisen J, Reichenbach JR. Influence of tissue conductivity changes on the EEG signal in the human brain: A simulation study. Z Med Phys. 2011;21(2):102-12. [Link] [DOI:10.1016/j.zemedi.2010.07.004]
4. Poulos M, Felekis T, Evangelou A. Is it possible to extract a fingerprint for early breast cancer via EEG analysis?. Med Hypotheses. 2012;78(6):711-6. [Link] [DOI:10.1016/j.mehy.2012.02.016]
5. Poulos M, Maliagani E, Paschopoulos M, Bokos G. Endometrial cancer recognition via EEG dependent upon 14-3-3 protein leading to an ontological diagnosis. Int Sch Sci Res Innov. 2009:3(7):143-50. [Link]
6. Silipo R, Deco G, Bartsch H. Brain tumor classification based on EEG hidden dynamics. Intell Data Anal. 1999:3(4):287-306.
https://doi.org/10.3233/IDA-1999-3404 [Link] [DOI:10.1016/S1088-467X(99)00024-4]
7. Karameh FN, Dahleh MA. Automated classification of EEG signals in brain tumor diagnostics. American Control Conference, 28-30 June, 2000, Chicago, IL, USA. Piscataway: IEEE; 2000. [Link] [DOI:10.1109/ACC.2000.877006]
8. Habl M, Bauer Ch, Ziegaus Ch, Lang EW, Schulmeyer F. Can ICA help identify brain tumor related EEG signals?. International Workshop on Independent Component Analysis and Blind Signal Separation 19-22 June 2000, Helsinki, Finland (ICA 2000). Helsinki: Helsinki University of Technology; 2000. p. 609-14. [Link]
9. Chetty S, Venayagamoorthy GK. A neural network based detection of brain tumours using electroencephalography. International Conference on Artificial Intelligence and Soft Computing, July 17-19, 2002, Banff, Canada. Piscataway: IEEE PES; 2002. p. 391-6. [Link]
10. Murugesan M, Sukanesh R. Automated detection of brain tumor in EEG signals using artificial neural networks. International Conference on Advances in Computing, Control, and Telecommunication Technologies, 28-29 Dec, 2009, Trivandrum, Kerala, India. Piscataway: IEEE; 2009. [Link] [DOI:10.1109/ACT.2009.77]
11. Murugesan M, Sukanesh R. Towards detection of brain tumor in electroencephalogram signals using support vector machines. Int J Comput Theory Eng. 2009;1(5):622-31. [Link] [DOI:10.7763/IJCTE.2009.V1.101]
12. Selvam VS, Shenbagadevi S. Brain tumor detection using scalp EEG with modified wavelet-ICA and multi layer feed forward neural network. Conf Proc IEEE Eng Med Biol Soc. 2011;2011:6104-9. [Link]
13. Samant IS, Kanungo GK, Mishra SK. Desired EEG signals for detecting brain tumor using lms algorithm and feedforward network. Int J Eng Trends Technol. 2012:3(6):718-23. [Link]
14. Sharanreddy M, Kulkarni PK. Brain tumor epilepsy seizure identification using multi-wavelet transform, neural network and clinical diagnosis data. Int J Comput Appl. 2013;67(2):10-7. [Link]
15. Sharanreddy M, Kulkarni PK. Detection of primary brain tumor present in EEG signal using wavelet transform and neural network. Int J Biol Med Res. 2013;4(1):2855-9. [Link]
16. Surkar AA, Ambatkar N. Review on wavelet transform based EEG analysis for primary tumor detection. Int J Recent Innov Trends Comput Commun. 2015:3(2):106-9. [Link]
17. Salai Selvam V, Shenbaga Devi S. Analysis of spectral features of EEG signal in brain tumor condition. Meas Sci Rev. 2015;15(4):219-25. [Link] [DOI:10.1515/msr-2015-0030]
18. Padmapriya P, Manikandan K, Jeyanthi K, Renuga V, Sivaraman J. Detection and classification of brain tumor using radial basis function. Indian J Sci Technol. 2016:9(1):1-5. [Link] [DOI:10.17485/ijst/2016/v9i1/85758]
19. Urigüen JA, Garcia-Zapirain B. EEG artifact removal-state-of-the-art and guidelines. J Neural Eng. 2015 Jun;12(3):031001. [Link] [DOI:10.1088/1741-2560/12/3/031001]
20. Rajendra Acharya U, Fujita H, Sudarshan VK, Bhat S, Koh JEW. Application of entropies for automated diagnosis of epilepsy using EEG signals: A review. Knowl Based Syst. 2015;88:85-96. [Link] [DOI:10.1016/j.knosys.2015.08.004]
21. Hornero R, Abásolo D, Jimeno N, Sánchez CI, Poza J, Aboy M. Variability, regularity, and complexity of time series generated by schizophrenic patients and control subjects. IEEE Trans Biomed Eng. 2006;53(2):210-8. [Link] [DOI:10.1109/TBME.2005.862547]
22. Christopher M B. Pattern recognition and machine learning. 1st ed. Springer-Verlag: Springer; 2006. [Link]
23. Chaovalitwongse WA, Fan YJ, Sachdeo RC. On the time series K-nearest neighbor classification of abnormal brain activity. IEEE Trans Syst Man Cybern Part A Syst Hum. 2007;37(6):1005-16. [Link] [DOI:10.1109/TSMCA.2007.897589]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |