Research Article
BibTex RIS Cite

Hilbert Dönüşümü Kullanılarak EEG İşaretlerinden Kanal Bazlı Şizofren Hastalığının Tespiti

Year 2020, Volume: 13 Issue: 2, 78 - 86, 16.12.2020

Abstract

Elektroensefalografi (EEG) nörolojik hastalıkların tespitinde sahip olduğu çok kanallı ve yüksek zaman çözünürlüklü yapısı ile çalışmalarda etkili bir görüntüleme aracı olarak popülerliğini korumaktadır. Bu çalışmada, Hilbert Dönüşümü (HD) kullanılarak EEG kayıtlarından kanal bazlı şizofreni hastalığının tespiti amaçlanmıştır. İşarete ait sanal bileşenler bu dönüşümle analiz edilip hasta/kontrol gruptan oluşan öznitelik vektörleri Destek Vektör Makinası (DVM) ile sınıflandırılmıştır. Kullanılan EEG veri seti, yaşları 10-14 arasında değişen 39 şizofreni ve yaşları 11-13 arasında farklılık gösteren 39 sağlıklı katılımcıdan elde edilmiştir. Mevcut kayıtlar katılımcının gözleri kapalı konumda iken 10-20 sistemine göre düzenlenmiş 16 elektrot aracılığı ile 1 dakika süresince alınmıştır. Çalışmada kullanılan kanallar frontal, parietal, temporal, central ve oksipital lob’un ilgili bölgelerinden seçilmiştir. Yapılan sınıflandırma işleminde k=10 çapraz doğrulama kullanılarak eğitim ve test kümeleri oluşturulmuştur. Çalışmada sınıflandırma başarımın yanında Tutturma (Precision), Bulma (Recall), F1-Score değerleri de hesaplanmıştır. Çalışmada en iyi sınıflandırma başarımı %95,19 ile frontal lob ’dan oluşan özniteliklerden elde edilmiştir. En düşük sınıflandırma performansının ise temporal lob bölgesinden alınan kanal öznitelikleri olduğu görülmüştür. Sağlıklı ve hasta grupların başarılı şekilde ayrıştırılması, izlenilen metodun klinik tedavilerde uygulanabileceğini, klinisyenlere tedavi edilecek kişinin durumu konusunda fikir verebileceğini göstermektedir. Önerilen çalışma mevcut hali ile şizofreni hastalığı tespitinde literatüre katkı sunacak pratik bir uygulama olarak umut vadetmektedir.

References

  • [1] Rajinikanth, V., Satapathy, S. C., Fernandes, S. L., ve Nachiappan, S. Entropy based segmentation of tumor from brain MR images – a study with teaching learningbased optimization, Pattern Recognit. Lett., vol. 94, pp. 87–95, 2017.
  • [2] Dünya Sağlık Örgütü (WHO): https://www.who.int/mental_health/management/schizophrenia/en.
  • [3] Wang, Z. ve Oates, T. Imaging time-series to improve classification and imputation, IJCAI Int. Jt. Conf. Artif. Intell., vol. 2015-January, no. Ijcai, pp. 3939– 3945, 2015.
  • [4] Sanei S. ve Chambers, J. A. EEG Signal Processing. New York: Wiley, 2007.
  • [5] Subudhi, A., Acharya, U. R., Dash, M., Jena, S. ve Sabut, S. Automated approach for detection of ischemic stroke using Delaunay Triangulation in brain MRI images, Comput. Biol. Med., vol. 103, no. August, pp. 116–129, 2018.
  • [6] Kim, J. W., Lee Y. S., Han D. H., Min K. J., Lee J., ve Lee K., Diagnostic utility of quantitative EEG in un-medicated schizophrenia, Neurosci. Lett., vol. 589, pp. 126– 131, 2015.
  • [7] Dvey-Aharon, Z., Fogelson, N., Peled, A. ve Intrator, N., Schizophrenia detection and classification by advanced analysis of EEG recordings using a single electrode approach, PLoS One, vol. 10, no. 4, pp. 1–12, 2015.
  • [8] Johannesen, J. K., Bi, J., Jiang, R. J., Kenney, G. ve Chen, C.-M. A., Machine learning identification of EEG features predicting working memory performance in schizophrenia and healthy adults, Neuropsychiatr. Electrophysiol., vol. 2, no. 1, pp. 1–21, 2016.
  • [9] Santos-Mayo, L., San-Jose-Revuelta, L. M., ve Arribas, J. I., A computer-aided diagnosis system with EEG based on the p3b wave during an auditory odd-ball task in schizophrenia, IEEE Trans. Biomed. Eng., vol. 64, no. 2, pp. 395–407, 2017.
  • [10] Jahmunah , V. ve ark., Automated detection of schizophrenia using nonlinear signal processing methods, Artif. Intell. Med., vol. 100, no. June, p. 101698, 2019.
  • [11] Şeker, D. ve Ozerdem, M. S. Sağlıklı ve Şizofrenik EEG Zaman Serilerinin Sınıflandırılması ve İstatistiksel Analizi, TIPTEKNO’20, Medical Technologies Congress, 19-20 November 2020/Online.
  • [12] Şeker, M. ve Ozerdem, M. S., Şizofreni Teşhisinde Bir Nöro-işaretçi olarak EEG Uyumluluğu, 2020 28th Signal Processing and Communications Application Conference (SIU), Online.
  • [13] Borisov, S. V., Kaplan, A. Y., Gorbachevskaya, N. L., ve Kozlova, I. A. Analysis of EEG structural synchrony in adolescents with schizophrenic disorders, Hum. Physiol., vol. 31, no. 3, pp. 255–261, 2005.
  • [14] Devia, C. ve ark., EEG classification during scene free-viewing for schizophrenia detection, IEEE Trans. Neural Syst. Rehabil. Eng., vol. 27, no. 6, pp. 1193–1199, Jun. 2019.
  • [15] Piryatinska, A., Darkhovsky, B. ve Kaplan, A., Binary classification of multichannel-EEG records based on the _-complexity of continuous vector functions, Comput. Methods Programs Biomed., vol. 152, pp. 131–139, Dec. 2017.
  • [16] Sui, J. ve ark., Combination of FMRI-SMRI-EEG data improves discrimination of schizophrenia patients by ensemble feature selection, in Proc. 36th Annu. Int. Conf. IEEE Eng. Med. Biol. Soc., Aug. 2014, pp. 3889–3892.
  • [17] Boostani, R., Sadatnezhad, K. ve Sabeti, M., An efficient classifier to diagnose of schizophrenia based on the EEG signals, Expert Syst. Appl., vol. 36, no. 3, pp. 6492–6499, Apr. 2009.
  • [18] Thilakvathi, B., Shenbaga,S. D., Bhanu, K. ve Malaippan, M. EEG signal complexity analysis for schizophrenia during rest and mental activity, Biomed. Res., vol. 28, no. 1, pp. 1–9, 2017.
  • [19] Siuly, S. ve ark., A Computerized Method for Automatic Detection of Schizophrenia Using EEG Signals, IEEE Transactions on Neural Systems And Rehabilitation Engineering, vol. 28, no. 11, pp. 2390-2400, November 2020.
  • [20] Sabeti, M., Katebi, S. ve Boostani, R, Entropy and complexity measures for EEG signal classification of schizophrenic and control participants, Artif Intell Med., 2009;47(3):263–74. http://dx.doi.org/10.1016/j.artmed.2009.03.003
  • [21] Santos-Mayo, L., San-Jose-Revuelta, L M., Arribas JI., A computer-aided diagnosis system with EEG based on the p3b wave during an auditory odd-ball task in schizophrenia, IEEE Trans Biomed Eng., 2017;64(2):395–407. http://dx.doi.org/10.1109/TBME.2016.255884
  • [22] Krishnan, P. T., Raj, A. N. J., Balasubramanian, P., Chen, Y. Schizophrenia detection using MultivariateEmprical Mode Decomposition and entropy measures from multichannel EEG signal, Biocybernetics and Biomedical Engineering, vol. 40, pp. 1124-1139, 2020
  • [23] Liu, Y., Zhou W., Yuan, Q. ve Chen, S. Automatic seizure detection using wavelet transform and SVM in long-term intracranial EEG, IEEE Trans. Neural Syst. Rehabil. Eng., vol. 20, no. 6, pp. 749–755, 2012.
  • [24] Christianini, N., ve Shawe-Taylor.J. C., An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge, UK: Cambridge University Press, 2000.

Detection of Schizophrenia from Channel Based EEG Signals Using Hilbert Transform

Year 2020, Volume: 13 Issue: 2, 78 - 86, 16.12.2020

Abstract

Electroencephalography (EEG) maintains its popularity as an effective neuroimaging tool in studies with its multi-channel and high time resolution features for detection of neurological diseases. In this study, it was aimed to detect channel-based schizophrenia disease from EEG recordings using Hilbert Transform (HT). The imagenery components of the markers were analyzed with this transform, and the feature vectors consisting of patient / control groups were classified with the Support Vector Machine (SVM). The EEG data set used was obtained from 39 schizophrenia aged 10-14 and 39 healthy participants aged 11-13. The current recordings were taken during participant's eyes closed for 1 minute through 16 electrodes arranged according to the 10-20 system. The channels used in the study were selected from the relevant regions of the frontal, parietal, temporal, central and occipital lobes. In the classification process, training and test sets were divided with using k = 10 fold cross validation. In addition to the classification accuracy, Precision, Recall, F1-Score values were also calculated in the study. The best classification performance was obtained from the features from frontal lobe with 95,19% rate. The lowest classification performance was found to be the features taken from the temporal lobe region. Discrimination rate of healthy and patient groups shows that the proposed method can be applied in clinical treatments and can give an idea to the clinicians about the status of the patinets to be treated. In its current form, the proposed study serves promising results as a practical application that will contribute to the literature in the detection of schizophrenia.

References

  • [1] Rajinikanth, V., Satapathy, S. C., Fernandes, S. L., ve Nachiappan, S. Entropy based segmentation of tumor from brain MR images – a study with teaching learningbased optimization, Pattern Recognit. Lett., vol. 94, pp. 87–95, 2017.
  • [2] Dünya Sağlık Örgütü (WHO): https://www.who.int/mental_health/management/schizophrenia/en.
  • [3] Wang, Z. ve Oates, T. Imaging time-series to improve classification and imputation, IJCAI Int. Jt. Conf. Artif. Intell., vol. 2015-January, no. Ijcai, pp. 3939– 3945, 2015.
  • [4] Sanei S. ve Chambers, J. A. EEG Signal Processing. New York: Wiley, 2007.
  • [5] Subudhi, A., Acharya, U. R., Dash, M., Jena, S. ve Sabut, S. Automated approach for detection of ischemic stroke using Delaunay Triangulation in brain MRI images, Comput. Biol. Med., vol. 103, no. August, pp. 116–129, 2018.
  • [6] Kim, J. W., Lee Y. S., Han D. H., Min K. J., Lee J., ve Lee K., Diagnostic utility of quantitative EEG in un-medicated schizophrenia, Neurosci. Lett., vol. 589, pp. 126– 131, 2015.
  • [7] Dvey-Aharon, Z., Fogelson, N., Peled, A. ve Intrator, N., Schizophrenia detection and classification by advanced analysis of EEG recordings using a single electrode approach, PLoS One, vol. 10, no. 4, pp. 1–12, 2015.
  • [8] Johannesen, J. K., Bi, J., Jiang, R. J., Kenney, G. ve Chen, C.-M. A., Machine learning identification of EEG features predicting working memory performance in schizophrenia and healthy adults, Neuropsychiatr. Electrophysiol., vol. 2, no. 1, pp. 1–21, 2016.
  • [9] Santos-Mayo, L., San-Jose-Revuelta, L. M., ve Arribas, J. I., A computer-aided diagnosis system with EEG based on the p3b wave during an auditory odd-ball task in schizophrenia, IEEE Trans. Biomed. Eng., vol. 64, no. 2, pp. 395–407, 2017.
  • [10] Jahmunah , V. ve ark., Automated detection of schizophrenia using nonlinear signal processing methods, Artif. Intell. Med., vol. 100, no. June, p. 101698, 2019.
  • [11] Şeker, D. ve Ozerdem, M. S. Sağlıklı ve Şizofrenik EEG Zaman Serilerinin Sınıflandırılması ve İstatistiksel Analizi, TIPTEKNO’20, Medical Technologies Congress, 19-20 November 2020/Online.
  • [12] Şeker, M. ve Ozerdem, M. S., Şizofreni Teşhisinde Bir Nöro-işaretçi olarak EEG Uyumluluğu, 2020 28th Signal Processing and Communications Application Conference (SIU), Online.
  • [13] Borisov, S. V., Kaplan, A. Y., Gorbachevskaya, N. L., ve Kozlova, I. A. Analysis of EEG structural synchrony in adolescents with schizophrenic disorders, Hum. Physiol., vol. 31, no. 3, pp. 255–261, 2005.
  • [14] Devia, C. ve ark., EEG classification during scene free-viewing for schizophrenia detection, IEEE Trans. Neural Syst. Rehabil. Eng., vol. 27, no. 6, pp. 1193–1199, Jun. 2019.
  • [15] Piryatinska, A., Darkhovsky, B. ve Kaplan, A., Binary classification of multichannel-EEG records based on the _-complexity of continuous vector functions, Comput. Methods Programs Biomed., vol. 152, pp. 131–139, Dec. 2017.
  • [16] Sui, J. ve ark., Combination of FMRI-SMRI-EEG data improves discrimination of schizophrenia patients by ensemble feature selection, in Proc. 36th Annu. Int. Conf. IEEE Eng. Med. Biol. Soc., Aug. 2014, pp. 3889–3892.
  • [17] Boostani, R., Sadatnezhad, K. ve Sabeti, M., An efficient classifier to diagnose of schizophrenia based on the EEG signals, Expert Syst. Appl., vol. 36, no. 3, pp. 6492–6499, Apr. 2009.
  • [18] Thilakvathi, B., Shenbaga,S. D., Bhanu, K. ve Malaippan, M. EEG signal complexity analysis for schizophrenia during rest and mental activity, Biomed. Res., vol. 28, no. 1, pp. 1–9, 2017.
  • [19] Siuly, S. ve ark., A Computerized Method for Automatic Detection of Schizophrenia Using EEG Signals, IEEE Transactions on Neural Systems And Rehabilitation Engineering, vol. 28, no. 11, pp. 2390-2400, November 2020.
  • [20] Sabeti, M., Katebi, S. ve Boostani, R, Entropy and complexity measures for EEG signal classification of schizophrenic and control participants, Artif Intell Med., 2009;47(3):263–74. http://dx.doi.org/10.1016/j.artmed.2009.03.003
  • [21] Santos-Mayo, L., San-Jose-Revuelta, L M., Arribas JI., A computer-aided diagnosis system with EEG based on the p3b wave during an auditory odd-ball task in schizophrenia, IEEE Trans Biomed Eng., 2017;64(2):395–407. http://dx.doi.org/10.1109/TBME.2016.255884
  • [22] Krishnan, P. T., Raj, A. N. J., Balasubramanian, P., Chen, Y. Schizophrenia detection using MultivariateEmprical Mode Decomposition and entropy measures from multichannel EEG signal, Biocybernetics and Biomedical Engineering, vol. 40, pp. 1124-1139, 2020
  • [23] Liu, Y., Zhou W., Yuan, Q. ve Chen, S. Automatic seizure detection using wavelet transform and SVM in long-term intracranial EEG, IEEE Trans. Neural Syst. Rehabil. Eng., vol. 20, no. 6, pp. 749–755, 2012.
  • [24] Christianini, N., ve Shawe-Taylor.J. C., An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge, UK: Cambridge University Press, 2000.
There are 24 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Makaleler(Araştırma)
Authors

Ömer Türk 0000-0002-0060-1880

Mesut Şeker 0000-0001-9245-6790

Mehmet Siraç Özerdem 0000-0002-9368-8902

Publication Date December 16, 2020
Published in Issue Year 2020 Volume: 13 Issue: 2

Cite

APA Türk, Ö., Şeker, M., & Özerdem, M. S. (2020). Hilbert Dönüşümü Kullanılarak EEG İşaretlerinden Kanal Bazlı Şizofren Hastalığının Tespiti. Türkiye Bilişim Vakfı Bilgisayar Bilimleri Ve Mühendisliği Dergisi, 13(2), 78-86.
AMA Türk Ö, Şeker M, Özerdem MS. Hilbert Dönüşümü Kullanılarak EEG İşaretlerinden Kanal Bazlı Şizofren Hastalığının Tespiti. TBV-BBMD. December 2020;13(2):78-86.
Chicago Türk, Ömer, Mesut Şeker, and Mehmet Siraç Özerdem. “Hilbert Dönüşümü Kullanılarak EEG İşaretlerinden Kanal Bazlı Şizofren Hastalığının Tespiti”. Türkiye Bilişim Vakfı Bilgisayar Bilimleri Ve Mühendisliği Dergisi 13, no. 2 (December 2020): 78-86.
EndNote Türk Ö, Şeker M, Özerdem MS (December 1, 2020) Hilbert Dönüşümü Kullanılarak EEG İşaretlerinden Kanal Bazlı Şizofren Hastalığının Tespiti. Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi 13 2 78–86.
IEEE Ö. Türk, M. Şeker, and M. S. Özerdem, “Hilbert Dönüşümü Kullanılarak EEG İşaretlerinden Kanal Bazlı Şizofren Hastalığının Tespiti”, TBV-BBMD, vol. 13, no. 2, pp. 78–86, 2020.
ISNAD Türk, Ömer et al. “Hilbert Dönüşümü Kullanılarak EEG İşaretlerinden Kanal Bazlı Şizofren Hastalığının Tespiti”. Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi 13/2 (December 2020), 78-86.
JAMA Türk Ö, Şeker M, Özerdem MS. Hilbert Dönüşümü Kullanılarak EEG İşaretlerinden Kanal Bazlı Şizofren Hastalığının Tespiti. TBV-BBMD. 2020;13:78–86.
MLA Türk, Ömer et al. “Hilbert Dönüşümü Kullanılarak EEG İşaretlerinden Kanal Bazlı Şizofren Hastalığının Tespiti”. Türkiye Bilişim Vakfı Bilgisayar Bilimleri Ve Mühendisliği Dergisi, vol. 13, no. 2, 2020, pp. 78-86.
Vancouver Türk Ö, Şeker M, Özerdem MS. Hilbert Dönüşümü Kullanılarak EEG İşaretlerinden Kanal Bazlı Şizofren Hastalığının Tespiti. TBV-BBMD. 2020;13(2):78-86.

Article Acceptance

Use user registration/login to upload articles online.

The acceptance process of the articles sent to the journal consists of the following stages:

1. Each submitted article is sent to at least two referees at the first stage.

2. Referee appointments are made by the journal editors. There are approximately 200 referees in the referee pool of the journal and these referees are classified according to their areas of interest. Each referee is sent an article on the subject he is interested in. The selection of the arbitrator is done in a way that does not cause any conflict of interest.

3. In the articles sent to the referees, the names of the authors are closed.

4. Referees are explained how to evaluate an article and are asked to fill in the evaluation form shown below.

5. The articles in which two referees give positive opinion are subjected to similarity review by the editors. The similarity in the articles is expected to be less than 25%.

6. A paper that has passed all stages is reviewed by the editor in terms of language and presentation, and necessary corrections and improvements are made. If necessary, the authors are notified of the situation.

0

.   This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.