Evrişimsel Sinir Ağları Kullanılarak Yeni Doğanlarda Nöbet Tespiti için 1D ve 2D EEG Sinyallerinin Sınıflandırılması

Abstract

Yeni doğanlar, yetişkinlerin aksine nöbetler sırasında her zaman klinik belirtiler göstermezler. Bu nedenle kontrolsüz nöbetler ciddi beyin hasarına yol açar. Nöbetlerin zamanında tespiti, yeni doğan bebekler için hayati bir rol oynar. Bu çalışmada yeni doğanların elektroensefalografi (EEG) sinyalleri kullanılarak C4-P4 kanalında otomatik nöbet tespiti için derin transfer öğrenme yaklaşımı önerilmiştir. EEG sinyalleri, performans, sağlam işlevsellik ve klinik olarak kabul edilebilir bir algılama doğruluğu seviyesi sağlamak için 1B ve 2B boyutlarda kullanılmıştır. Çalışmada önceden eğitilmiş derin öğrenme modelleri Alexnet, ResNet, GoogleNet ve VggNet kullanılmıştır. 1 boyutlu sinyal verilerinin 2 boyutlu görüntülere dönüştürülmesiyle spektrogramlar elde edilmiş ve ardından hem 1 boyutlu hem de 2 boyutlu veri setinde sınıflandırma yapılmıştır. 1B sınıflandırmada en yüksek performans %91,67 ile VggNet mimarisinden, 2B sınıflandırma ise %95,83 ile AlexNet ve ResNet mimarisinden elde edilmiştir. Spektrogramların kullanımı, sınıflandırma performansını büyük ölçüde iyileştirdi ve yeni doğanlarda nöbet tespiti ve kararı klinik olarak daha güvenilir hale getirdi.

Keywords

• Yeni doğan Nöbeti
• EEG Sinyali
• C4-P4 kanalı
• Evrişimli Sinir Ağı

Classification of 1D and 2D EEG Signals for Seizure Detection in the Newborn Using Convolutional Neural Networks

Abstract

Newborns do not always show clinical symptoms during seizures unlike adults. Therefore, uncontrolled seizures lead to serious brain damage. Timely detection of seizures plays a vital role for newborn babies. In this study, a deep transfer learning approach was proposed for automatic seizure detection on the C4-P4 channel using electroencephalography (EEG) signals of newborns. EEG signals have been used in 1D and 2D dimensions to ensure performance, robust functionality, and a clinically acceptable level of detection accuracy. Pre-trained deep learning models Alexnet, ResNet, GoogleNet and VggNet were used in the study. Spectrograms were obtained by converting 1-dimensional signal data to 2-dimensional images, and then the classification was made on both 1D and 2D data set. In 1D classification, the highest performance was obtained from VggNet architecture with 91.67%, while 2D classification was obtained from AlexNet and ResNet architecture with 95.83%. The use of spectrograms has greatly improved the classification performance and made seizure detection and decision clinically more reliable in newborns.

Keywords

• Newborn Seizure
• EEG Signal
• C4-P4 channel
• Convolutional Neural Network

References

1. 1. Temko A., Thomas E., Marnane W., Lightbody G., Boylan G. 2011. EEG-based neonatal seizure detection with Support Vector Machines. Clinical Neurophysiology, vol.122(3), p.464-473.
2. 2. Yıldız E.P., Tatlı B., Aydınlı N., Çalışkan M., Özmen M. 2013. Yenidoğan Konvülziyonları. Çocuk Dergisi, vol.13(3), p.89-94.
3. 3. Boonyakitanont P., Lek-uthai A., Chomtho K., Songsiri J. 2020. A review of feature extraction and performance evaluation in epileptic seizure detection using EEG. Biomedical Signal Processing and Control, vol.57, 101702.
4. 4. Mouleeshuwarapprabu R., Kasthuri N. 2020. Nonlinear vector decomposed neural network-based EEG signal feature extraction and detection of seizure. Microprocessors and Microsystems, vol.76, 103075.
5. 5. Prathaban B.P., Balasubramanian R. 2021. Dynamic learning framework for epileptic seizure prediction using sparsity-based EEG Reconstruction with Optimized CNN classifier. Expert Systems with Applications, vol.170, 114533
6. 6. Yildirim Ö., Talo M., Ay B., Baloglu U.B., Aydin G., Acharya U.R. 2019. Automated detection of diabetic subject using pre-trained 2D-CNN models with frequency spectrum images extracted from heart rate signals, Computers in Biology and Medicine, vol.113, 103387.
7. 7. Ullah I., Hussain M., Qazi E. 2018. Aboalsamh H. An automated system for epilepsy detection using EEG brain signals based on deep learning approach. Expert Systems with Applications, vol.107, p.61-71.
8. 8. Yıldırım Ö., Baloglu U.B., Acharya U.R. 2020. A deep convolutional neural network model for automated identification of abnormal EEG signals. Neural Comput & Applic,vol.32, 15857–15868.

9. 9. Qin H., Deng B., Wang J., Yi G., Wang R., Zhang Z. 2020. Deep Multi-scale Feature Fusion Convolutional Neural Network for Automatic Epilepsy Detection Using EEG Signals. 2020 39th Chinese Control Conference (CCC), Shenyang, China, p.7061-7066.
10. 10. Acharya U. R., Shu L. O., Hagiwara Y., Jen H. T., Adeli H. 2018. Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Computers in Biology and Medicine, vol.100, p.270-278.
11. 11. Rosas-Romero R., Guevara E., Peng K., Nguyen D.K., Lesage F., Poulio, P., Lima-Saad W-E. 2019. Prediction of epileptic seizures with convolutional neural networks and functional near-infrared spectroscopy signals. Computers in Biology and Medicine, vol.111, 103355.
12. 12. O’Shea A., Lightbody G., Boyla G., Temko, A. 2020. Neonatal seizure detection from raw multi-channel EEG using a fully convolutional architecture. Neural Networks, vol. 123, p.12-25.
13. 13. Krizhevsky A., Sutskever I. Hinton G.E. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, 25(2), 1097-1105, 201.
14. 14. Szegedy C., et al.2015. Going deeper with convolutions, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, MA, USA, pp. 1-9, doi: 10.1109/CVPR.2015.7298594.
15. 15. Simonyan K., Zisserman A. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
16. 16. Zagoruyko S., Nikos K.2016. Wide residual networks. arXiv preprint 27. arXiv:1605.07146.
17. 17. Toraman S., Tuncer S.A., Balgetir F. 2019. Is it possible to detect cerebral dominance via EEG signals by using deep learning?. Medical Hypotheses, vol.131, 109315.