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

Unlike adults, neonates do not always show clinical symptoms during seizures. Therefore, uncontrolled seizures lead to severe brain damage. Timely recognition of seizures plays a crucial role for neonates. In this study, a deep transfer learning approach was proposed for automatic detection of seizures on the C4-P4 channel using electroencephalography (EEG) signals from neonates. The EEG signals were used in 1D and 2D dimensions to ensure performance, robust functionality, and a clinically acceptable level of detection accuracy. The pre-trained deep learning models Alexnet, ResNet, GoogleNet and VggNet were used in the study. Spectrograms were obtained by converting 1-dimensional signal data into 2- dimensional images, and then classification was performed for both the 1D and 2D datasets. For 1D classification, the highest performance was obtained by VggNet architecture with 91.67%, while 2D classification was obtained by AlexNet and ResNet architecture with 95.83%. The use of spectrograms significantly improved classification performance and made neonatal seizure detection and decision-making more clinically reliable.

PDF

___

[1] A. Temko, E. Thomas, W. Marnane, G. Lightbody and G. Boylan “EEG-based neonatal seizure detection with support vector machines,” Clinical Neurophysiology, vol. 122, no. 3, pp: 464-473, 2011.
[2] E.P. Yıldız B. Tatlı, N. Aydınlı, M. Çalışkan and M. Özmen “Yeni doğan konvülziyonları,” Çocuk Dergisi, vol. 13, no. 3, pp: 89-94, 2013.
[3] P. Boonyakitanont, A. Lek-uthai, K. Chomtho and J. Songsiri, “A review of feature extraction and performance evaluation in epileptic seizure detection using EEG,” Biomedical Signal Processing and Control, vol. 57, pp: 101702, 2020.
[4] R. Mouleeshuwarapprabu and N. Kasthuri, “Nonlinear vector decomposed neural network-based EEG signal feature extraction and detection of seizure,” Microprocessors and Microsystems, vol. 76, pp: 103075, 2020.
[5] B.P. Prathaban and R. Balasubramania, “Dynamic learning framework for epileptic seizure prediction using sparsity-based EEG reconstruction with optimized CNN classifier,” Expert Systems with Applications, vol. 170, pp: 114533, 2021.
[6] M. Albayrak and E. Köklükaya, “Eeg sinyallerindeki epileptiform aktivitenin veri madenciliği süreci ile tespiti,” Technological Applied Sciences, vol. 4, no. 1, pp: 1-12, 2009.
[7] Ö. Yıldırım, M. Talo, B. Ay, U.B. Baloğlu, G. Aydın and U.R. Acharya, “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, pp: 103387, 2019.
[8] N J. Stevenson, K. Tapani, L. Lauronen and Vanhatalo. S, “A dataset of neonatal EEG recordings with seizure annotations,” Scientific Data, vol. 6, pp: 190039, 2019.
[9] M. Açıkoğlu and S.A. Tuncer, “Incorporating feature selection methods into a machine learning-based neonatal seizure diagnosis,” Medical Hypotheses, vol. 135, pp: 0306-9877, 2020.
[10] I. Ullah, M. Hussain and E. Qazi, “Aboalsamh H. An automated system for epilepsy detection using EEG brain signals based on deep learning approach,” Expert Systems with Applications, vol. 107, pp: 61-71, 2018.
[11] Ö. Yıldırım, U.B. Baloglu and U.R. Acharya, “A deep convolutional neural network model for automated identification of abnormal EEG signals,” Neural Comput & Applic, vol. 32, pp: 15857– 15868, 2020.
[12] H. Qin, B. Deng, J. Wang, G. Yi, R. Wang and Z. Zhang, “Deep multi-scale feature fusion convolutional neural network for automatic epilepsy detection using EEG signals,” 39th Chinese Control Conference (CCC), Shenyang, China, pp: 7061-7066, 2020.
[13] U. R. Acharya, L. O. Shu, Y. Hagiwara, H. T. Jen and H. Adeli, “Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals,” Computers in Biology and Medicine, vol. 100, pp: 270-278, 2018.
[14] R. Rosas-Romero, E. Guevara, K. Peng, D.K. Nguyen, F. Lesage, P. Poulio and W-E, “Prediction of epileptic seizures with convolutional neural networks and functional near-infrared spectroscopy signals,” Computers in Biology and Medicine, vol. 111, pp: 103355, 2019.
[15] A. O’Shea, G. Lightbody, G. Boyla and A. Temko, “Neonatal seizure detection from raw multi-channel EEG using a fully convolutional architecture,” Neural Networks, vol. 123, pp: 12-25, 2020.
[16] S. Ryu, S. Back, S. Lee, H. Seo, C. Park, K. Lee and DS. Kim, “Pilot study of a single-channel EEG seizure detection algorithm using machine learning,” Childs Nerv Syst. vol. 37, no. 7, pp: 2239-2244, 2021.
[17] A. Krizhevsky, I. Sutskever and G.E. Hinton, “Imagenet classification with deep convolutional neural networks,” In Advances in neural information processing systems, vol. 25, no. 2, pp: 1097-1105, 2012.
[18] B. Buyukarikan and E. Ülker, “Aydınlatma özniteliği kullanılarak Evrişimsel Sinir Ağı modelleri ile meyve sınıflandırma,” Uludağ University Journal of The Faculty of Engineering. vol. 25, pp: 81-100, 2020.
[19] C. Szegedy et al, “Going deeper with convolutions,” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, MA, USA,1-9, 2015.
[20] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition” arXiv preprint arXiv:1409-1556, 2014
[21] S. Zagoruyko and K. Nikos, “Wide residual networks,” arXiv preprint 27. arXiv:1605-07146, 2016
[22] S. Toraman, S.A. Tuncer and F. Balgetir, “Is it possible to detect cerebral dominance via EEG signals by using deep learning?,” Medical Hypotheses, vol. 131, pp: 109315, 2019.