ChronoNet: A Deep Recurrent Neural Network for Abnormal EEG Identification

  • Subhrajit RoyEmail author
  • Isabell Kiral-Kornek
  • Stefan Harrer
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11526)


Brain-related disorders such as epilepsy can be diagnosed by analyzing electroencephalograms (EEG). However, manual analysis of EEG data requires highly trained clinicians, and is a procedure that is known to have relatively low inter-rater agreement (IRA). Moreover, the volume of the data and the rate at which new data becomes available make manual interpretation a time-consuming, resource-hungry, and expensive process. In contrast, automated analysis of EEG data offers the potential to improve the quality of patient care by shortening the time to diagnosis and reducing manual error. In this paper, we focus on one of the first steps in interpreting an EEG session - identifying whether the brain activity is abnormal or normal. To address this specific task, we propose a novel recurrent neural network (RNN) architecture termed ChronoNet which is inspired by recent developments from the field of image classification and designed to work efficiently with EEG data. ChronoNet is formed by stacking multiple 1D convolution layers followed by deep gated recurrent unit (GRU) layers where each 1D convolution layer uses multiple filters of exponentially varying lengths and the stacked GRU layers are densely connected in a feed-forward manner. We used the recently released TUH Abnormal EEG Corpus dataset for evaluating the performance of ChronoNet. Unlike previous studies using this dataset, ChronoNet directly takes time-series EEG as input and learns meaningful representations of brain activity patterns. ChronoNet outperforms previously reported results on this dataset thereby setting a new benchmark.


Machine learning Recurrent neural networks Electroencephalography 


  1. 1.
  2. 2.
    Acharya, J.N., et al.: American clinical neurophysiology society guideline 3: a proposal for standard montages to be used in clinical EEG. J. Clin. Neurophysiol. 33(4), 312–316 (2016)CrossRefGoogle Scholar
  3. 3.
    Cho, K., et al.: On the properties of neural machine translation: encoder-decoder approaches. arXiv:1409.1259v2, September 2014
  4. 4.
    Golmohammadi, M., et al.: Deep architectures for automated seizure detection in scalp EEGs. arXiv:1712.09776 [cs, eess, q-bio, stat], December 2017
  5. 5.
    Goodfellow, I., et al.: Deep Learning. The MIT Press, Cambridge (2016)zbMATHGoogle Scholar
  6. 6.
    Graves, A.: Generating sequences with recurrent neural networks. arXiv:1308.0850 [cs], August 2013
  7. 7.
    Homan, R.W.: The 10-20 electrode system and cerebral location. Am. J. EEG Technol. 28(4), 269–279 (1988)CrossRefGoogle Scholar
  8. 8.
    Huang, G., et al.: Densely connected convolutional networks. arXiv:1608.06993, August 2016
  9. 9.
    Chung, J., Gulcehre, C.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv:1412.3555 [cs], December 2014
  10. 10.
    He, K., et al.: Deep residual learning for image recognition. arXiv:1512.03385 [cs], December 2015
  11. 11.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv:1412.6980 [cs], December 2014
  12. 12.
    López, S.: Automated interpretation of abnormal adult electroencephalograms. MS thesis, Temple University (2017).
  13. 13.
    López, S., et al.: Automated Identification of Abnormal Adult EEGs. IEEE Signal Process. Med. Biol. Symp. 2015 (2015)Google Scholar
  14. 14.
    Obeid, I., Picone, J.: The temple university hospital EEG data corpus. Front. Neurosci. 10 (2016).
  15. 15.
    Pennington, J., et al.: GloVe: Global vectors for word representation. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)Google Scholar
  16. 16.
    Schirrmeister, R.T., et al.: Deep learning with convolutional neural networks for decoding and visualization of EEG pathology. CoRR abs/1708.08012 (2017)Google Scholar
  17. 17.
    Szegedy, C., et al.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9, June 2015Google Scholar
  18. 18.
    Tang, Y., et al.: Question detection from acoustic features using recurrent neural network with gated recurrent unit. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6125–6129, March 2016Google Scholar
  19. 19.
    Yin, W., et al.: Comparative study of CNN and RNN for natural language processing. arXiv:1702.01923 [cs], February 2017

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.IBM Research - AustraliaSouthbankAustralia

Personalised recommendations