Uma abordagem baseada em redes neurais artificiais sobre o espectro de potência de eletroencefalogramas para o auxílio médico na classificação de crises epiléticas

  • Dionathan Luan de Vargas UTFPR
  • Jefferson Tales Oliva UTFPR
  • Marcelo Teixeira UTFPR

Resumo


A epilepsia é a quarta enfermidade neurológica mais comum e atinge aproximadamente 1% da população mundial. O diagnóstico é, em geral, amparado por um eletroencefalograma (EEG), cuja análise depende da interpretação médica, o que por vezes gera incongruência de diagnóstico, além de ser um trabalho tedioso, impreciso e propenso a erros. Este trabalho propõe um método de reconhecimento automático de padrões baseado em aprendizado de máquina e engenharia de características aplicadas ao espectros de potência de segmentos de EEGs. Resultados sugerem a possibilidade de detectar crises epilépticas com uma precisão superior a 80% em bases de dados já utilizadas na literatura.

Referências

Andrzejak, R. G., Lehnertz, K., Mormann, F., Rieke, C., David, P., and Elger, C. E. (2001). Indications of nonlinear deterministic and nite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state. Physical Review E, 64(6):061907.

Aydemir, E., Tuncer, T., and Dogan, S. (2020). A tunable-Q wavelet transform and quadruple symmetric pattern based EEG signal classication method. Medical hypotheses, 134:109519.

Babadi, B. and Brown, E. N. (2014). A review of multitaper spectral analysis. IEEE Transactions on Biomedical Engineering, 61(5):1555–1564.

Bhattacharyya, A. and Pachori, R. B. (2017). A multivariate approach for patient-specic EEG seizure detection using empirical wavelet transform. IEEE Transactions on Biomedical Engineering, 64(9):2003–2015.

Clevert, D.-A., Unterthiner, T., and Hochreiter, S. (2015). Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289.

Cura, O. K. and Akan, A. (2021). Analysis of epileptic EEG signals by using dynamic mode decomposition and spectrum. Biocybernetics and Biomedical Engineering, 41(1):28–44.

Cybenko, G. (1989). Approximation by superpositions of a sigmoidal function. Mathe matics of control, signals and systems, 2(4):303–314.

David Freedman, Robert Pisani, R. P. (2007). Statistics. W. W. Norton Co, 4th edition.

Faceli, K., Lorena, A. C., Gama, J., Carvalho, A., et al. (2011). Inteligência articial: Uma abordagem de aprendizado de máquina. Rio de Janeiro: LTC, 2:192.

Fisher, R. S., Scharfman, H. E., and DeCurtis, M. (2014). How can we identify ictal and interictal abnormal activity? Issues in Clinical Epileptology: A View from the Bench, pages 3–23.

Freeman, W. and Quiroga, R. Q. (2012). Imaging brain function with EEG: advanced temporal and spatial analysis of electroencephalographic signals. Springer Science & Business Media.

Fukushima, K. (1969). Visual feature extraction by a multilayered network of analog threshold elements. IEEE Transactions on Systems Science and Cybernetics, 5(4):322– 333.

Gallucci Neto, J. and Marchetti, R. L. (2005). Aspectos epidemiológicos e relevância dos transtornos mentais associados à epilepsia. Brazilian Journal of Psychiatry, 27(4):323– 328.

Gao, X., Yan, X., Gao, P., Gao, X., and Zhang, S. (2020). Automatic detection of epileptic seizure based on approximate entropy, recurrence quantication analysis and convolutional neural networks. Articial intelligence in medicine, 102:101711.

Häfele, C. A., Freitas, M. P., Gervini, B. L., de Carvalho, R. M., and Rombaldi, A. J. (2018). Who are the individuals diagnosed with epilepsy using the public health system in the city of pelotas, southern brazil? Epilepsy & Behavior, 78:84–90.

Hwang, S. T., Goodman, T., and Stevens, S. J. (2019). Painful seizures: a review of epileptic ictal pain. Current pain and headache reports, 23(11):1–7.

Kalogirou, S. A. (2001). Articial neural networks in renewable energy systems applica tions: a review. Renewable and sustainable energy reviews, 5(4):373–401.

Keeton, G. (2015). What is crest factor and why is it important? https://shorturl.at/yB234, Abril.

Klambauer, G., Unterthiner, T., Mayr, A., and Hochreiter, S. (2017). Self-normalizing neural networks. arXiv preprint arXiv:1706.02515.

Kramer, C. and Gerhardt, H. J. (2012). Advances in wind engineering. Elsevier.

Lewis, D. and Gale, W. (1994). Training text classiers by uncertainty sampling. In seventeenth annual international ACM SIGIR conference on research and development in information retrieval, pages 3–12.

Li, Y., Liu, Y., Cui, W.-G., Guo, Y.-Z., Huang, H., and Hu, Z.-Y. (2020). Epileptic seizure detection in EEG signals using a unied temporal-spectral squeeze-andexcitation network. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 28(4):782–794.

Manjusha, M. and Harikumar, R. (2016). Performance analysis of KNN classier and Kmeans clustering for robust classication of epilepsy from EEG signals. In 2016 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), pages 2412–2416. IEEE.

Mansour, A. M., Obeidat, M. A., and Al-Aqtash, M. (2020). Data mining based approach for evaluation of EEG signals for epilepsy detection. WSEAS Transactions on Biology and Biomedicine.

Nair, V. and Hinton, G. E. Rectied linear units improve restricted boltzmann machines. In Icml. https://redirect.is/xg939zy, Abril.

Nicolaou, N. and Georgiou, J. (2012). Detection of epileptic electroencephalogram based on permutation entropy and support vector machines. Expert Systems with Applications, 39(1):202–209.

Oliva, J. T. (2019). Geração automática de laudos médicos para o diagnóstico de epilepsia por meio do processamento de eletroencefalogramas utilizando aprendizado de máquina. PhD thesis, Universidade de São Paulo.

Oliva, J. T. and Rosa, J. L. G. (2019). Classication for EEG report generation and epilepsy detection. Neurocomputing, 335:81–95.

OMS (2019). Epilepsy: a public health imperative. https://shorturl.at/yKNQ6, Março.

Raghu, S., Sriraam, N., Hegde, A. S., and Kubben, P. L. (2019). A novel approach for classication of epileptic seizures using matrix determinant. Expert Systems with Applications, 127:323–341.

Riaz, F., Hassan, A., Rehman, S., Niazi, I. K., and Dremstrup, K. (2015). Emd-based temporal and spectral features for the classication of EEG signals using supervised learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 24(1):28–35.

Rumelhart, D. E., Hinton, G. E., and Williams, R. J. (1986). Learning representations by back-propagating errors. nature, 323(6088):533–536.

Sharma, M., Pachori, R. B., and Acharya, U. R. (2017). A new approach to characterize epileptic seizures using analytic time-frequency exible wavelet transform and fractal dimension. Pattern Recognition Letters, 94:172–179.

Sharmila, A. and Geethanjali, P. (2016). DWT based detection of epileptic seizure from EEG signals using naive bayes and kNN classiers. Ieee Access, 4:7716–7727.

Shin, H. W., Jewells, V., Hadar, E., Fisher, T., and Hinn, A. (2014). Review of epilepsyetiology, diagnostic evaluation and treatment. Int J Neurorehabilitation, 1(130):2376– 0281.

Siuly, S., Alcin, O. F., Bajaj, V., Sengur, A., and Zhang, Y. (2018). Exploring hermite transformation in brain signal analysis for the detection of epileptic seizure. IET Science, Measurement & Technology, 13(1):35–41.

Slepian, D. and Pollak, H. O. (1961). Prolate spheroidal wave functions, Fourier analysis and uncertainty—I. Bell System Technical Journal, 40(1):43–63.

Thomson, D. J. (1982). Spectrum estimation and harmonic analysis. Proceedings of the IEEE, 70(9):1055–1096.

Tsipouras, M. G. (2019). Spectral information of EEG signals with respect to epilepsy classication. EURASIP Journal on Advances in Signal Processing, 2019(1):1–17.

Tzallas, A. T., Tsipouras, M. G., Tsalikakis, D. G., Karvounis, E. C., Astrakas, L., Konitsiotis, S., and Tzaphlidou, M. (2012). Automated epileptic seizure detection methods: a review study. Epilepsy-histological, electroencephalographic and psychological aspects, pages 75–98.

Upadhya, S. S., Cheeran, A., and Nirmal, J. H. (2018). Thomson multitaper MFCC and PLP voice features for early detection of parkinson disease. Biomedical Signal Processing and Control, 46:293–301.

Wen, T. and Zhang, Z. (2018). Deep convolution neural network and autoencoders-based unsupervised feature learning of EEG signals. IEEE Access, 6:25399–25410.

Zhang, T. and Chen, W. (2016). LMD based features for the automatic seizure detection of EEG signals using SVM. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(8):1100–1108.

Zhou, S.-M., Gan, J. Q., and Sepulveda, F. (2008). Classifying mental tasks based on features of higher-order statistics from EEG signals in brain–computer interface. Information Sciences, 178(6):1629–1640.
Publicado
15/06/2021
VARGAS, Dionathan Luan de; OLIVA, Jefferson Tales; TEIXEIRA, Marcelo. Uma abordagem baseada em redes neurais artificiais sobre o espectro de potência de eletroencefalogramas para o auxílio médico na classificação de crises epiléticas. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 21. , 2021, Evento Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2021 . p. 141-152. ISSN 2763-8952. DOI: https://doi.org/10.5753/sbcas.2021.16060.

##plugins.generic.recommendByAuthor.heading##