Otimizando uma CNN baseada em DenseNet para o diagnóstico de COVID19
Resumo
O principal método utilizado para o diagnóstico de COVID-19 é o RT-PCR, mas esse método ainda leva de 1 a 3 dias para gerar resultados, por isso se fazem necessários métodos que façam um diagnóstico rápido e efetivo do vírus. Um desses métodos que se mostra bastante eficiente é a utilização de Convolutional Neural Networks, que podem fazer o diagnóstico da doença por meio de radiografias do tórax ou tomografias computadorizadas. Assim, o nosso trabalho avalia a utilização do algoritmo Tree-structured Parzen Estimator para realizar a otimização de um modelo CNN especializado no diagnóstico de COVID-19 baseada na arquitetura DenseNet. Assim, o modelo construído neste trabalho atingiu um resultado promissor com uma acurácia de 96%, demonstrando a efetividade da utilização do algoritmo de otimização na construção da rede.
Referências
Alsharif, W., & Qurashi, A. (2021). Effectiveness of COVID-19 diagnosis and management tools: A review. Radiography, 27(2), 682-687.
O'Shea, Keiron, and Ryan Nash. "An introduction to convolutional neural networks." arXiv preprint arXiv:1511.08458 (2015).
Pavlova, M., Terhljan, N., Chung, A. G., Zhao, A., Surana, S., Aboutalebi, H., ... & Wong, A. (2021). COVID-Net CXR-2: An enhanced deep convolutional neural network design for detection of covid-19 cases from chest x-ray images. arXiv preprint arXiv:2105.06640.
Aslan, M. F., Unlersen, M. F., Sabanci, K., & Durdu, A. (2021). CNN-based transfer learning-BiLSTM network: A novel approach for COVID-19 infection detection. Applied Soft Computing, 98, 106912.
Al-Rakhami, M. S., Islam, M. M., Islam, M. Z., Asraf, A., Sodhro, A. H., & Ding, W. (2021). Diagnosis of COVID-19 from X-rays using combined CNN-RNN architecture with transfer learning. MedRxiv, 2020-08.
Aslan, M. F., Sabanci, K., Durdu, A., & Unlersen, M. F. (2022). COVID-19 diagnosis using state-of-the-art CNN architecture features and Bayesian Optimization. Computers in Biology and Medicine, 105244.
Costa, G., Paiva, A., Braz Júnior, G., & Ferreira, M. (2021). COVID-19 automatic diagnosis with CT images using the novel Transformer architecture. In Anais do XXI Simpósio Brasileiro de Computação Aplicada à Saúde, (pp. 293-301). Porto Alegre: SBC. doi:10.5753/sbcas.2021.16073
Wang, L., Lin, Z. Q., & Wong, A. (2020). Covid-net: A tailored deep convolutional neural network design for detection of covid-19 cases from chest x-ray images. Scientific Reports, 10(1), 1-12.
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4700-4708).
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
Huang, G., Sun, Y., Liu, Z., Sedra, D., & Weinberger, K. Q. (2016, October). Deep networks with stochastic depth. In European conference on computer vision (pp. 646-661). Springer, Cham.
Bergstra, J., Bardenet, R., Bengio, Y., & Kégl, B. (2011). Algorithms for hyper-parameter optimization. Advances in neural information processing systems, 24.
Jones, D. R. (2001). A taxonomy of global optimization methods based on response surfaces. Journal of global optimization, 21(4), 345-383.
Hutter, F., Hoos, H. H., & Leyton-Brown, K. (2011, January). Sequential model-based optimization for general algorithm configuration. In International conference on learning and intelligent optimization (pp. 507-523). Springer, Berlin, Heidelberg.
Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019, July). Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 2623-2631).
Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
De Boer, P. T., Kroese, D. P., Mannor, S., & Rubinstein, R. Y. (2005). A tutorial on the cross-entropy method. Annals of operations research, 134(1), 19-67.
O'Shea, Keiron, and Ryan Nash. "An introduction to convolutional neural networks." arXiv preprint arXiv:1511.08458 (2015).
Pavlova, M., Terhljan, N., Chung, A. G., Zhao, A., Surana, S., Aboutalebi, H., ... & Wong, A. (2021). COVID-Net CXR-2: An enhanced deep convolutional neural network design for detection of covid-19 cases from chest x-ray images. arXiv preprint arXiv:2105.06640.
Aslan, M. F., Unlersen, M. F., Sabanci, K., & Durdu, A. (2021). CNN-based transfer learning-BiLSTM network: A novel approach for COVID-19 infection detection. Applied Soft Computing, 98, 106912.
Al-Rakhami, M. S., Islam, M. M., Islam, M. Z., Asraf, A., Sodhro, A. H., & Ding, W. (2021). Diagnosis of COVID-19 from X-rays using combined CNN-RNN architecture with transfer learning. MedRxiv, 2020-08.
Aslan, M. F., Sabanci, K., Durdu, A., & Unlersen, M. F. (2022). COVID-19 diagnosis using state-of-the-art CNN architecture features and Bayesian Optimization. Computers in Biology and Medicine, 105244.
Costa, G., Paiva, A., Braz Júnior, G., & Ferreira, M. (2021). COVID-19 automatic diagnosis with CT images using the novel Transformer architecture. In Anais do XXI Simpósio Brasileiro de Computação Aplicada à Saúde, (pp. 293-301). Porto Alegre: SBC. doi:10.5753/sbcas.2021.16073
Wang, L., Lin, Z. Q., & Wong, A. (2020). Covid-net: A tailored deep convolutional neural network design for detection of covid-19 cases from chest x-ray images. Scientific Reports, 10(1), 1-12.
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4700-4708).
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
Huang, G., Sun, Y., Liu, Z., Sedra, D., & Weinberger, K. Q. (2016, October). Deep networks with stochastic depth. In European conference on computer vision (pp. 646-661). Springer, Cham.
Bergstra, J., Bardenet, R., Bengio, Y., & Kégl, B. (2011). Algorithms for hyper-parameter optimization. Advances in neural information processing systems, 24.
Jones, D. R. (2001). A taxonomy of global optimization methods based on response surfaces. Journal of global optimization, 21(4), 345-383.
Hutter, F., Hoos, H. H., & Leyton-Brown, K. (2011, January). Sequential model-based optimization for general algorithm configuration. In International conference on learning and intelligent optimization (pp. 507-523). Springer, Berlin, Heidelberg.
Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019, July). Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 2623-2631).
Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
De Boer, P. T., Kroese, D. P., Mannor, S., & Rubinstein, R. Y. (2005). A tutorial on the cross-entropy method. Annals of operations research, 134(1), 19-67.
Publicado
07/06/2022
Como Citar
COSTA, Gabriel de Jesus S.; OLIVEIRA, Marcus Vinicius; FREITAS, Mario; BESSA, Matheus de Lima; BRAZ JUNIOR, Geraldo; ALMEIDA, João Dallyson S. de; PAIVA, Anselmo C..
Otimizando uma CNN baseada em DenseNet para o diagnóstico de COVID19. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 22. , 2022, Teresina.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2022
.
p. 289-298.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2022.222666.
