Detecção de pneumonia usando redes neurais convolucionais treinadas com destilação do conhecimento obscuro
Resumo
A pneumonia é definida como inflamação do tecido pulmonar devido a um agente infeccioso, pode ser causada por um vírus ou por uma bactéria. É uma infecção comum e afeta principalmente idosos e crianças. Atualmente, o exame de raio X do tórax é frequentemente a melhor maneira de diagnosticar a doença. Nesse trabalho, imagens de raio X são usadas como base para diagnóstico de pacientes (saúde normal ou com pneumonia) aplicando-se para isso redes neurais convolucionais treinadas com a técnica de destilação do conhecimento obscuro. Esta técnica de treinamento é capaz de melhorar o desempenho de uma rede neural, permitindo que uma rede de arquitetura simples e menos custosa computacionalmente (modelo aprendiz) possa atingir um desempenho próximo ao de um modelo mais complexo, chamado de modelo professor. Os resultados obtidos demonstram a viabilidade da técnica.
Palavras-chave:
Aprendizagem de Máquina, Inteligência Artificial, Processamento Digital de Imagens, Reconhecimento de Padrões, Visão Computacional
Referências
Ba, J., & Caruana, R. (2014). Do deep nets really need to be deep?. In Advances in neural information processing systems (pp. 2654-2662).
Chouhan, V. et al. (2020). A Novel Transfer Learning Based Approach for Pneumonia Detection in Chest X-ray Images. Applied Sciences, 10(2), 559.
Franquet, T. (2001). Imaging of pneumonia: trends and algorithms. European Respiratory Journal, 18(1), 196-208.
Gong, W., Chen, H., Zhang, Z., Zhang, M., Wang, R., Guan, C., & Wang, Q. (2019). A novel deep learning method for intelligent fault diagnosis of rotating machinery based on improved CNN-SVM and multichannel data fusion. Sensors, 19(7), 1693.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press.
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).
Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531.
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).
Kermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C., Liang, H., Baxter, S. L., ... & Dong, J. (2018). Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 172(5), 1122-1131.
Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097-1105).
Längkvist, M., Karlsson, L., and Loutfi, A. (2014). A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recognition Letters, 42:11– 24.
Rajpurkar, P. et al. (2017). Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv:1711.05225.
Russakovsky, O. et al. (2015). Imagenet large scale visual recognition challenge. International journal of computer vision, 115(3), 211-252.
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2818-2826).
Szegedy, C. et al. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1-9).
Tang, Z., Wang, D., & Zhang, Z. (2016, March). Recurrent neural network training with dark knowledge transfer. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 5900-5904). IEEE.
World Health Organization. (2001). Standardization of interpretation of chest radiographs for the diagnosis of pneumonia in children (No. WHO/V&B/01.35). World Health Organization.
Chouhan, V. et al. (2020). A Novel Transfer Learning Based Approach for Pneumonia Detection in Chest X-ray Images. Applied Sciences, 10(2), 559.
Franquet, T. (2001). Imaging of pneumonia: trends and algorithms. European Respiratory Journal, 18(1), 196-208.
Gong, W., Chen, H., Zhang, Z., Zhang, M., Wang, R., Guan, C., & Wang, Q. (2019). A novel deep learning method for intelligent fault diagnosis of rotating machinery based on improved CNN-SVM and multichannel data fusion. Sensors, 19(7), 1693.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press.
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).
Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531.
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).
Kermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C., Liang, H., Baxter, S. L., ... & Dong, J. (2018). Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 172(5), 1122-1131.
Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097-1105).
Längkvist, M., Karlsson, L., and Loutfi, A. (2014). A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recognition Letters, 42:11– 24.
Rajpurkar, P. et al. (2017). Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv:1711.05225.
Russakovsky, O. et al. (2015). Imagenet large scale visual recognition challenge. International journal of computer vision, 115(3), 211-252.
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2818-2826).
Szegedy, C. et al. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1-9).
Tang, Z., Wang, D., & Zhang, Z. (2016, March). Recurrent neural network training with dark knowledge transfer. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 5900-5904). IEEE.
World Health Organization. (2001). Standardization of interpretation of chest radiographs for the diagnosis of pneumonia in children (No. WHO/V&B/01.35). World Health Organization.
Publicado
26/10/2020
Como Citar
SILVA, José Vitor; MATOS, Leonardo.
Detecção de pneumonia usando redes neurais convolucionais treinadas com destilação do conhecimento obscuro. In: ESCOLA REGIONAL DE COMPUTAÇÃO BAHIA, ALAGOAS E SERGIPE (ERBASE), 20. , 2020, Arapiraca-AL.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 51-60.
