Análise comparativa da influência de otimizadores no desempenho de uma CNN para detecção do câncer de mama
Resumo
O campo da inteligência artificial (IA) apresenta notáveis avanços na medicina. Estudos analisam a aplicação de Redes Neurais Convolucionais para a detecção de câncer de mama. Neste artigo, é realizada uma análise comparativa entre os métodos de otimização (Adam, Adadelta, Adagrad, Adamax, Nadam, RMSprop) aplicados a uma arquitetura VggNet16 para a classificação de neoplasias em imagens histopatológicas. Os experimentos foram realizados com a criação de modelos para os fatores de ampliação (40x, 100x, 200x, 400x) das imagens extraídas do dataset BreakHis. O otimizador Adam obteve o melhor resultado para o conjunto de imagens, especificamente na base 400x.
Referências
Alanazi SA, Kamruzzaman MM, I. S. M. A. M. A. Y. A. N. S. M. (2021). 3 boosting breast cancer detection using convolutional neural network. In Magnenat-Thalmann, N. and Thalmann, D., editors, J Healthc Eng. John Wiley & Sons ltd.
American Cancer Society (2019). What is breast cancer? Disponível em: https://www.cancer.org/cancer/breast-cancer/about/what-is-breast-cancer.html. Acessado em: 11 jul. 2021.
Attallah, O., Anwar, F., Ghanem, N., and Ismail, M. (2021). Histo-cadx: duo cascaded fusion stages for breast cancer diagnosis from histopathological images. PeerJ Computer Science, 7:e493.
Dozat, T. (2016). Incorporating Nesterov Momentum into Adam. In Proceedings of the 4th International Conference on Learning Representations, San Juan, Puerto Rico.
Duchi, J., Hazan, E., and Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res., 12(null):2121–2159.
Fukushima, K. (1980). Neocognitron: a self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological cybernetics, 36(4):193-202.
Gayathri, B. M. and Sumathi, C. P. (2016). Comparative study of relevance vector machine with various machine learning techniques used for detecting breast cancer. In 2016 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), pages 1–5.
Hinton, G., Srivastava, N., and Swersky, K. (2020). Neural networks for machine learning, lecture 6a overview of mini-batch gradient descent. Disponível em: http://www.cs.toronto.edu/-hinton/coursera/lecture6/lec6.pdf. Acessado em: 12 jul. 2021.
Horie, Y., Yoshio, T., Aoyama, K., Yoshimizu, S., Horiuchi, Y., Ishiyama, A., Hirasawa, T., Tuchida, T., Ozawa, T., Ishihara, S., Kumagai, Y., Fujishiro, M., Maetani, I., Fujisaki, J., and Tada, T. (2018). The diagnostic outcomes of esophageal cancer by artificial intelligence using convolutional neural networks. Gastrointestinal Endoscopy, 89.
Kandel, I., Castelli, M., and Popovic, A. (2020). Comparative study of first order optimizers for image classification using convolutional neural networks on histopathology images. Journal of Imaging, 6(9).
Kingma, D. P. and Ba, J. (2017). Adam: A method for stochastic optimization.
Osareh, A. and Shadgar, B. (2011). A computer aided diagnosis system for breast cancer.
Ribeiro, A. M. and Junior, F. P. S. A. (2020). Um estudo comparativo entre cinco métodos de otimização aplicados em uma RNC voltada ao diagnótico do glaucoma. Revista de Sistemas e Computação, 10(1):122–130.
Simonyan, K. and Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition.
Singh, V., Pencina, M., Einstein, A. J., Liang, J. X., Berman, D. S., and Slomka, P. (2021). Impact of train/test sample regimen on performance estimate stability of machine learning in cardiovascular imaging. Scientific Reports, 11.
Spanhol, F. A., Oliveira, L. S., Petitjean, C., and Heutte, L. (2016a). Breast cancer histopathological image classification using convolutional neural networks. In 2016 International Joint Conference on Neural Networks (IJCNN), pages 2560–2567.
Spanhol, F. A., Oliveira, L. S., Petitjean, C., and Heutte, L. (2016b). A dataset for breast cancer histopathological image classification. IEEE Transactions on Biomedical Engineering, 63(7):1455–1462.
Tschandl, P., Rosendahl, C., Akay, B., Argenziano, G., Blum, A., Braun, R., Cabo, H., Gourhant, J.-Y., Kreusch, J., Lallas, A., Lapins, J., Marghoob, A., Menzies, S., Neuber, N., Paoli, J., Rabinovitz, H., Rinner, C., Scope, A., Soyer, P., and Kittler, H. (2018). Expert-level diagnosis of nonpigmented skin cancer by combined convolutional neural networks. JAMA Dermatology, 155.
Vargas, Paes, and Vasconcelos (2016). Um estudo sobre redes neurais convolucionais e sua aplicação em detecção de pedestres. In CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES, volume 29.
Yaqub, M., Feng, J., Zia, M. S., Arshid, K., Jia, K., Rehman, Z. U., and Mehmood, A. (2020). State-of-the-art CNN optimizer for brain tumor segmentation in magnetic resonance images. Brain Sciences, 10(7).
Zeiler, M. D. (2012). Adadelta: An adaptive learning rate method.
American Cancer Society (2019). What is breast cancer? Disponível em: https://www.cancer.org/cancer/breast-cancer/about/what-is-breast-cancer.html. Acessado em: 11 jul. 2021.
Attallah, O., Anwar, F., Ghanem, N., and Ismail, M. (2021). Histo-cadx: duo cascaded fusion stages for breast cancer diagnosis from histopathological images. PeerJ Computer Science, 7:e493.
Dozat, T. (2016). Incorporating Nesterov Momentum into Adam. In Proceedings of the 4th International Conference on Learning Representations, San Juan, Puerto Rico.
Duchi, J., Hazan, E., and Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res., 12(null):2121–2159.
Fukushima, K. (1980). Neocognitron: a self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological cybernetics, 36(4):193-202.
Gayathri, B. M. and Sumathi, C. P. (2016). Comparative study of relevance vector machine with various machine learning techniques used for detecting breast cancer. In 2016 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), pages 1–5.
Hinton, G., Srivastava, N., and Swersky, K. (2020). Neural networks for machine learning, lecture 6a overview of mini-batch gradient descent. Disponível em: http://www.cs.toronto.edu/-hinton/coursera/lecture6/lec6.pdf. Acessado em: 12 jul. 2021.
Horie, Y., Yoshio, T., Aoyama, K., Yoshimizu, S., Horiuchi, Y., Ishiyama, A., Hirasawa, T., Tuchida, T., Ozawa, T., Ishihara, S., Kumagai, Y., Fujishiro, M., Maetani, I., Fujisaki, J., and Tada, T. (2018). The diagnostic outcomes of esophageal cancer by artificial intelligence using convolutional neural networks. Gastrointestinal Endoscopy, 89.
Kandel, I., Castelli, M., and Popovic, A. (2020). Comparative study of first order optimizers for image classification using convolutional neural networks on histopathology images. Journal of Imaging, 6(9).
Kingma, D. P. and Ba, J. (2017). Adam: A method for stochastic optimization.
Osareh, A. and Shadgar, B. (2011). A computer aided diagnosis system for breast cancer.
Ribeiro, A. M. and Junior, F. P. S. A. (2020). Um estudo comparativo entre cinco métodos de otimização aplicados em uma RNC voltada ao diagnótico do glaucoma. Revista de Sistemas e Computação, 10(1):122–130.
Simonyan, K. and Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition.
Singh, V., Pencina, M., Einstein, A. J., Liang, J. X., Berman, D. S., and Slomka, P. (2021). Impact of train/test sample regimen on performance estimate stability of machine learning in cardiovascular imaging. Scientific Reports, 11.
Spanhol, F. A., Oliveira, L. S., Petitjean, C., and Heutte, L. (2016a). Breast cancer histopathological image classification using convolutional neural networks. In 2016 International Joint Conference on Neural Networks (IJCNN), pages 2560–2567.
Spanhol, F. A., Oliveira, L. S., Petitjean, C., and Heutte, L. (2016b). A dataset for breast cancer histopathological image classification. IEEE Transactions on Biomedical Engineering, 63(7):1455–1462.
Tschandl, P., Rosendahl, C., Akay, B., Argenziano, G., Blum, A., Braun, R., Cabo, H., Gourhant, J.-Y., Kreusch, J., Lallas, A., Lapins, J., Marghoob, A., Menzies, S., Neuber, N., Paoli, J., Rabinovitz, H., Rinner, C., Scope, A., Soyer, P., and Kittler, H. (2018). Expert-level diagnosis of nonpigmented skin cancer by combined convolutional neural networks. JAMA Dermatology, 155.
Vargas, Paes, and Vasconcelos (2016). Um estudo sobre redes neurais convolucionais e sua aplicação em detecção de pedestres. In CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES, volume 29.
Yaqub, M., Feng, J., Zia, M. S., Arshid, K., Jia, K., Rehman, Z. U., and Mehmood, A. (2020). State-of-the-art CNN optimizer for brain tumor segmentation in magnetic resonance images. Brain Sciences, 10(7).
Zeiler, M. D. (2012). Adadelta: An adaptive learning rate method.
Publicado
14/09/2021
Como Citar
SANTOS, Stefane A.; MOREIRA, Andressa G.; P. JUNIOR, Ialis C..
Análise comparativa da influência de otimizadores no desempenho de uma CNN para detecção do câncer de mama. In: ESCOLA REGIONAL DE COMPUTAÇÃO DO CEARÁ, MARANHÃO E PIAUÍ (ERCEMAPI), 9. , 2021, Quixadá/CE.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 1-8.
DOI: https://doi.org/10.5753/ercemapi.2021.17901.
