A Deep Learning Application for Psoriasis Detection
Resumo
Nesse artigo é apresentado um estudo comparativo do desempenho de três modelos de Redes Neurais Convolucionais, ResNet50, Inception v3 e VGG19 para classificação de imagens de pele com lesões afetadas por psoríase. As imagens utilizadas para o treinamento e validação dos modelos foram obtidas em plataformas especializadas. Foram utilizadas várias técnicas para ajuste das métricas de avaliação das redes neurais. Os resultados encontrados sugerem o modelo Inception v3 como uma ferramenta valiosa para apoio ao diagnóstico de psoríase. Isso se deve ao seu desempenho satisfatório no que diz respeito à acurácia e F1-Score (97,5% ± 0,2).
Palavras-chave:
aprendizado profundo, redes neurais convolucionais, psoríase
Referências
Academy, D. S. (2022). Deep learning book. [link]. Acessado em: 01 de outubro de 2022.
Agarap, A. F. (2018). Deep learning using rectified linear units (relu). arXiv preprint arXiv:1803.08375. DOI: 10.48550/arXiv.1803.08375.
Aggarwal, S. L. P. (2019). Data augmentation in dermatology image recognition using machine learning. Skin Research and Technology, 25(6):815–820.
Arlot, S. and Celisse, A. (2010). A survey of cross-validation procedures for model selection. Statist. Surv., 4:40–79. First available in Project Euclid: 9 March 2010. DOI: 10.1214/09-SS054.
Bottou, L. (2012). Stochastic gradient descent tricks. In Neural Networks: Tricks of the Trade: Second Edition, pages 421–436. Springer. DOI: 10.1007/978-3-642-35289-8 25.
Bouckaert, R. R. and Frank, E. (2004). Evaluating the replicability of significance tests for comparing learning algorithms. In Pacific-Asia conference on knowledge discovery and data mining, pages 3–12. Springer. DOI: 10.1007/978-3-540-24775-3 3.
Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1251–1258. DOI: 10.48550/arXiv.1610.02357.
de Dermatologia, S. B. (2012). Consenso Brasileiro de Psoríase 2012. Guias de avaliaç ao e tratamento Sociedade Brasileira de Dermatologia. Sociedade Brasileira de Dermatologia, 2nd edition. Acessado em: 17 de agosto de 2022.
Fawcett, T. (2006). An introduction to roc analysis. Pattern Recognition Letters, 27(8):861–874. DOI: 10.1016/j.patrec.2005.10.010.
Guimaraes, A. J., Araújo, V. J., de Oliveira Batista, L., Souza, P. V. C., Araújo, V., and Rezende, T. S. (2018). Using fuzzy neural networks to improve prediction of expert systems for detection of breast cancer. In Anais do XV Encontro Nacional de Inteligência Artificial e Computacional, pages 799–810. SBC. DOI: 10.5753/eniac.2018.4468.
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778. DOI: 10.1109/CVPR.2016.90.
Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708. DOI: 10.48550/arXiv.1608.06993.
Keras (2023). Globalaveragepooling2d layer. [link]. Acessado em: 01 de outubro de 2022.
Kingma, D. P. and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. DOI: 10.48550/arXiv.1412.6980.
Moura, L. R. d., Coelho, A. M., and Baffa, M. d. F. O. (2021). Detecção automática de anomalias oculares utilizando redes neurais convolucionais. In Anais do VIII Encontro Nacional de Computação dos Institutos Federais, pages 73–79, [S.l.]. SBC. DOI: 10.5753/encompif.2021.15953.
Neto, C. F., Cucé, L. C., and dos Reis, V. M. S. (1990). Manual de dermatologia. Editora Manole.
Nhat, H. et al. (2014). A preliminary report on a full-body imaging system for effectively collecting and processing biometric traits of prisoners. In IEEE Symposium Series on Computational Intelligence. DOI: 10.1109/CIBIM.2014.7015459.
OMS (2016). Relatório global sobre a psoríase. [link]. Acessado em: 20 de agosto de 2022.
Pan, S. J. and Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10):1345–1359. DOI: 10.1109/TKDE.2009.191.
Pezo, A. R., Nogueira, K., Bologna, R., and Montoya, G. (2020). Computer application for the detection of skin diseases in photographic images using convolutional neural networks. In Latin American High Performance Computing Conference, pages 193–204. Springer. DOI: 10.1007/978-3-030-68035-0 14.
Ruder, S. (2016). An overview of gradient descent optimization algorithms. arXiv pre-print arXiv:1609.04747. DOI: 10.48550/arXiv.1609.04747.
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). Imagenet large scale visual recognition challenge. International journal of computer vision, 115:211–252. DOI: 10.48550/arXiv.1409.0575.
Silva, G. et al. (2022). Cardiac arrhythmia detection in ecg signals using graph convolutional network. In Anais do XXII Simpósio Brasileiro de Computação Aplicada à Saúde, pages 25–35. DOI: 10.5753/sbcas.2022.222434.
Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. DOI: 10.48550/arXiv.1409.1556.
Snoek, J., Larochelle, H., and Adams, R. P. (2012). Practical bayesian optimization of machine learning algorithms. In Advances in neural information processing systems, volume 25. DOI: 10.48550/arXiv.1206.2944.
Swets, J. A. (1988). Measuring the accuracy of diagnostic systems. Science, 240(4857):1285–1293. DOI: 10.1126/science.3287615.
Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. In Proceedings of the AAAI conference on artificial intelligence, volume 31. DOI: 10.48550/arXiv.1602.07261.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826. IEEE. DOI: 10.48550/arXiv.1512.00567.
Vilefort, L. A., Souza, H., Vilela, L. C., Tanaka, V. Y. T., Vianna, R. M., de Sá, Y. A., Lisbôa, A. C. C., Oliveira, M. S., Duarte, A. C. S., Rezende, O. G. M., et al. (2022). Aspectos gerais da psoríase: revisão narrativa. Revista Eletrônica Acervo Científico, 42:e10310–e10310. DOI: 10.25248/reac.e10310.2022.
Zhao, S., Yang, X., Xu, W., Zhang, Y., Huang, L., Chen, W., Wei, H., and Jiang, B. (2020). Smart identification of psoriasis by images using convolutional neural networks: a case study in china. Journal of the European Academy of Dermatology and Venereology, 34(3):518–524. DOI: 10.1111/jdv.15965.
Agarap, A. F. (2018). Deep learning using rectified linear units (relu). arXiv preprint arXiv:1803.08375. DOI: 10.48550/arXiv.1803.08375.
Aggarwal, S. L. P. (2019). Data augmentation in dermatology image recognition using machine learning. Skin Research and Technology, 25(6):815–820.
Arlot, S. and Celisse, A. (2010). A survey of cross-validation procedures for model selection. Statist. Surv., 4:40–79. First available in Project Euclid: 9 March 2010. DOI: 10.1214/09-SS054.
Bottou, L. (2012). Stochastic gradient descent tricks. In Neural Networks: Tricks of the Trade: Second Edition, pages 421–436. Springer. DOI: 10.1007/978-3-642-35289-8 25.
Bouckaert, R. R. and Frank, E. (2004). Evaluating the replicability of significance tests for comparing learning algorithms. In Pacific-Asia conference on knowledge discovery and data mining, pages 3–12. Springer. DOI: 10.1007/978-3-540-24775-3 3.
Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1251–1258. DOI: 10.48550/arXiv.1610.02357.
de Dermatologia, S. B. (2012). Consenso Brasileiro de Psoríase 2012. Guias de avaliaç ao e tratamento Sociedade Brasileira de Dermatologia. Sociedade Brasileira de Dermatologia, 2nd edition. Acessado em: 17 de agosto de 2022.
Fawcett, T. (2006). An introduction to roc analysis. Pattern Recognition Letters, 27(8):861–874. DOI: 10.1016/j.patrec.2005.10.010.
Guimaraes, A. J., Araújo, V. J., de Oliveira Batista, L., Souza, P. V. C., Araújo, V., and Rezende, T. S. (2018). Using fuzzy neural networks to improve prediction of expert systems for detection of breast cancer. In Anais do XV Encontro Nacional de Inteligência Artificial e Computacional, pages 799–810. SBC. DOI: 10.5753/eniac.2018.4468.
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778. DOI: 10.1109/CVPR.2016.90.
Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708. DOI: 10.48550/arXiv.1608.06993.
Keras (2023). Globalaveragepooling2d layer. [link]. Acessado em: 01 de outubro de 2022.
Kingma, D. P. and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. DOI: 10.48550/arXiv.1412.6980.
Moura, L. R. d., Coelho, A. M., and Baffa, M. d. F. O. (2021). Detecção automática de anomalias oculares utilizando redes neurais convolucionais. In Anais do VIII Encontro Nacional de Computação dos Institutos Federais, pages 73–79, [S.l.]. SBC. DOI: 10.5753/encompif.2021.15953.
Neto, C. F., Cucé, L. C., and dos Reis, V. M. S. (1990). Manual de dermatologia. Editora Manole.
Nhat, H. et al. (2014). A preliminary report on a full-body imaging system for effectively collecting and processing biometric traits of prisoners. In IEEE Symposium Series on Computational Intelligence. DOI: 10.1109/CIBIM.2014.7015459.
OMS (2016). Relatório global sobre a psoríase. [link]. Acessado em: 20 de agosto de 2022.
Pan, S. J. and Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10):1345–1359. DOI: 10.1109/TKDE.2009.191.
Pezo, A. R., Nogueira, K., Bologna, R., and Montoya, G. (2020). Computer application for the detection of skin diseases in photographic images using convolutional neural networks. In Latin American High Performance Computing Conference, pages 193–204. Springer. DOI: 10.1007/978-3-030-68035-0 14.
Ruder, S. (2016). An overview of gradient descent optimization algorithms. arXiv pre-print arXiv:1609.04747. DOI: 10.48550/arXiv.1609.04747.
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). Imagenet large scale visual recognition challenge. International journal of computer vision, 115:211–252. DOI: 10.48550/arXiv.1409.0575.
Silva, G. et al. (2022). Cardiac arrhythmia detection in ecg signals using graph convolutional network. In Anais do XXII Simpósio Brasileiro de Computação Aplicada à Saúde, pages 25–35. DOI: 10.5753/sbcas.2022.222434.
Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. DOI: 10.48550/arXiv.1409.1556.
Snoek, J., Larochelle, H., and Adams, R. P. (2012). Practical bayesian optimization of machine learning algorithms. In Advances in neural information processing systems, volume 25. DOI: 10.48550/arXiv.1206.2944.
Swets, J. A. (1988). Measuring the accuracy of diagnostic systems. Science, 240(4857):1285–1293. DOI: 10.1126/science.3287615.
Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. In Proceedings of the AAAI conference on artificial intelligence, volume 31. DOI: 10.48550/arXiv.1602.07261.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826. IEEE. DOI: 10.48550/arXiv.1512.00567.
Vilefort, L. A., Souza, H., Vilela, L. C., Tanaka, V. Y. T., Vianna, R. M., de Sá, Y. A., Lisbôa, A. C. C., Oliveira, M. S., Duarte, A. C. S., Rezende, O. G. M., et al. (2022). Aspectos gerais da psoríase: revisão narrativa. Revista Eletrônica Acervo Científico, 42:e10310–e10310. DOI: 10.25248/reac.e10310.2022.
Zhao, S., Yang, X., Xu, W., Zhang, Y., Huang, L., Chen, W., Wei, H., and Jiang, B. (2020). Smart identification of psoriasis by images using convolutional neural networks: a case study in china. Journal of the European Academy of Dermatology and Venereology, 34(3):518–524. DOI: 10.1111/jdv.15965.
Publicado
25/09/2023
Como Citar
MILANI, Anna; DA SILVA, Fábio S.; GUEDES, Elloá B.; RIOS, Ricardo.
A Deep Learning Application for Psoriasis Detection. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 20. , 2023, Belo Horizonte/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2023
.
p. 315-329.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2023.234030.
