Aplicação de Redes de Aprendizado Profundo e Algoritmos de Aprendizado de Máquina para Classificar Imagens de Câncer de Pele
Resumo
O câncer de pele representa um grande desafio para a saúde pública, demandando de tecnologias que auxiliem em seu diagnóstico. Neste trabalho, propomos um método que combina algoritmos de aprendizagem profunda, utilizados para a extração de atributos de imagens de câncer de pele, e algoritmos de aprendizado de máquina tradicionais, utilizados como classificadores. Para isso, empregamos em nossos experimentos o conjunto de dados HAM10000 que nos permite realizar a classificação multiclasse. Utilizamos a rede convolucional VGG como extrator de atributos, os quais foram usados como entrada para algoritmos como Perceptron e LR realizarem a tarefa de classificação. Os resultados alcançados demonstram boa efetividade do nosso método, amparando a continuidade de nossa pesquisa.Referências
Alpaydin, E. (2020). Introduction to machine learning. MIT Press, Cambridge, 4 edition.
Auxilia, V., Meenakshi, A., Prabahavathy, P., and Shamreen, A. B. (2022). Skin lesion classification and prediction by data augmentation in ham10000 and isic 2019 dataset. DOI: 10.21203/rs.3.rs-2242686/v2. Acessado em 05/05/2024.
Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2):123–140.
Britto, A. S., Sabourin, R., and Oliveira, L. E. S. (2014). Dynamic selection of classifiers—a comprehensive review. Pattern Recognition, 47(11):3665–3680.
Cruz, R. M., Sabourin, R., and Cavalcanti, G. D. C. (2018). Dynamic classifier selection: Recent advances and perspectives. Information Fusion, 41:195–216.
Giuffrida, R., Conforti, C., Meo, N. D., Deinlein, T., Guida, S., and Zalaudek, I. (2020). Use of noninvasive imaging in the management of skin cancer. Current Opinion in Oncology, 32(2):98–105.
Gutman, D., Codella, N., Celebi, E., Helba, B., Marchetti, M., Mishra, N., and Halpern., A. (2018). Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC). 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pages 168–172.
Ho, T. K. (1998). The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(8):832–844.
Layode, O., Alam, T., and Rahman, M. M. (2019). Deep Learning Based Integrated Classification and Image Retrieval System for Early Skin Cancer Detection. 2019 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), pages 1–7.
Mendonça, T., Ferreira, P. M., Marques, J. S., Marcal, A. R. S., and Rozeira, J. (2013). Ph2 a dermoscopic image database for research and benchmarking. 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 5437–5440.
O’Neill, C. H. and Scoggins, C. R. (2019). Melanoma. J Surg Oncol.
Pathan, S., Prabhu, K. G., and Siddalingaswamy, P. (2019). Automated detection of melanocytes related pigmented skin lesions: A clinical framework. Biomedical Signal Processing and Control, 51(1):59–72.
Roy, A., Cruz, R. M., Sabourin, R., and Cavalcanti, G. D. (2018). A study on combining dynamic selection and data preprocessing for imbalance learning. Neurocomputing, 286:179–192.
Simonyan, K. and Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. arXiv 1409.1556, 6.
Spolaôr, N., Lee, H. D., Mendes, A. I., Nogueira, C. V., Parmezan, A. R. S., Takaki, W. S. R., Coy, C. S. R., Wu, F. C., and Fonseca-Pinto, R. (2024). Fine-tuning pre-trained neural networks for medical image classification in small clinical datasets. Multimedia Tools and Applications, 83:27305–27329.
Tschandl, P. (2018). The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Harvard Dataverse, 4.
World Health Organization (2022). Skin cancer. Disponível em: [link]. Acessado em: 28 fev. 2024.
Auxilia, V., Meenakshi, A., Prabahavathy, P., and Shamreen, A. B. (2022). Skin lesion classification and prediction by data augmentation in ham10000 and isic 2019 dataset. DOI: 10.21203/rs.3.rs-2242686/v2. Acessado em 05/05/2024.
Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2):123–140.
Britto, A. S., Sabourin, R., and Oliveira, L. E. S. (2014). Dynamic selection of classifiers—a comprehensive review. Pattern Recognition, 47(11):3665–3680.
Cruz, R. M., Sabourin, R., and Cavalcanti, G. D. C. (2018). Dynamic classifier selection: Recent advances and perspectives. Information Fusion, 41:195–216.
Giuffrida, R., Conforti, C., Meo, N. D., Deinlein, T., Guida, S., and Zalaudek, I. (2020). Use of noninvasive imaging in the management of skin cancer. Current Opinion in Oncology, 32(2):98–105.
Gutman, D., Codella, N., Celebi, E., Helba, B., Marchetti, M., Mishra, N., and Halpern., A. (2018). Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC). 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pages 168–172.
Ho, T. K. (1998). The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(8):832–844.
Layode, O., Alam, T., and Rahman, M. M. (2019). Deep Learning Based Integrated Classification and Image Retrieval System for Early Skin Cancer Detection. 2019 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), pages 1–7.
Mendonça, T., Ferreira, P. M., Marques, J. S., Marcal, A. R. S., and Rozeira, J. (2013). Ph2 a dermoscopic image database for research and benchmarking. 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 5437–5440.
O’Neill, C. H. and Scoggins, C. R. (2019). Melanoma. J Surg Oncol.
Pathan, S., Prabhu, K. G., and Siddalingaswamy, P. (2019). Automated detection of melanocytes related pigmented skin lesions: A clinical framework. Biomedical Signal Processing and Control, 51(1):59–72.
Roy, A., Cruz, R. M., Sabourin, R., and Cavalcanti, G. D. (2018). A study on combining dynamic selection and data preprocessing for imbalance learning. Neurocomputing, 286:179–192.
Simonyan, K. and Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. arXiv 1409.1556, 6.
Spolaôr, N., Lee, H. D., Mendes, A. I., Nogueira, C. V., Parmezan, A. R. S., Takaki, W. S. R., Coy, C. S. R., Wu, F. C., and Fonseca-Pinto, R. (2024). Fine-tuning pre-trained neural networks for medical image classification in small clinical datasets. Multimedia Tools and Applications, 83:27305–27329.
Tschandl, P. (2018). The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Harvard Dataverse, 4.
World Health Organization (2022). Skin cancer. Disponível em: [link]. Acessado em: 28 fev. 2024.
Publicado
25/06/2024
Como Citar
SÁ, João P. C. A. de; ENSINA, Leandro A.; JERONYMO, Daniel C..
Aplicação de Redes de Aprendizado Profundo e Algoritmos de Aprendizado de Máquina para Classificar Imagens de Câncer de Pele. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 24. , 2024, Goiânia/GO.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 651-656.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2024.2230.
