Aprendizado Ativo Aplicado ao Diagnóstico de Lesões Dermatológicas
Resumo
O presente trabalho explora a abordagem de aprendizado ativo, selecionando amostras mais informativas, de forma a reduzir o custo para anotação de lesões dermatológicas. Para validação foi realizada uma avaliação experimental extensiva considerando diferentes conjuntos de dados, métricas e estratégias para descrição (com extratores tradicionais e profundos), seleção (com critérios baseados em diversidade, incerteza e representatividade) e classificação (com algoritmos supervisionados tradicionais). A partir dos resultados, é possível observar que a abordagem proposta apresentou contribuições significativas, possibilitando uma redução de 65% na quantidade de amostras rotuladas requeridas para o aprendizado do classificador.
Palavras-chave:
aprendizado ativo, aprendizado de máquina, câncer, lesão de pele, classificação de imagens
Referências
Adegun, A. and Viriri, S. (2021). Deep learning techniques for skin lesion analysis and melanoma cancer detection: a survey of state-of-the-art. Artificial Intelligence Review, 54(2):811–841.
Ali, A.-R. H., Li, J., and Yang, G. (2020). Automating the abcd rule for melanoma detection: a survey. IEEE Access, 8:83333–83346.
Benyahia, S., Meftah, B., and Lézoray, O. (2022). Multi-features extraction based on deep learning for skin lesion classification. Tissue and Cell, 74:101701.
Codella, N. C. F., Gutman, D., Celebi, M. E., Helba, B., Marchetti, M. A., Dusza, S. W., Kalloo, A., Liopyris, K., Mishra, N., Kittler, H., and et al. (2018). Skin lesion analysis toward melanoma detection: A challenge at the 2017 international symposium on biomedical imaging (isbi), hosted by the international skin imaging collaboration (isic). 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).
Kaur, R., GholamHosseini, H., Sinha, R., and Lindén, M. (2022). Melanoma classification using a novel deep convolutional neural network with dermoscopic images. Sensors, 22(3):1134.
Popescu, D., El-Khatib, M., El-Khatib, H., and Ichim, L. (2022). New trends in melanoma detection using neural networks: A systematic review. Sensors, 22(2):496.
Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. CoRR, abs/1505.04597.
Saito, P. T., Suzuki, C. T., Gomes, J. F., de Rezende, P. J., and Falcão, A. X. (2015). Robust active learning for the diagnosis of parasites. Pattern Recognition, 48(11):3572–3583.
Settles, B. (2012). Active Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan and Claypool Publishers.
Shi, X., Dou, Q., Xue, C., Qin, J., Chen, H., and Heng, P.-A. (2019). An active learning approach for reducing annotation cost in skin lesion analysis.
Tschandl, P., Rosendahl, C., and Kittler, H. (2018). The HAM10000 dataset: A large collection of multi-source dermatoscopic images of common pigmented skin lesions. CoRR, abs/1803.10417.
Tschandl, P., Sinz, C., and Kittler, H. (2019). Domain-specific classification-pretrained fully convolutional network encoders for skin lesion segmentation. Computers in Biology and Medicine, 104:111–116.
Valle, E., Fornaciali, M., Menegola, A., Tavares, J., Bittencourt, F. V., Li, L. T., and Avila, S. (2020). Data, depth, and design: Learning reliable models for skin lesion analysis. Neurocomputing, 383:303–313.
Ali, A.-R. H., Li, J., and Yang, G. (2020). Automating the abcd rule for melanoma detection: a survey. IEEE Access, 8:83333–83346.
Benyahia, S., Meftah, B., and Lézoray, O. (2022). Multi-features extraction based on deep learning for skin lesion classification. Tissue and Cell, 74:101701.
Codella, N. C. F., Gutman, D., Celebi, M. E., Helba, B., Marchetti, M. A., Dusza, S. W., Kalloo, A., Liopyris, K., Mishra, N., Kittler, H., and et al. (2018). Skin lesion analysis toward melanoma detection: A challenge at the 2017 international symposium on biomedical imaging (isbi), hosted by the international skin imaging collaboration (isic). 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).
Kaur, R., GholamHosseini, H., Sinha, R., and Lindén, M. (2022). Melanoma classification using a novel deep convolutional neural network with dermoscopic images. Sensors, 22(3):1134.
Popescu, D., El-Khatib, M., El-Khatib, H., and Ichim, L. (2022). New trends in melanoma detection using neural networks: A systematic review. Sensors, 22(2):496.
Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. CoRR, abs/1505.04597.
Saito, P. T., Suzuki, C. T., Gomes, J. F., de Rezende, P. J., and Falcão, A. X. (2015). Robust active learning for the diagnosis of parasites. Pattern Recognition, 48(11):3572–3583.
Settles, B. (2012). Active Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan and Claypool Publishers.
Shi, X., Dou, Q., Xue, C., Qin, J., Chen, H., and Heng, P.-A. (2019). An active learning approach for reducing annotation cost in skin lesion analysis.
Tschandl, P., Rosendahl, C., and Kittler, H. (2018). The HAM10000 dataset: A large collection of multi-source dermatoscopic images of common pigmented skin lesions. CoRR, abs/1803.10417.
Tschandl, P., Sinz, C., and Kittler, H. (2019). Domain-specific classification-pretrained fully convolutional network encoders for skin lesion segmentation. Computers in Biology and Medicine, 104:111–116.
Valle, E., Fornaciali, M., Menegola, A., Tavares, J., Bittencourt, F. V., Li, L. T., and Avila, S. (2020). Data, depth, and design: Learning reliable models for skin lesion analysis. Neurocomputing, 383:303–313.
Publicado
31/07/2022
Como Citar
BATISTA, Lucas G.; CRUZ, Fernando F.; BUGATTI, Pedro H.; SAITO, Priscila T. M..
Aprendizado Ativo Aplicado ao Diagnóstico de Lesões Dermatológicas. In: BRAZILIAN E-SCIENCE WORKSHOP (BRESCI), 16. , 2022, Niterói.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2022
.
p. 65-72.
ISSN 2763-8774.
DOI: https://doi.org/10.5753/bresci.2022.223093.
