Segmentação Semântica do Câncer de Pele Utilizando Aprendizado Profundo

• João Victor M. da Silva UFPI
• Kelson R. T. Aires UFPI
• Alan R. F. dos Santos UFPI
• Rodrigo de M. S. Veras UFPI
• Laurindo de S. B. Neto UFPI
• Leonardo P. de Sousa UFPI
• Francisco das C. I. Filho UFPI

DOI: https://doi.org/10.5753/sbcas.2023.229926

Resumo

O câncer de pele é um dos grandes problemas enfrentados pela saúde pública, e a utilização de Aprendizado de Profundo pode permitir a classificação de lesões de pele em imagens. Nesse contexto, este trabalho tem o objetivo de desenvolver um método de segmentação de lesões de pele para facilitar a classificação de lesões. Nesse sentido, foi utilizado a arquitetura DeepLab3+ associada à limiarização global, refinado em três modelos específicos: (1) somente para lesões malignas, (2) somente para lesões benignas e (3) para todos os tipos de lesões. Os experimentos utilizaram quatro bases públicas, HAM10000, ISIC 2016, ISIC 2017 e PH². Os melhores resultados atingiram um Dice de 94,42% na base HAM10000, 91,68% na base ISIC 2016, 87,19% na base ISIC 2017 e 92,12% na base PH². Os melhores resultados foram alcançados com o modelo treinado para todos os tipos de lesões.

Referências

Alom, M. Z., Hasan, M., Yakopcic, C., Taha, T. M., and Asari, V. K. (2018). Recurrent residual convolutional neural network based on u-net (r2u-net) for medical image segmentation. arXiv preprint arXiv:1802.06955.

Azad, R., Asadi-Aghbolaghi, M., Fathy, M., and Escalera, S. (2020). Attention deeplabv3+: Multi-level context attention mechanism for skin lesion segmentation. In Computer Vision–ECCV 2020 Workshops: Glasgow, UK, August 23–28, 2020, Proceedings, Part I 16, pages 251–266. Springer.

Bagheri, F., Tarokh, M. J., and Ziaratban, M. (2021). Skin lesion segmentation from dermoscopic images by using mask r-cnn, retina-deeplab, and graph-based methods. Biomedical Signal Processing and Control, 67:102533.

Basak, H., Kundu, R., and Sarkar, R. (2022). Mfsnet: A multi focus segmentation network for skin lesion segmentation. Pattern Recognition, 128:108673.

Chan, S., Reddy, V., Myers, B., Thibodeaux, Q., Brownstone, N., and Liao, W. (2020). Machine learning in dermatology: current applications, opportunities, and limitations. Dermatology and therapy, 10:365–386.

Chen, L.-C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587.

Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV), pages 801–818.

Codella, N. C., Gutman, D., Celebi, M. E., Helba, B., Marchetti, M. A., Dusza, S. W., Kalloo, A., Liopyris, K., Mishra, N., Kittler, H., 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). In 2018 IEEE 15th international symposium on biomedical imaging (ISBI 2018), pages 168–172. IEEE.

de Oliveira Santos, M., de Lima, F. C. d. S., Martins, L. F. L., Oliveira, J. F. P., de Almeida, L. M., and de Camargo Cancela, M. (2023). Estimativa de incidência de câncer no brasil, 2023-2025. Revista Brasileira de Cancerologia, 69(1).

Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee.

Dildar, M., Akram, S., Irfan, M., Khan, H. U., Ramzan, M., Mahmood, A. R., Alsaiari, S. A., Saeed, A. H. M., Alraddadi, M. O., and Mahnashi, M. H. (2021). Skin cancer detection: a review using deep learning techniques. International journal of environmental research and public health, 18(10):5479.

Fan, H., Xie, F., Li, Y., Jiang, Z., and Liu, J. (2017). Automatic segmentation of dermoscopy images using saliency combined with otsu threshold. Computers in biology and medicine, 85:75–85.

Ferlay, J., Colombet, M., Soerjomataram, I., Parkin, D. M., Piñeros, M., Znaor, A., and Bray, F. (2021). Cancer statistics for the year 2020: An overview. International journal of cancer, 149(4):778–789.

Ge, Z., Demyanov, S., Bozorgtabar, B., Abedini, M., Chakravorty, R., Bowling, A., and Garnavi, R. (2017). Exploiting local and generic features for accurate skin lesions classification using clinical and dermoscopy imaging. In 2017 IEEE 14th international symposium on biomedical imaging (ISBI 2017), pages 986–990. IEEE.

Goyal, M., Oakley, A., Bansal, P., Dancey, D., and Yap, M. H. (2019). Skin lesion segmentation in dermoscopic images with ensemble deep learning methods. IEEE Access, 8:4171–4181.

Gutman, D., Codella, N. C., Celebi, E., Helba, B., Marchetti, M., Mishra, N., and Halpern, A. (2016). 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). arXiv preprint arXiv:1605.01397.

Hong, Y., Zhang, G., Wei, B., Cong, J., Xu, Y., and Zhang, K. (2022). Weakly supervised semantic segmentation for skin cancer via cnn superpixel region response. Multimedia Tools and Applications, pages 1–19.

Isa, N. A. M., Salamah, S. A., and Ngah, U. K. (2009). Adaptive fuzzy moving k-means clustering algorithm for image segmentation. IEEE Transactions on Consumer Electronics, 55(4):2145–2153.

Karri, M., Annavarapu, C. S. R., and Acharya, U. R. (2023). Skin lesion segmentation using two-phase cross-domain transfer learning framework. Computer Methods and Programs in Biomedicine, page 107408.

Kaur, R., GholamHosseini, H., Sinha, R., and Lindén, M. (2022). Automatic lesion segmentation using atrous convolutional deep neural networks in dermoscopic skin cancer images. BMC Medical Imaging, 22(1):1–13.

MacQueen, J. (1967). Classification and analysis of multivariate observations. In 5th Berkeley Symp. Math. Statist. Probability, pages 281–297. University of California Los Angeles LA USA.

Mendonça, T., Ferreira, P. M., Marques, J. S., Marcal, A. R., and Rozeira, J. (2013). Ph 2-a dermoscopic image database for research and benchmarking. In 2013 35th annual international conference of the IEEE engineering in medicine and biology society (EMBC), pages 5437–5440. IEEE.

Monard, M. C. and Baranauskas, J. A. (2003). Conceitos sobre aprendizado de máquina. Sistemas inteligentes-Fundamentos e aplicações, 1(1):32.

Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1):62–66.

Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pages 234–241. Springer.

Tschandl, P., Rosendahl, C., and Kittler, H. (2018). The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific data, 5(1):1–9.

Yang, L., Fan, C., Lin, H., and Qiu, Y. (2023). Rema-net: An efficient multi-attention convolutional neural network for rapid skin lesion segmentation. Computers in Biology and Medicine, 159:106952.

Yuan, Y., Chao, M., and Lo, Y.-C. (2017). Automatic skin lesion segmentation using deep fully convolutional networks with jaccard distance. IEEE Transactions on Medical Imaging, 36(9):1876–1886.