Detecção de Câncer Peniano em Imagens Histopatológicas usando Redes Neurais Convolucionais em Cascata

• Filipe Correia Belfort UFMA
• Italo Francyles Santos da Silva UFMA
• Aristófanes Corrêa Silva UFMA
• Anselmo Cardoso de Paiva UFMA

DOI: https://doi.org/10.5753/sbcas.2023.229942

Abstract

Penile cancer has a high incidence in developing countries, including Brazil, where the state of Maranhão has the highest worldwide occurrence rate. This pathology, when advanced, can lead to an invasive surgery with physical and psychological consequences, making early diagnosis important. Histopathological analysis is an exam indicated for diagnosis, but it is timeconsuming and complex. Computational methods, such as convolutional neural networks (CNNs), can help in obtaining a faster and more accurate diagnosis. Therefore, this work proposes a method for classifying penile cancer in histopathological images using cascaded CNNs and the Soft-Attention mechanism, which assigns more weight to relevant image features. Experiments were carried out on a dataset containing 194 samples at 40× and 100× magnification. As a final result, the method achieves 93% and 90% accuracy, respectively, for detecting cancer at 40× and 100× magnification.

References

Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., and Zheng, X. (2015). TensorFlow: Large-scale machine learning on heterogeneous systems. Software available from tensorflow.org.

Bedoya, S. A. O., Conceição, L., Viloria, M., Loures, F., Valente, F., Amorim, R., and Silva, F. (2016). Caracterização de colágenos tipos i e iii no estroma do carcinoma de células escamosas cutâneo em cães. Arquivo Brasileiro de Medicina Veterinária e Zootecnia, 68:147–154.

Chollet, F. et al. (2015). Keras. https://keras.io.

Gaio, D. E. (2022). Análise comparativa das técnicas de implementação de arquiteturas da função sigmoide.

Hakenberg, O. W., Dräger, D. L., Erbersdobler, A., Naumann, C. M., Jünemann, K.-P., and Protzel, C. (2018). The diagnosis and treatment of penile cancer. Deutsches Ärzteblatt International, 115(39):646.

Kingma, D. P. and Ba, J. (2015). Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference for Learning Representations (ICLR 2015), pages 1–15.

Lauande, M. G. M., Teles, A. M., da Silva, L. L., Matos, C. E. F., Junior, G. B., de Paiva, A. C., de Almeida, J. D. S., da Costa Oliveira, R. M. G., Brito, H. O., Nascimento, A. G., et al. (2022). Classification of histopathological images of penile cancer using densenet and transfer learning. In VISIGRAPP (4: VISAPP), pages 976–983.

Lourenço, S. d. Q. C., Schueler, A. F., Camisasca, D. R., de Castro Lindenblatt, R., and Bernardo, V. G. (2007). Classificações histopatológicas para o carcinoma de células escamosas da cavidade oral: revisão de sistemas propostos. Revista Brasileira de Cancerologia, 53(3):325–333.

Melo, R. C., Raas, M. W., Palazzi, C., Neves, V. H., Malta, K. K., and Silva, T. P. (2020). Whole slide imaging and its applications to histopathological studies of liver disorders. Frontiers in medicine, 6:310.

Morris, B. J., Gray, R. H., Castellsague, X., Bosch, F. X., Halperin, D. T., Waskett, J. H., and Hankins, C. A. (2011). The strong protective effect of circumcision against cancer of the penis. Advances in urology, 2011.

Olesen, T. B., Sand, F. L., Rasmussen, C. L., Albieri, V., Toft, B. G., Norrild, B., Munk, C., and Kjær, S. K. (2019). Prevalence of human papillomavirus dna and p16ink4a in penile cancer and penile intraepithelial neoplasia: a systematic review and metaanalysis. The lancet oncology, 20(1):145–158.

Reis, A. A. d. S., Paula, L. B. d., Paula, A. A. P. d., Saddi, V. A., and Cruz, A. D. d. (2010). Aspectos clínico-epidemiológicos associados ao câncer de pênis. Ciência & Saúde Coletiva, 15:1105–1111.

Sinha, A. and Dolz, J. (2020). Multi-scale self-guided attention for medical image segmentation. IEEE journal of biomedical and health informatics.

Tan, M. and Le, Q. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In Chaudhuri, K. and Salakhutdinov, R., editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 6105–6114. PMLR.

Thomas, A., Necchi, A., Muneer, A., Tobias-Machado, M., Tran, A. T. H., Van Rompuy, A.-S., Spiess, P. E., and Albersen, M. (2021). Penile cancer. Nature Reviews Disease Primers, 7(1):11.

Vieira, C. B., Feitoza, L., Pinho, J., Teixeira-Júnior, A., Lages, J., Calixto, J., Coelho, R., Nogueira, L., Cunha, I., Soares, F., et al. (2020). Profile of patients with penile cancer in the region with the highest worldwide incidence. Scientific reports, 10(1):2965.