Multiple Instance Learning for Histopathological Grading of Penile Cancer

• Rick Eick V. Santos UFMA
• Victor José B. A. Martinez UFMA
• Geraldo Braz Júnior UFMA

DOI: https://doi.org/10.5753/sbcas.2026.21658

Resumo

Penile cancer exhibits a relatively high incidence in developing countries. In this context, this work proposes a Multiple Instance Learning–based approach for the classification of histopathological images in the PCPAm dataset, addressing both binary cancer detection and histopathological grade classification. The method leverages patch-based decomposition of high-resolution images combined with feature aggregation strategies and class imbalance mitigation techniques, evaluated under stratified five-fold cross-validation. The best configuration achieved over 81.5% accuracy and 80.2% F1-score in histopathological grade classification, establishing a strong baseline for future research in computer-assisted diagnosis of penile cancer.

Referências

Belfort, F., Silva, I., Silva, A., and Paiva, A. (2023). Detecção de câncer peniano em imagens histopatológicas usando redes neurais convolucionais em cascata. In Anais do XXIII SBCAS, pages 328–339. SBC.

Coelho, R. W. P., Pinho, J. D., Moreno, J. S., Garbis, D. V. e. O., do Nascimento, A. M. T., Larges, J. S., Calixto, J. R. R., Ramalho, L. N. Z., da Silva, A. A. M., Nogueira, L. R., de Moura Feitoza, L., and Silva, G. E. B. (2018). Penile cancer in maranhão, northeast brazil: the highest incidence globally? BMC Urology, 18(1):50.

Douglawi, A. and Masterson, T. A. (2017). Updates on the epidemiology and risk factors for penile cancer. Translational Andrology and Urology, 6(5).

Durand, J. R., Junior, G. B., da Silva, I. F. S., and da Costa Oliveira, R. M. G. (2025). Histattentionnas: A cnn built via nas for penile cancer diagnosis using histopathological images. Procedia Computer Science, 256:764–771.

Goyal, M., Tafe, L. J., Feng, J. X., Muller, K. E., Hondelink, L., Bentz, J. L., and Hassanpour, S. (2024). Vision transformer-based deep learning for histologic classification of endometrial cancer.

Ilse, M., Tomczak, J., and Welling, M. (2018). Attention-based deep multiple instance learning. In Dy, J. and Krause, A., editors, Proceedings of the 35th International Conference on Machine Learning, volume 80 of Proceedings of Machine Learning Research, pages 2127–2136. PMLR.

Lauande, M. G. M., Braz Junior, G., de Almeida, J. D. S., Silva, A. C., Gil da Costa, R. M., Teles, A. M., da Silva, L. L., Brito, H. O., Vidal, F. C. B., do Vale, J. G. A., Rodrigues Junior, J. R. D., and Cunha, A. (2024). Building a densenet-based neural network with transformer and mbconv blocks for penile cancer classification. Applied Sciences, 14(22).

Lauande, M. G. M., Júnior, G. B., de Almeida, J. D. S., Fernandes, V. R. M., de Paiva, A. C., da Costa, R. M. G., Teles, A. M., da Silva, L. L., Brito, H. O., and Vidal, F. C. B. (2025). PCPAm - a dataset of histopathological images of penile cancer for classification tasks. Data in Brief, 61:111823. eCollection 2025 Aug.

Lauande, M. G. M., Teles, A. M., Lima da Silva, L., Matos, C. E. F., Braz Júnior, G., Cardoso de Paiva, A., Sousa de Almeida, J. D., da Costa Oliveira, R. M. G., Brito, H. O., dos Nascimento, A. P. S. A., Pestana, A. G., dos Pestana, A. P. S. A., Santos, A. G., and Lopes, F. F. (2022). Classification of histopathological images of penile cancer using densenet and transfer learning. In VISAPP. INSTICC, SciTePress.

Liang, Y., Sheng, G., Guo, Y., Zou, Y., Guo, H., Li, Z., Chang, S., Man, Q., Gao, S., and Hao, J. (2024). Prognostic significance of grade of malignancy based on histopathological differentiation and ki-67 in pancreatic ductal adenocarcinoma. Cancer Biology & Medicine, 21(5).

Malekmohammadi, A., Badiezadeh, A., Mirhassani, S. M., Gifani, P., and Vafaeezadeh, M. (2024). Classification of gleason grading in prostate cancer histopathology images using deep learning techniques: Yolo, vision transformers, and vision mamba.

Martins, L. Q., Bezerra, J. d. M., Silva, C. E. O. d., Silva, S. d. C. P. d., Figueiredo, L. F. d., Lima, J. C. C. d., Lima, L. F. L., Nunes, G. G. d. C., and Carvalho, L. E. W. d. (2025). Psycholog ical impacts and in quality of life of patients with penile cancer: Systematic literature review. Revista Brasileira de Cancerologia, 71(3):e–094823.

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.

Mokoena, T. S. (2025). Histological tumor grading: Progress and future directions. Review article on histological tumor grading systems and future perspectives.

Pinheiro, P. O. and Collobert, R. (2015). From image-level to pixel-level labeling with convolutional networks.

Rosas, N. A. B., Souza, P. M. d., Bandeira, V. H. R., Rondon, H. H. d. M. F., Castro, N. S., Heibel, M., Silva, K. L. T., and Alves, V. d. C. R. (2021). Risk factors for penile cancer: literature review. Brazilian Journal of Health Review, 4(3):13138–13147.

Santos, R., Martinez, V., Lauande, M., and Braz Júnior, G. (2026). Adversarial domain adaptation for penile cancer diagnosis in histopathological images. In Proceedings of the 21st International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, pages 560–567. INSTICC, SciTePress.

Silva, I. F. S., Junior, G. B., Silva, A. C., de Paiva, A. C., Oliveira, R., and Cunha, A. (2025a). Experimental study of an active learning-based method for the classification of penile cancer in histopathological images using convolutional neural networks. Procedia Computer Science.

Silva, J., Júnior, G. B., de Paiva, A. C., da Silva, I. S., and Pessoa, A. (2025b). Assessing the attention layers in convolutional neural networks for penile cancer detection in histopathological images. In Proceedings of the 27th ICEIS, pages 654–661. INSTICC, SciTePress.

Soares, A., de Carvalho, I. T., da Fonseca, A. G., Alencar, A. M., J., Leite, C. H. B., Bastos, D. A., Soares, J. P. H., Leite, K. R. M., Filho, M. R. B., Coelho, R. W. P., Cavallero, S. R. A., de Cassio Zequi, S., and de Ribamar Rodrigues Calixto, J. (2020). Penile cancer: a brazilian consensus statement for low- and middle-income countries. Journal of Cancer Research and Clinical Oncology, 146(12):3281–3296. Epub 2020 Oct 26.

Srinidhi, C. L., Ciga, O., and Martel, A. L. (2021). Deep neural network models for computational histopathology: A survey. Medical Image Analysis, 67:101813.

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.

Vale, J., Silva, I., Matos, C., Júnior, G. B., and Lauande, M. (2024). Redes densenet com mecanismos de atenção múltipla aplicadas à classificação automática de câncer peniano em imagens histopatológicas. In Anais do XXIV SBCAS, pages 495–506. SBC.

Xu, H., Wang, M., Shi, D., Qin, H., Zhang, Y., Liu, Z., Madabhushi, A., Gao, P., Cong, F., and Lu, C. (2025). When multiple instance learning meets foundation models: Advancing histological whole slide image analysis. Medical Image Analysis, 101:103456.

Zhou, X., Li, C., Rahaman, M. M., Yao, Y., Ai, S., Sun, C., Wang, Q., Zhang, Y., Li, M., Li, X., Jiang, T., Xue, D., Qi, S., and Teng, Y. (2020). A comprehensive review for breast histopathology image analysis using classical and deep neural networks. IEEE Access, 8:90931–90956.