Segmentação de Imagens Histológicas da Cavidade Oral: Um Estudo sobre Variantes da U-Net e Lightweight Backbones

• Luana R. Borges UFU
• Vitória F. C. Silva UFU
• Davi Soares UFU
• Gustavo C. Miranda UFU
• Luis Felipe G. S. Paim UFU
• Daniel B. Gonçalves UFU
• Adriano B. Silva UFU
• Domingos L. L. de Oliveira UFU / IFSP
• Leandro A. Neves UNESP
• Marcelo Z. do Nascimento UFU

DOI: https://doi.org/10.5753/sbcas.2026.20794

Resumo

O câncer da cavidade oral apresenta elevada incidência, tornando o diagnóstico precoce essencial para a melhoria do prognóstico. Nesse contexto, a análise automática de imagens histopatológicas tem ganhado destaque, embora a elevada complexidade estrutural e a variabilidade morfológica imponham desafios significativos. A segmentação semântica constitui uma etapa fundamental em sistemas de diagnóstico assistido por computador, pois permite a delimitação automática de regiões de interesse. Este trabalho avalia diferentes arquiteturas da família U-Net para a segmentação de imagens histológicas, incluindo modelos tradicionais, variantes aprimoradas e versões com lightweight pre-trained backbones. Os experimentos foram conduzidos em dois conjuntos de dados públicos, alcançando coeficientes Dice de 0,912 e 0,871 para os bancos OCDC e OralEpitheliumDB, respectivamente. Além disso, foram analisados o impacto do aumento de dados, do pré-treinamento e o compromisso entre desempenho de segmentação e eficiência computacional. Os resultados evidenciam o potencial das arquiteturas avaliadas e contribuem para a compreensão de estratégias mais robustas e eficientes nesse domínio.

Referências

Banerji, S. and Mitra, S. (2022). Deep learning in histopathology: A review. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 12(1):e1439.

Basu, A., Senapati, P., Deb, M., Rai, R., and Dhal, K. G. (2024). A survey on recent trends in deep learning for nucleus segmentation from histopathology images. Evolving Systems, 15(1):203–248.

Cheplygina, V. e. a. (2019). Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis. Medical Image Analysis.

Crepaldi, G. G., de Oliveira, D. L., Tosta, T. A., Neves, L. A., Silva, A. B., Martins, A. S., and do Nascimento, M. Z. (2025). Nuclear segmentation in histological images using multiple attention system mixing. In 2025 IEEE 38th International Symposium on Computer-Based Medical Systems (CBMS), pages 154–159. IEEE.

de Oliveira, D. L., Tosta, T. A., Neves, L. A., Silva, A. B., Martins, A. S., de Fariall, P. R., and do Nascimento, M. Z. (2025). A u-net-based approach for histological tissue segmentation using rcaug data augmentation. In 2025 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pages 1–6. IEEE.

Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861.

Litjens, G. e. a. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis.

Madabhushi, A. and Lee, G. (2016). Image analysis and machine learning in digital pathology. Medical Image Analysis.

Moscalu, M., Moscalu, R., Dascălu, C. G., T, arcă, V., Cojocaru, E., Costin, I. M., T, arcă, E., and S, erban, I. L. (2023). Histopathological images analysis and predictive modeling implemented in digital pathology—current affairs and perspectives. Diagnostics, 13(14):2379.

Oktay, O., Schlemper, J., Folgoc, L. L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N. Y., Kainz, B., et al. (2018). Attention u-net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999.

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.

Santos, D. F., de Faria, P. R., Travençolo, B. A., and do Nascimento, M. Z. (2023a). Influence of data augmentation strategies on the segmentation of oral histological images using fully convolutional neural networks. Journal of Digital Imaging, 36(4):1608–1623.

Santos, D. F. D., de Faria, P. R., Loyola, A. M., Cardoso, S. V., Travençolo, B. A. N., and do Nascimento, M. Z. (2023b). Hematoxylin and eosin stained oral squamous cell carcinoma histological images dataset.

Santos, M. d. O. (2023). Estimativa de incidência de câncer no brasil, 2023-2025. Revista Brasileira de Cancerologia, 69(1).

Shorten, C. and Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data.

Silva, A. B., Martins, A. S., Tosta, T. A. A., Loyola, A. M., Cardoso, S. V., Neves, L. A., de Faria, P. R., and do Nascimento, M. Z. (2024a). Oralepitheliumdb: A dataset for oral epithelial dysplasia image segmentation and classification. Journal of Imaging Informatics in Medicine, 37(4):1691–1710.

Silva, A. B., Rozendo, G. B., Tosta, T. A., Martins, A. S., Loyola, A. M., Cardoso, S. V., Lumini, A., Neves, L. A., de Faria, P. R., and do Nascimento, M. Z. (2023). Cnn ensembles for nuclei segmentation on histological images of oed. In 2023 IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS), pages 601–604. IEEE.

Silva, A. B., Tosta, T. A., Neves, L. A., Martins, A. S., De Faria, P. R., and Do Nascimento, M. Z. (2024b). Ensemble of semantic segmentation models for oral epithelial dysplasia images. In 2024 37th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pages 1–6. IEEE.

Springenberg, M., Frommholz, A., Wenzel, M., Weicken, E., Ma, J., and Strodthoff, N. (2023). From modern cnns to vision transformers: Assessing the performance, robustness, and classification strategies of deep learning models in histopathology. Medical Image Analysis, 87:102809.

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

Tan, M. and Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105–6114. PMLR.

Xu, Y., Quan, R., Xu, W., Huang, Y., Chen, X., and Liu, F. (2024). Advances in medical image segmentation: a comprehensive review of traditional, deep learning and hybrid approaches. Bioengineering, 11(10):1034.

Zhou, Z., Rahman Siddiquee, M. M., Tajbakhsh, N., and Liang, J. (2018). Unet++: A nested u-net architecture for medical image segmentation. In Deep learning in medical image analysis and multimodal learning for clinical decision support: 4th international workshop, DLMIA 2018, and 8th international workshop, ML-CDS 2018, held in conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, proceedings 4, pages 3–11. Springer.

Zunair, H. and Hamza, A. B. (2021). Sharp u-net: Depthwise convolutional network for biomedical image segmentation. Computers in biology and medicine, 136:104699.