Classificação de Células Cervicais Cancerígenas com CNNs e ViTs em Ensemble para Auxílio ao Diagnóstico Médico
Resumo
O câncer cervical é um problema global de saúde pública que exige métodos eficazes de triagem. Este trabalho propõe um ensemble de EfficientViT, EVA-02 e EdgeNeXt para classificação automática de células cervicais. Foram avaliados os conjuntos Herlev (917 imagens) e SIPaKMeD (4.049 imagens) em tarefas de classificação binária e multiclasse. A metodologia inclui transferência de aprendizado, aumento de dados e validação cruzada (5 folds). No conjunto Herlev, os resultados foram 98,35% de acurácia (binário) e 83,40% (7 classes). No SIPaKMeD, obteve-se 99,73% (binário), 98,96% (3 classes) e 98,08% (5 classes), atingindo o estado da arte. Os resultados demonstram o potencial do modelo para auxílio ao diagnóstico médico, reduzindo a necessidade de análise manual.Referências
Alohali, M. A., El-Rashidy, N., Alaklabi, S., Elmannai, H., Alharbi, S., and Saleh, H. (2024). Swin-GA-RF: genetic algorithm-based Swin Transformer and random forest for enhancing cervical cancer classification. Frontiers in Oncology, 14.
Bedell, S. L., Goldstein, L. S., Goldstein, A. R., and Goldstein, A. T. (2020). Cervical cancer screening: Past, present, and future. Sexual Medicine Reviews, 8(1):28–37.
Bridge, P. and Sawilowsky, S. (1999). Increasing Physicians’ Awareness of the Impact of Statistics on Research Outcomes: Comparative Power of the t-test and Wilcoxon Rank-Sum Test in Small Samples Applied Research. J CLIN EPIDEMIOL.
Cai, H., Li, J., Hu, M., Gan, C., and Han, S. (2022). Efficientvit: Multi-scale linear attention for high-resolution dense prediction. arXiv preprint arXiv:2205.14756.
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929.
Fang, M., Liao, B., Lei, X., and Wu, F.-X. (2024a). A systematic review on deep learning based methods for cervical cell image analysis. Neurocomputing, 610:128630.
Fang, Y., Sun, Q., Wang, X., Huang, T., Wang, X., and Cao, Y. (2024b). Eva-02: A visual representation for neon genesis. Image and Vision Computing, 149:105171.
Ferlay, J., Colombet, M., Soerjomataram, I., and D. M., P. (2024a). Global cancer observatory: Cancer today. Acessado em 17 de abril de 2024.
Ferlay, J., Laversanne, M., Ervik, M., Lam, F., Colombet, M., Mery, L., Piñeros, M., Znaor, A., Soerjomataram, I., and Bray, F. (2024b). Global cancer observatory: Cancer tomorrow (version 1.1). Acessado em 27 de dezembro de 2024.
Hou, X., Shen, G., Zhou, L., Li, Y., Wang, T., and Ma, X. (2022). Artificial intelligence in cervical cancer screening and diagnosis. Frontiers in Oncology, 12.
Ikenberg, H., Lieder, S., Ahr, A., Wilhelm, M., Schön, C., and Xhaja, A. (2023). Comparison of the hologic genius digital diagnostics system with the thinprep imaging system—a retrospective assessment. Cancer Cytopathology, 131(7):424–432.
Jantzen, J., Norup, J., Dounias, G., and Bjerregaard, B. (2005). Pap-smear benchmark data for pattern classification. NiSIS, pages 1–9.
Jiang, P., Li, X., Shen, H., Chen, Y., Wang, L., Chen, H., Feng, J., and Liu, J. (2023). A systematic review of deep learning-based cervical cytology screening: from cell identification to whole slide image analysis. Artif. Intell. Rev., 56(Suppl 2):2687–2758.
Khare, S. K., Blanes-Vidal, V., Booth, B. B., Petersen, L. K., and Nadimi, E. S. (2024). A systematic review and research recommendations on artificial intelligence for automated cervical cancer detection. WIREs Data Min. Knowl. Discov., 14(6):e1550.
Maaz, M., Shaker, A., Cholakkal, H., Khan, S., Zamir, S. W., Anwer, R. M., and Khan, F. S. (2022). Edgenext: Efficiently amalgamated cnn-transformer architecture for mobile vision applications. In CADL. Springer.
Mathew, B. and Cheriyan, R. (2024). A detailed review on classification and risk factor analysis of cervical cancer using artificial intelligence. In IATMSI, pages 1–6. IEEE.
Plissiti, M. E., Dimitrakopoulos, P., Sfikas, G., Nikou, C., Krikoni, O., and Charchanti, A. (2018). Sipakmed: A new dataset for feature and image based classification of normal and pathological cervical cells in pap smear images. In ICIP, pages 3144–3148. IEEE.
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., and Sutskever, I. (2021). Learning transferable visual models from natural language supervision.
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A. C., and Fei-Fei, L. (2015). ImageNet Large Scale Visual Recognition Challenge. IJCV, 115(3):211–252.
S., V., N., M. D., G., M., D., V. K., C., S., and C., A. M. (2024). Predicting cervical cancer using advanced machine learning algorithms. In ICSCSS, pages 1600–1604.
Sholik, M., Fatichah, C., and Amaliah, B. (2024). Deep feature extraction of pap smear images based on convolutional neural network and vision transformer for cervical cancer classification. In IAICT, pages 290–296. IEEE.
Tolles, W. E. and Bostrom, R. C. (1956). Automatic screening of cytological smears for cancer: The instrumentation. Ann. N. Y. Acad. Sci., 63(6):1211–1218.
Vargas-Cardona, H. D., Rodriguez-Lopez, M., Arrivillaga, M., Vergara-Sanchez, C., García-Cifuentes, J. P., Bermúdez, P. C., and Jaramillo-Botero, A. (2024). Artificial intelligence for cervical cancer screening: Scoping review, 2009–2022. International Journal of Gynecology & Obstetrics, 165(2):566–578.
Wu, T., Lucas, E., Zhao, F., Basu, P., and Qiao, Y. (2024). Artificial intelligence strengthenes cervical cancer screening–present and future. Cancer Biol. Med., 21(10):864.
Wubineh, B. Z., Rusiecki, A., and Halawa, K. (2024). Segmentation and classification techniques for pap smear images in detecting cervical cancer: A systematic review. IEEE Access, 12:118195–118213.
Bedell, S. L., Goldstein, L. S., Goldstein, A. R., and Goldstein, A. T. (2020). Cervical cancer screening: Past, present, and future. Sexual Medicine Reviews, 8(1):28–37.
Bridge, P. and Sawilowsky, S. (1999). Increasing Physicians’ Awareness of the Impact of Statistics on Research Outcomes: Comparative Power of the t-test and Wilcoxon Rank-Sum Test in Small Samples Applied Research. J CLIN EPIDEMIOL.
Cai, H., Li, J., Hu, M., Gan, C., and Han, S. (2022). Efficientvit: Multi-scale linear attention for high-resolution dense prediction. arXiv preprint arXiv:2205.14756.
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929.
Fang, M., Liao, B., Lei, X., and Wu, F.-X. (2024a). A systematic review on deep learning based methods for cervical cell image analysis. Neurocomputing, 610:128630.
Fang, Y., Sun, Q., Wang, X., Huang, T., Wang, X., and Cao, Y. (2024b). Eva-02: A visual representation for neon genesis. Image and Vision Computing, 149:105171.
Ferlay, J., Colombet, M., Soerjomataram, I., and D. M., P. (2024a). Global cancer observatory: Cancer today. Acessado em 17 de abril de 2024.
Ferlay, J., Laversanne, M., Ervik, M., Lam, F., Colombet, M., Mery, L., Piñeros, M., Znaor, A., Soerjomataram, I., and Bray, F. (2024b). Global cancer observatory: Cancer tomorrow (version 1.1). Acessado em 27 de dezembro de 2024.
Hou, X., Shen, G., Zhou, L., Li, Y., Wang, T., and Ma, X. (2022). Artificial intelligence in cervical cancer screening and diagnosis. Frontiers in Oncology, 12.
Ikenberg, H., Lieder, S., Ahr, A., Wilhelm, M., Schön, C., and Xhaja, A. (2023). Comparison of the hologic genius digital diagnostics system with the thinprep imaging system—a retrospective assessment. Cancer Cytopathology, 131(7):424–432.
Jantzen, J., Norup, J., Dounias, G., and Bjerregaard, B. (2005). Pap-smear benchmark data for pattern classification. NiSIS, pages 1–9.
Jiang, P., Li, X., Shen, H., Chen, Y., Wang, L., Chen, H., Feng, J., and Liu, J. (2023). A systematic review of deep learning-based cervical cytology screening: from cell identification to whole slide image analysis. Artif. Intell. Rev., 56(Suppl 2):2687–2758.
Khare, S. K., Blanes-Vidal, V., Booth, B. B., Petersen, L. K., and Nadimi, E. S. (2024). A systematic review and research recommendations on artificial intelligence for automated cervical cancer detection. WIREs Data Min. Knowl. Discov., 14(6):e1550.
Maaz, M., Shaker, A., Cholakkal, H., Khan, S., Zamir, S. W., Anwer, R. M., and Khan, F. S. (2022). Edgenext: Efficiently amalgamated cnn-transformer architecture for mobile vision applications. In CADL. Springer.
Mathew, B. and Cheriyan, R. (2024). A detailed review on classification and risk factor analysis of cervical cancer using artificial intelligence. In IATMSI, pages 1–6. IEEE.
Plissiti, M. E., Dimitrakopoulos, P., Sfikas, G., Nikou, C., Krikoni, O., and Charchanti, A. (2018). Sipakmed: A new dataset for feature and image based classification of normal and pathological cervical cells in pap smear images. In ICIP, pages 3144–3148. IEEE.
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., and Sutskever, I. (2021). Learning transferable visual models from natural language supervision.
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A. C., and Fei-Fei, L. (2015). ImageNet Large Scale Visual Recognition Challenge. IJCV, 115(3):211–252.
S., V., N., M. D., G., M., D., V. K., C., S., and C., A. M. (2024). Predicting cervical cancer using advanced machine learning algorithms. In ICSCSS, pages 1600–1604.
Sholik, M., Fatichah, C., and Amaliah, B. (2024). Deep feature extraction of pap smear images based on convolutional neural network and vision transformer for cervical cancer classification. In IAICT, pages 290–296. IEEE.
Tolles, W. E. and Bostrom, R. C. (1956). Automatic screening of cytological smears for cancer: The instrumentation. Ann. N. Y. Acad. Sci., 63(6):1211–1218.
Vargas-Cardona, H. D., Rodriguez-Lopez, M., Arrivillaga, M., Vergara-Sanchez, C., García-Cifuentes, J. P., Bermúdez, P. C., and Jaramillo-Botero, A. (2024). Artificial intelligence for cervical cancer screening: Scoping review, 2009–2022. International Journal of Gynecology & Obstetrics, 165(2):566–578.
Wu, T., Lucas, E., Zhao, F., Basu, P., and Qiao, Y. (2024). Artificial intelligence strengthenes cervical cancer screening–present and future. Cancer Biol. Med., 21(10):864.
Wubineh, B. Z., Rusiecki, A., and Halawa, K. (2024). Segmentation and classification techniques for pap smear images in detecting cervical cancer: A systematic review. IEEE Access, 12:118195–118213.
Publicado
09/06/2025
Como Citar
LIMA, Marcelo Victor; BRITTO, Maria Helena Mesquita; BRITTO NETO, Laurindo.
Classificação de Células Cervicais Cancerígenas com CNNs e ViTs em Ensemble para Auxílio ao Diagnóstico Médico. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 25. , 2025, Porto Alegre/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 497-508.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2025.7467.
