Breast cancer detection in histopathological images using convolutional neural networks

  • Andrio Rodrigo Corrêa da Silva UFC
  • Iális Cavalcante de Paula Júnior UFC
  • Márcio André Baima Amora UFC

Resumo


Breast cancer is one of the biggest causes of death among women around the world. Diagnosing this disease early can offer better treatment to the patient. Intelligent systems have been used for the detection of diseases using images. In this work a convolutional neural network was used for the detection of breast cancer in histopathological images through Keras library and TensorFlow framework. Models were created for 4 datasets with different magnifying factors (40x, 100x, 200x and 400x). Using k-fold cross-validation, it was found that there was a better result for the set of 400x images with 98.44% accuracy in the training data. The set of 200x images obtained a better result for recall and f1-score.

Referências

Parkin, D. (1998). Epidemiology of cancer: global patterns and trends. In Toxicology Letters, pages 227–234. ScienceDirect, Lyon, France. http://dx.doi.org/10.1016/S0378-4274(98)00311-7.

Jangade, R. e Chauhan, R. (2006). Applications of machine learning in cancer prediction and prognosis. In Departments of Biological Science and Computing Science. Libertas Academica, Thousand Oaks, California.

Osareh, A. e Shadgar, B. (2010). Machine learning techniques to diagnose breast cancer. In 5th International Symposium on Health Informatics and Bioinformatics. IEEE,Antalya, Turkey. http://dx.doi.org/10.1109/HIBIT.2010.5478895

Chollet, F. (2015). Keras. https://github.com/keras-team/keras.

Gayathri, B. e Sumathi, C. (2016). Comparative study of relevance vector machine with various machine learning techniques used for detecting breast cancer. In IEEE International Conference on Computational Intelligence and Computing Research, pages 1–5. IEEE, Chennai, India. http://dx.doi.org/10.1109/ICCIC.2016.7919576

Spanhol, F., Oliveira, L., Petitjean, C., e Heutte, L. (2016). A dataset for breast cancer histopathological image classification. In IEEE Transactions on biomedical engineering (TBME), pages 1455–1462. http://dx.doi.org/10.1109/TBME.2015.2496264

Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., Wicke, M., Yu, Y., e Zheng, X. (2016). Tensorflow: A system for large-scale machine learning. In 12th USENIX Symposium on Operating Systems Design and Implementation. Usenix, Savannah, GA, USA.

Bray, F., Ferlay, J., Soerjomataram, I., Siegel, R., Torre, L., e Jemal, A. (2018). Global cancer statistics 2018: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries: Global cancer statistics 2018. In CA: A Cancer Journal for Clinicians. http://dx.doi.org/10.3322/caac.21492
Publicado
11/06/2019
DA SILVA, Andrio Rodrigo Corrêa; JÚNIOR, Iális Cavalcante de Paula ; AMORA, Márcio André Baima . Breast cancer detection in histopathological images using convolutional neural networks. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 19. , 2019, Niterói. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2019 . p. 1-9. ISSN 2763-8952. DOI: https://doi.org/10.5753/sbcas.2019.6237.