Segmentação de Imagens Infravermelhas Para Detecção do Câncer de Mama Utilizando U-NET CNN

• Matheus de Freitas Oliveira Baffa USP
• Alessandra Martins Coelho IF SudesteMG
• Aura Conci UFF

DOI: https://doi.org/10.5753/sbcas.2021.16058

Abstract

Breast cancer is the leading type of cancer among women. According to the World Cancer Research Fund, in 2018, over 2 million new cases were detected around the world. Despite its high occurrence, early detection provides a better prognosis and helps increases the patient's survival. Significant advances in screening techniques, such as infrared imaging, have provided a cheap and less invasive way to detect the disease. Besides, computational tools can be used to assist doctors to provide a better diagnosis. Thus, this paper presents a segmentation method based on U-Net Convolutional Neural Networks. In contrast to state-of-art, machine learning approaches have shown to be efficient for the region of interest segmentation, reaching an accuracy of 98.24% and an Intersection-Over-Union of 94.38%. The use of this segmentation method may be very useful for classification tasks, once the region of interest is well delimited for feature extraction.

References

Amalu, W., Hobbins, W., Head, J., and Elliot, R. (2006). Infrared imaging of the breast— an overview. The Biomedical Engineering Handbook, 3rd ed., Medical Devices and Systems. CRC Press, Baton Rouge.

Baffa, M., Cheloni, D., and Lattari, L. (2016). Segmentação automática de imagens térmicas das mamas utilizando limiarização com refinamento adaptativo. In Anais do XVI Workshop de Informática Médica, pages 39–48. SBC.

Baffa, M. F. O. and Lattari, L. G. (2018). Convolutional neural networks for static and dynamic breast infrared imaging classification. In 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pages 174–181. IEEE.

Conci, A., Azevedo, E., and Leta, F. (2008). Computação Gráfica: Teoria e Prática, volume 2. Elsevier Editora.

Gore, J. P. and Xu, L. X. (2003). Thermal imaging for biological and medical diagnostics. Biomedical Photonics Handbook, 17:1–12.

IFF/Fiocruz. (2021). Câncer de mama: a importância do diagnóstico precoce. Disponível em: <http://www.iff.fiocruz.br/index.php/8-noticias/274-cancerdemama>. Acesso em: 05 abr. 2021.

Instituto Nacional do Câncer. (2021). Câncer de mama. Disponível em: <https://www.inca.gov.br/tipos-de-cancer/cancer-de-mama>. Acesso em: 05 abr. 2021.

Ismael, A. M. and Sengür, A. (2021). Deep learning approaches for covid-19 detection based on chest x-ray images. Expert Systems with Applications, 164:114054.

Marques, R. S. (2012). Segmentação automática das mamas em imagens térmicas. Master’s thesis, Instituto de Computação, Universidade Federal Fluminense, Niterói, RJ, Brasil.

Marques, R. S., Conci, A., Perez, M. G., Andaluz, V. H., and Mejia, T. M. (2016). An approach for automatic segmentation of thermal imaging in computer aided diagnosis. IEEE Latin America Transactions, 14(4):1856–1865.

Melo, R. H. C., Conci, A., and Vasconcelos, C. N. (2017). On the use of fully convolutional networks on evaluation of infrared breast image segmentations. In Anais do XVII Workshop de Informática Médica. SBC.

Motta, L. S. (2010). Obtenção automática da regi˜ao de interesse em termogramas frontais da mama para o auxílio à detecção precoce de doenças. Master’s thesis, Instituto de Computação, Universidade Federal Fluminense, Niterói, RJ, Brasil.

Rehman, A., Khan, M. A., Saba, T., Mehmood, Z., Tariq, U., and Ayesha, N. (2021). Microscopic brain tumor detection and classification using 3d cnn and feature selection architecture. Microscopy Research and Technique, 84(1):133–149.

Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer.

Silva, L., Saade, D., Sequeiros, G., Silva, A., Paiva, A., Bravo, R., and Conci, A. (2014). A new database for breast research with infrared image. Journal of Medical Imaging and Health Informatics, 4(1):92–100.

U.S. National Cancer Institute. (2021). Breast cancer screening (pdq) - patient version. Disponível em: <https://www.cancer.gov/types/breast/patient/breast-screening-pdq>. Acesso em: 05 abr. 2021.

Zuluaga-Gomez, J., Zerhouni, N., Al Masry, Z., Devalland, C., and Varnier, C. (2019). A survey of breast cancer screening techniques: thermography and electrical impedance tomography. Journal of medical engineering & technology, 43(5):305–322