Classification of breast injuries in categories 4 and 5 of the BI-RADS® standard using neural networks




Breast cancer; BI-RADS® Classification; Image processing; Neural networks.


Breast cancer is the disease with the highest incidence among women worldwide, with an estimate for Brazil in the 2020-2021 biennium about 66,280 new cases of breast cancer, which corresponds to a rate of 29.7% of cases in the female population and about 15,000 deaths from the disease. Mammography is one of the most used tests for early detection of this type of neoplasm. However, errors occur in the reading and interpretation of reports, even a well-trained professional has a success rate between 65% and 75% with an amount of false negative varying between 15% to 30% and a false positive of 7% to 10%, resulting in an unnecessary amount of biopsy, 65% to 90% of tissue biopsies with suspected cancer are benign, causing emotional and physical repercussions for patients. Computer systems can be developed to aid in medical diagnosis. This article applied neural network techniques to develop a computational tool capable of classifying injuries from categories 4 and 5 of the BI-RADS® standard. The results acquired by the software, observed that the best classifier with regard to the accuracy rate was Deep Learning, reaching a percentage of 82.60%, the Support Vectors Machine - SVM had a percentage of 73.97%. This demonstrates that the neural network techniques used in the software design show an efficiency in the lesion classification task.


Alves-Ribeiro, F. A., Costa-Silva, D. R., Escórcio-Dourado, C. S., da Silva-Neto, O. P., de Castro-Gonçalves, M. E., de Ribeiro, V. O., ... & da Silva, B. B. (2017). Masse detection in mammographic images using texture feature extraction and neural networks. Journal of Computational and Theoretical Nanoscience, 14(4), 2064-2068.

AMERICAN COLLEGE OF RADIOLOGY (ACR) (2016). Atlas BI-RADS do ACR: sistema de laudos e registro de dados de imagem da mama / American College of Radiology; [tradução Angela Caracik] Colégio Brasileiro de Radiologia. 2. ed. - São Pàulo

Balas, N., Yun, H., Jaeger, B. C., Aung, M., & Jolly, P. E. (2020). Factors associated with breast cancer screening behaviors in a sample of Jamaican women in 2013. Women & health, 60(9), 1032-1039.

Batista, G. V., Moreira, J. A., Leite, A. L., & Moreira, C. I. H. (2020). Câncer de mama: fatores de risco e métodos de prevenção. Research, Society and Development, 9(12), e15191211077-e15191211077.

Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992, July). A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on Computational learning theory (pp. 144-152).

Costa, F., & Ferreira, D. D. (2020, December). Classificação de nódulos mamários com máquina de vetores de suporte. In Congresso Brasileiro de Automática-CBA (Vol. 2, No. 1).

El Atlas, N., El Aroussi, M., & Wahbi, M. (2014, November). Computer-aided breast cancer detection using mammograms: A review. In 2014 Second World Conference on Complex Systems (WCCS) (pp. 626-631). IEEE.

Fernandes, I., & dos Santos, W. (2014). Classificação de mamografias utilizando extração de atributos de textura e redes neurais artificiais. In Congresso Brasileiro de Engenharia Biomédica (Vol. 8).

Ganesan, K., Acharya, U. R., Chua, C. K., Min, L. C., Abraham, K. T., & Ng, K. H. (2012). Computer-aided breast cancer detection using mammograms: a review. IEEE Reviews in biomedical engineering, 6, 77-98.

Giess, C. S., Frost, E. P., & Birdwell, R. L. (2012, August). Difficulties and errors in diagnosis of breast neoplasms. In Seminars in Ultrasound, CT and MRI (Vol. 33, No. 4, pp. 288-299). WB Saunders.

Giger, M. L. (2000). Computer-aided diagnosis of breast lesions in medical images. Computing in Science & Engineering, 2(5), 39-45.

International Agency for Research on Cancer. (2020). Global cancer observatory: cancer today. 2020.

Gonçalves, C. B. (2017). Detecção de câncer de mama utilizando imagens termográficas.

Gonzalez, R. C., Woods, R. E., & Eddins, S. L. (2010). Morphological reconstruction. Digital image processing using MATLAB, MathWorks.

Guimaraes, M. D., Bitencourt, A. G., Marchiori, E., Chojniak, R., Gross, J. L., & Kundra, V. (2014). Imaging acute complications in cancer patients: what should be evaluated in the emergency setting?. Cancer Imaging, 14(1), 1-12.

Haralick, R. M., Shanmugam, K., & Dinstein, I. H. (1973). Textural features for image classification. IEEE Transactions on systems, man, and cybernetics, (6), 610-621.

Heath, M. D., & Bowyer, K. W. (2000, June). Mass detection by relative image intensity. In Proceedings of the 5th International Workshop on Digital Mammography (IWDM-2000) (pp. 219-225).

Huynh, B. Q., Li, H., & Giger, M. L. (2016). Digital mammographic tumor classification using transfer learning from deep convolutional neural networks. Journal of Medical Imaging, 3(3), 034501.

INCA National Cancer Institute. Controle do Cancer de Mama, (2019) [Online]. Available: [Accessed: 12/09/2021].

Justo, N., Wilking, N., Jönsson, B., Luciani, S., & Cazap, E. (2013). A review of breast cancer care and outcomes in Latin America. The oncologist, 18(3), 248-256.

LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. nature, 521(7553), 436-444.

Moore, K. L., Dalley, A. F., & ARTHUER, F. (2018). AgurAMR. Anatomia orientada para a clínica. Guanabara 2014.

Neto, O. P. S., Silva, A. C., Paiva, A. C., & Gattass, M. (2017). Automatic mass detection in mammography images using particle swarm optimization and functional diversity indexes. Multimedia Tools and Applications, 76(18), 19263-19289.

Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE transactions on systems, man, and cybernetics, 9(1), 62-66.

Pacífico, L. (2020, October). Agrupamento de imagens baseado em uma abordagem híbrida entre a otimização por busca em grupo e k-means para a segmentação automática de doenças em plantas. In Anais do XVII Encontro Nacional de Inteligência Artificial e Computacional (pp. 152-163). SBC.

Pavan, A. L. M., Vacavant, A., Trindade, A. P., & de Pina, D. R. (2017). Fibroglandular tissue quantification in mammography by optimized fuzzy C-means with variable compactness. Irbm, 38(4), 228-233.

Prado, N., Loiola, P., Guimarães, T., Ohara, E. C. C., & Oliveira, L. D. R. (2020). Gestante com diagnóstico de câncer de mama: prevenção, diagnóstico e assistência. Brazilian Journal of Health Review, 3(1), 1109-1131.

Reese, H. (2017). Understanding the differences between AI, machine learning, and deep learning. URL: https://www. techrepublic. com/article/understandingthedifferencesbetweenaimachine learninganddeeplearning.

Sala, D. C. P. (2021). Rastreamento mamográfico no Brasil: determinantes à implementação no Sistema Único de Saúde e contribuições da Atenção Primária à Saúde (Doctoral dissertation, Universidade de São Paulo).

Santos, T. A., & Gonzaga, M. F. N. (2018). Fisiopatologia do câncer de mama e os fatores relacionados. Revista Saúde em Foco, 10, 359-366.

Schaeffer, S. E. (2007). Graph clustering. Computer science review, 1(1), 27-64.

Tilman, D. (2001). Functional diversity. Encyclopedia of biodiversity, 3(1), 109-120.

Tortora, G. J., & Derrickson, B. (2016). Corpo Humano-: Fundamentos de Anatomia e Fisiologia. Artmed Editora.

Van Den Bergh, F. (2007). An analysis of particle swarm optimizers (Doctoral dissertation, University of Pretoria).

Vapnik, V. N. (1999). An overview of statistical learning theory. IEEE transactions on neural networks, 10(5), 988-999.



How to Cite

NERY JÚNIOR, E. de J. .; SILVA NETO, O. P. da .; RIBEIRO, F. A. A. .; LIMA, F. das C. A. .; VERDES, L. M. C. C. .; SILVA, D. R. C. .; OLIVEIRA, M. da C. B. .; DINIZ, P. H. B. .; PAIVA, A. C. de .; SILVA, A. C. . Classification of breast injuries in categories 4 and 5 of the BI-RADS® standard using neural networks . Research, Society and Development, [S. l.], v. 11, n. 9, p. e26611931305, 2022. DOI: 10.33448/rsd-v11i9.31305. Disponível em: Acesso em: 30 sep. 2022.



Exact and Earth Sciences