Segmentação Automática de Imagens Térmicas das Mamas Utilizando Limiarização com Refinamento Adaptativo

• Matheus Baffa IFSEMG
• Deivison Cheloni IFSEMG
• Lucas Lattari IFSEMG

DOI: https://doi.org/10.5753/sbcas.2016.9896

Abstract

Breast cancer is the most common type of cancer in the world. New cases of cancer are detected every year, and 25% of them are breast cancer. It is known that early diagnosis is critical for the prognosis of patients, and image based techniques has been developed to guide an effective, minimally invasive and cheaper way to diagnose breast cancer. In this work, we propose an automatic segmentation method based on adaptive thresholding. The experimental results show that our method is competitive with other works on both solution quality and runtime performance, achieving 96% of accuracy and 98% of sensibility. Furthermore, it is simpler to implement, computationally efficient and suitable for real time applications.

References

Arora, N. M., Martins, D., Ruggerio, D., Tousimis, E., Swistel, A. J., Osborne, M. P.,and Simmons, R. M. (2008). Effectiveness of a noninvasive digital infrared thermal imaging systems in the detection of breast cancer. American Journal of Surgery, 196(4):523–526.

Gore, J. P. and Xu, L. X. (2014). Thermal Imaging for Biological and Medical Diagnostics. CRC Press.

HCB (2015). Informação: Saiba quais são os tipos de câncer mais comuns no brasil. http://www.hcancerbarretos.com.br/82-institucional/noticias-institucional/1300-informacao-saiba-quais-saoos-tipos-de-cancer-mais-comuns-no-brasil. Acesso em: 29 de outubro de 2015.

INCA (2015). Tipos de câncer. http://www2.inca.gov.br/wps/wcm/connect/tiposdecancer/site/home/mama. Acesso em: 07 de novembro de 2015.

Li, X., Aldridge, B., Fisher, R. B., and Rees, J. (2011). Estimating the ground truth from multiple individual segmentations incorporating prior pattern analysis with application to skin lesion segmentation. In ISBI, pages 1438–1441. IEEE.

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

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.

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