Advertisement

Segmentation and Classification of Noisy Thermographic Images as an Aid for Identifying Risk Levels of Breast Cancer

  • Pilar Gomez-GilEmail author
  • Daniela Reynoso-Armenta
  • Jorge Castro-Ramos
  • Juan Manuel Ramirez-Cortes
  • Vicente Alarcon-Aquino
Chapter
  • 47 Downloads
Part of the Studies in Computational Intelligence book series (SCI, volume 862)

Abstract

During 2016, breast cancer was the second cause of death among women within ages of 24–30. This makes mandatory to find reliable strategies that support physicians and medical services for early diagnosis of such disease. Currently, mammography is considered the gold instrument for assessing the risk of having breast cancer, but other methods are being analyzed, looking for systems that may be cheaper and easier to apply, including the use of thermographic images. In this paper, we present an analysis of the performance of a system based on a “Feed-Forward Neural Network” (FFNN), for the identification of two and three levels of risk cancer. Indeed, a system based on a “Regions-Convolutional Neural network” (R-CNN) for automatic segmentation of the breast is proposed. Both systems were tested in a private database developed by the “Center for Studies and Cancer Prevention, A.C.” located in Oaxaca, Mexico, which presents important challenges as class unbalances, a slack recording with respect to application of the protocol and noise. The systems were evaluated using three subsets of the database, built using images with different levels of challenges. Our results showed that a FNNN classifier performed well only with data strictly following the protocol, while the levels of performance with noisy data are not yet acceptable for real applications. In the other hand, the results obtained by the automatic segmentation based on R-CNN were competitive, encouraging for more research in this area.

Keywords

Deep convolutional neural networks (CNN) Breast cancer Regions-CNN Classification Image processing Thermography 

Notes

Acknowledgements

The authors would like to thank Dr. Francisco Gutierrez and the rest of the staff of CEPREC for their kindly support and advice during the development of this research. This work was supported by INAOE. D. Reynoso thanks the National Council of Science and Technology in Mexico (CONACYT) for the scholarship provided during the development of this work.

References

  1. 1.
    U. S. Food and Drug Administration. Mammography: What You Need to Know, 27 October 2017. [Online]. Available: https://www.fda.gov/ForConsumers/ConsumerUpdates/ucm420463.htm. Accessed 16 Febrero 2018
  2. 2.
    U.S. Food and Drug Administration.: Breast Cancer Screening: Thermogram No Substitute for Mammogram, 30 10 2017. [Online]. Available: https://www.fda.gov/ForConsumers/ConsumerUpdates/ucm257499.htm. Accessed 16 Febrero 2018
  3. 3.
    Centro de Estudios y Prevención del Cancer A.C.: Centro de Estudios y Prevención del Cancer, A.C. (2018) [Online]. Available: http://ceprec.org/index/index.html. Accessed 13 Febrero 2019
  4. 4.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH (2014)Google Scholar
  5. 5.
    Gonzalez-Hernandez, J., Recinella, A., Kandlikar, S., Dabydeen, D., Medeiros, L., Phatak, P.: Technology, application and potential of dynamic breast thermography for the detection of breast cancer. Int. J. Heat Mass Trans. 131, 558–573 (2019)CrossRefGoogle Scholar
  6. 6.
    Koay, J., Herry, C., Frize, M.: Analysis of breast thermography with an artificial neural network. In: 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEMBS ‘04, Vol. 1, pp. 1159–1162 (2004)Google Scholar
  7. 7.
    Sossa Azuela, J.H., Rodríguez Morales, R.: Capítulo 2. Proceso de captación y formación de una imagen. In: Procesamiento y Análisis Digital de Imágenes, Madrid, Alfaomega pp. 45–59 (2011)Google Scholar
  8. 8.
    Zare, I., Ghafarpour, A., Zadeh, H., Haddadnia, J., Mohammad, S., Isfahani, M.: Evaluating the thermal imaging system in detecting certain types of breast tissue masses. Biomed. Res. 27(3), 670–675 (2016)Google Scholar
  9. 9.
    Hankare, P., Shah, K., Nair, D., Nair, D.: Breast cancer detection using thermography. Int. Res. J. Eng. Technol. 3(4), 2356–2395 (2016)Google Scholar
  10. 10.
    Reynoso Armenta, D.M.: Diagnosis of breast cancer through the processing of thermographic images and Neural Networks. Master thesis in Optics, Tonantzintla, Puebla (2017)Google Scholar
  11. 11.
    Luna, J.G.V., Gutierrez Delgado, F.: Feasibility of new-generation infrared screening for breast cancer in rural communities. US Obstetrics and Gynecology, Touch Briefings. 5, 52–56 (2010)Google Scholar
  12. 12.
    Hobbins, W.: In abnormal thermogram-significance in breast cancer. Interamer. J Rad. 12, 337 (1987)Google Scholar
  13. 13.
    Flir®.: Veterinary applications of thermography. Accessed 10 November 2017. [Online]. Available: http://www.flir.com/uploadedFiles/Thermography/MMC/Brochures/T820340/T820340_EN.pdf
  14. 14.
    MathWorks®.: Help « rgb2gray, » . Available: https://www.mathworks.com/help/matlab/ref/rgb2gray.html. Accessed 31 October 2017
  15. 15.
    MathWorks®.: Object Detection Using Deep Learning. Available: https://www.mathworks.com/help/vision/examples/object-detection-using-deep-learning.html?requestedDomain=www.mathworks.com. Accessed 16 Febrero 2018]

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Pilar Gomez-Gil
    • 1
    Email author
  • Daniela Reynoso-Armenta
    • 1
  • Jorge Castro-Ramos
    • 1
  • Juan Manuel Ramirez-Cortes
    • 1
  • Vicente Alarcon-Aquino
    • 2
  1. 1.National Institute of Astrophysics, Optics and ElectronicsTonantzintlaMexico
  2. 2.University of Americas PueblaSan Andrés CholulaMexico

Personalised recommendations