Journal of Medical Systems

, Volume 36, Issue 1, pp 103–111 | Cite as

Automated Detection of Breast Cancer in Thermal Infrared Images, Based on Independent Component Analysis

  • Luciano BoqueteEmail author
  • Sergio Ortega
  • Juan Manuel Miguel-Jiménez
  • José Manuel Rodríguez-Ascariz
  • Román Blanco
Original Paper


Breast cancer, among women, is the second-most common cancer and the leading cause of cancer death. It has become a major health issue in the world over the past decades and its incidence has increased in recent years mostly due to increased awareness of the importance of screening and population ageing. Early detection is crucial in the effective treatment of breast cancer. Current mammogram screening may turn up many tiny abnormalities that are either not cancerous or are slow-growing cancers that would never progress to the point of killing a woman and might never even become known to her. Ideally a better screening method should find a way of distinguishing the dangerous, aggressive tumors that need to be excised from the more languorous ones that do not. This paper therefore proposes a new method of thermographic image analysis for automated detection of high tumor risk areas, based on independent component analysis (ICA) and on post-processing of the images resulting from this algorithm. Tests carried out on a database enable tumor areas of 4 × 4 pixels on an original thermographic image to be detected. The proposed method has shown that the appearance of a heat anomaly indicating a potentially cancerous zone is reflected as an independent source by ICA analysis of the YCrCb components; the set of available images in our small series is giving us a sensitivity of 100% and a specificity of 94.7%.


Breast cancer Thermography ICA Image processing 


  1. 1.
    Ferlay, J., Bray, F., Pisani, P., and Parkin, D. M., Globocan 2002: Cancer incidence, mortality and prevalence worldwide, IARC CancerBase no.5, ver. 2.0. Lyon: IARC, 2004.Google Scholar
  2. 2.
    Boyd, B. A., and Fine, R. E., Stereotactic breast biopsy: the nurse’s role. J. Radiol. Nurs. 26:4–10, 2007. doi: 10.1016/j.jradnu.2006.11.001.CrossRefGoogle Scholar
  3. 3.
    Gautherine, M., Thermopathology of breast cancer: measurement and analysis of in vivo temperature and blood flow. Ann. NY Acad. Sci. 1980:383–415, 1999.Google Scholar
  4. 4.
    Tan, T. Z., Quek, C., Ng, G. S., and Ng, E. Y. K., A novel cognitive interpretation of breast cancer thermography with complementary learning fuzzy neural memory structure. Expert. Systems Appl. 33:652–666, 2007.CrossRefGoogle Scholar
  5. 5.
    Zou, Y., and Guo, Z., A review of electrical impedance techniques for breast cancer detection. Med. Eng. Phys. 25:79–90, 2003.CrossRefGoogle Scholar
  6. 6.
    Mandelblatt, J. S., et al., Effects of mammography screening under different screening schedules: model estimates of potential benefits and harms. Ann. Intern. Med. 151:738–747, 2009.Google Scholar
  7. 7.
    Ng, E. Y. K., A review of thermography as promising non-invasive detection modality for breast tumor. Int. J. Therm. Sci. 48:849–859, 2009. doi: 10.1016/j.ijthermalsci.2008.06.015.CrossRefGoogle Scholar
  8. 8.
    Zhixiong, G., and Kan-Wan, S., Simulated parametric studies in optical imaging of tumors through temporal log-slope difference mapping. Med. Eng. Phys. 29:1142–1148, 2007.CrossRefGoogle Scholar
  9. 9.
    Tan, J. M. Y., Ng, E. Y. K., Acharya, R., Keith, L. G., and Holmes, J., Comparative study on the use of analytical software to identify the different stages of breast cancer using discrete temperature data. J. Med. Syst. 33:141–153, 2009. doi: 10.1007/s10916-008-9174-4.CrossRefGoogle Scholar
  10. 10.
    Orel, V. E., Romanov, A. V., Dzyatkovskaya, N. N., and Mel’nik, Y. I., The device and algorithm for estimation of the mechanoemisson chaos in blood of patients with gastric cancer. Med. Eng. Phys. 24:365–371, 2002.CrossRefGoogle Scholar
  11. 11.
    Yahara, T., Koga, T., Yoshida, S., Nakagawa, S., Deguchi, H., and Shirouzu, K., Relationship between microvessel density and thermographic hot areas in breast cancer. Surg. Today. 33:243–248, 2003. doi: 10.1007/s005950300055.CrossRefGoogle Scholar
  12. 12.
    Carmeliet, P., and Jain, R. K., Angiogenesis in cancer and other diseases. Nature. 407:249–57, 2000.CrossRefGoogle Scholar
  13. 13.
    Lloyd-Williams, K., and Handley, R. S., Infrared thermometry in the diagnosis of breast disease. Lancet. 2:1378–1381, 1961.CrossRefGoogle Scholar
  14. 14.
    Parisky, Y. R., Sardi, A., Hamm, R., Hughes, K., Esserman, L., Rust, S., and Callahan, K., Efficacy of computerized infrared imaging analysis to evaluate mammographically suspicious lesions. AJR. 180:263–269, 2003.Google Scholar
  15. 15.
    Arora, N., Martins, D., Ruggerio, D., Tousimis, E., Swistel, A. J., Osborne, M. P., and Simmons, R. M., Effectiveness of a noninvasive digital infrared thermal imaging system in the detection of breast cancer. Am. J. Surg. 196:523–526, 2008.CrossRefGoogle Scholar
  16. 16.
    Kennedy, D. A., A comparative review of thermography as a breast cancer screening technique. Integr. Cancer Ther. 8:9–16, 2009. doi: 10.1177/1534735408326171.CrossRefGoogle Scholar
  17. 17.
    Qi, H., Kurungati, P. T., and Liu, Z., Early detection of breast cancer using thermal texture maps. Biomedical imaging 2002. Proceedings. 2002 IEEE International Symposium on. doi: 10.1109/ISBI.2002.1029255.
  18. 18.
    Tang, X., and Ding H., Asymmetry analysis of breast thermograms with morphological image segmentation. Eng in Med and Bio Soc 2005, 27th Annual conference, IEEE-EMBS 2005, 10.1109/IEMBS.2005.1616766Google Scholar
  19. 19.
    Qi, H., and Head, J. F., Asymmetry analysis using automatic segmentation and classification for breast cancer detection in thermograms. 23rd IEEE International Conference on Eng in Med and Bio 2001.Google Scholar
  20. 20.
    Tang, X., Ding, H., Yuan, Y., and Wang, Q., Morphological measurement of localized temperature increase amplitudes in breast infrared thermograms and its clinical application. Biomed. Signal Process. Contr. 3:312–318, 2008.CrossRefGoogle Scholar
  21. 21.
    Ng, E. Y. K., and Kee, E. C., Integrative computer-aided diagnostic with breast thermogram. J.F Mechanics in Medicine and Biology 7:1–10, 2007. doi: 10.1142/so219519407002091.Google Scholar
  22. 22.
    Koay, J., Herry, C., and Frize, M., Analysis of breast thermography with an artificial neural network. Proceedings of the 26th Annual International Conference of the IEEE EMBS, San Francisco, CA, USA September 2004;1–5.Google Scholar
  23. 23.
    EtehadTavakol, M., Sadri, S., and Ng, E. Y. K., Application of k- and fuzzy c-means for color segmentation of thermal infrared breast images. J. Med. Syst., 2008. doi: 10.1007/s10916-008-9213-1.Google Scholar
  24. 24.
    Schaefer, G., Nakashima, T., Zaivisek, M., Yokota, Y., Drastich, A., and Ishibuchi, H., Breast cancer classification using statistical features and fuzzy classification of thermograms. Fuzzy Systems Conference 2007, FUZZ-IEEE 2007, IEEE International, doi: 10.1109/FUZZY.2007.4295520.
  25. 25.
    Schaefer, G., Závišek, M., and Nakashima, T., Thermography based breast cancer analysis using statistical features and fuzzy classification. Pattern Recogn. 42:1133–1137, 2009. doi: 10.1016/j.patcog.2008.08.007.CrossRefGoogle Scholar
  26. 26.
    Zhao, Q., Zhang, J., Wang, R., and Cong, W., Use of a thermocouple for malignant tumor detection. IEEE Eng. Med. Biol. Mag. 27:164–66, 2008.CrossRefGoogle Scholar
  27. 27.
    Jakubowska, T., Wiecek, B., Wysocki, M., and Drews-Peszynski, C., Thermal signatures for breast cancer screening comparative study. In Proceedings of the 25th Annual International Conference of the IEEE EMBS Conference, Cancun. 2:1117–1120, 2003.Google Scholar
  28. 28.
    Ng, E. Y. K., and Fok, S. C., A framework for early discovery of breast tumor using thermography with artificial neural network. Breast J. 9:4341–343, 2003. doi: 10.1046/j.1524-4741.2003.09425.x.CrossRefGoogle Scholar
  29. 29. (last accessed Nov 2009).
  30. 30.
    Bronzino, J. D. (Ed.), Medical Devices and Systems (Biomedical Engineering Handbook), Ed. J. D. Bronzino, Publ. Taylor & Francis, pp. 25.1–25.20, 2006.Google Scholar
  31. 31.
    Abu-Amara, F., and Abdel-Qader, I., Detection of breast cancer using independent component analysis. Electro/Information Technology, 2007 IEEE International Conference on, pp. 428–431. doi: 10.1109/EIT.2007.4374509.
  32. 32.
    Gallardo-Caballero, R., García-Orellana, C. J., Macías-Macías, M., González-Velasco, H. M., and López-Aligué, F. J., Independent component analysis applied to breast cancer detection on digitized mammograms. Int. Congr. Ser. 1281:1052–1057, 2005. doi: 10.1016/j.ics.2005.03.072.CrossRefGoogle Scholar
  33. 33.
    Amari, S., Chen, T., and Cichocki, A., Non-holonomic constraints in learning blind source separation. Kasabov, N. (Eds.), Progress in Connectionist-Based Information Systems, ICONIP-97, Vol. I. New Zealand: Springer, pp. 633–636, 1997.Google Scholar
  34. 34.
    Otsu, N., A threshold selection method from gray level histograms. IEEE Trans. Syst. Man Cybern. 9:62–66, 1979.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  • Luciano Boquete
    • 1
    Email author
  • Sergio Ortega
    • 1
  • Juan Manuel Miguel-Jiménez
    • 1
  • José Manuel Rodríguez-Ascariz
    • 1
  • Román Blanco
    • 2
  1. 1.Electronics Department, Biomedical Engineering GroupUniversity of AlcaláAlcalá de HenaresSpain
  2. 2.Surgery DepartmentUniversity of AlcaláAlcalá de HenaresSpain

Personalised recommendations