Automated Detection of Breast Cancer in Thermal Infrared Images, Based on Independent Component Analysis
- 755 Downloads
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%.
KeywordsBreast cancer Thermography ICA Image processing
- 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
- 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
- 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
- 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
- 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.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.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
- 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
- 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.
- 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
- 29.http://aathermography.com (last accessed Nov 2009).
- 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.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.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.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