Automatic segmentation of thermal images to support breast cancer diagnosis

  • Steve Rodríguez Guerrero Universidad del Valle, Cali
  • Humberto Loaiza Universidad del Valle, Cali
  • Andrés David Restrepo Girón Universidad del Valle, Cali
Keywords: Infrared thermography, image segmentation, geometric analysis, breast cancer


A proposal for segmenting thermographic images that can be used as a pre-processing step in the asymmetric analysis of breast cancer. This proposed segmentation of detecting areas of high temperature gradients, from which geometric regions of interest [Region of Interest, ROI] are defined. Hot spots selected as a reference at the start of the identification of the ROI corresponded to those presented under each breast, then, using a contour following on both sides of the body, it was sought to define the coordinates of the vertices that shaped the region of interest. The results show an average success of 67.5% in the segmentation of the breast region from 40 thermograms, which were captured in patients with raised arms or hands on hips while capturing images at a distance of 1 m camera.


Download data is not yet available.

Author Biographies

Steve Rodríguez Guerrero, Universidad del Valle, Cali

Estudiante de la Maestría en Ingeniería con énfasis en Electrónica de la Universidad del Valle e Ingeniero Electrónico de la Universidad Santiago de Cali (2008). Docente de la Fundación Universitaria Católica, vinculado a los grupos de investigación en Telemedicina e Ingeniería Biomédica [Telebio] de la Universidad Santiago de Cali, y Percepción y Sistemas Inteligentes [PSI] de la Universidad del Valle. Sus áreas de interés son: telesalud, telemedicina, procesamiento de imágenes biomédicas y visión artificial.

Humberto Loaiza, Universidad del Valle, Cali
Ingeniero electricista (1990) y Magister en Automática (1995) de la Universidad del Valle; Doctor en Robótica por la Universite D'evry Val D'essonne (Francia, 1999). Es profesor titular y Director de la Escuela de Ingeniería Eléctrica y Electrónica de la Universidad del Valle, donde además es Co-Director del grupo de investigación en Percepción y Sistemas Inteligentes [PSI]). Sus áreas de interés son: procesamiento de señales e imágenes, visión artificial, robótica, inteligencia computacional, instrumentación inteligente y reconocimiento de patrones.

Andrés David Restrepo Girón, Universidad del Valle, Cali

Ingeniero Electrónico (1999), Magíster en Automática (2005) y Doctor en Ingeniería (2014) de la Universidad del Valle (Cali-Colombia), asociado al grupo de investigación en Percepción y Sistemas Inteligentes [PSI]. Profesor de tiempo completo del Programa de Ingeniería Electrónica de la Universidad del Valle. Sus áreas de interés son la instrumentación electrónica, los sistemas digitales microcontrolados y el procesamiento de señales e imágenes.


Bao-ping, Ch. & Zeng-qiang, MA. (2008). Automated image segmentation and asymmetry analysis for breast using infrared images. Structural health monitoring and control. En International Workshop on Education Technology and Training 2008. Los Alamitos, CA: IEEE Computer Society

Danaei G et al. (2005). Causes of cancer in the world: comparative risk assessment of nine behavioural and environmental risk factors. Lancet, 366, 1784–93.

Ferlay. J., Soerjomataram, I., Ervik, M., Dikshit, R., Eser, S., Mathers, C., Rebelo, M., Parkin, DM., Forman, D., Bray, F. (2013). Cancer incidence and mortality worldwide [IARC Cancer base, No. 11]. Lyon, France: IARC

Hairong Qi, & Head, JF. (2001). Asymmetry analysis using automatic segmentation and classification for breast cancer detection in thermograms, in Proceedings of the 23rd Annual International Conference of the IEEE [Vol.3]. doi: 10.1109/IEMBS.2001.1017386. (pp. 2866-2869). Piscataway, NJ: IEEE

Hairong Qi., Snyder, WE., Head, JF, Elliott, RL. (2000). Detecting breast cancer from infrared images by asymmetry analysis. In Proceedings of the 22nd Annual EMBS International Conference, Chicago IL, 2000 (pp. 1227-1228). Piscataway, NJ: IEEE.

Head, J., Wang, F., Lipari, C., & Elliot, R. (2000). The important role of infrared imaging in breast cancer. IEEE Engineering in Medicine & Biology Society Journal, 19(3), 52-57

Herry, C. & Frize, M. (2004). Quantitative assessment of pain-related thermal dysfunction through clinical digital infrared thermal imaging. BioMedical Engineering Online, 3(19), doi:10.1186/1475-925X-3-19

IARC (2002). Breast cancer screening, IARC handbooks for cancer prevention, volume 7, Lyon, International Agency for Research on Cancer, IARC

Kapoor, P, Prasad, S., Patni, S. (2012). Image segmentation and asymmetry analysis of breast thermograms for tumor detection. International Journal of Computer Applications, 50 (9), 40-45

Kapoor, P. & Prasad. S. (2010). Image processing for early diagnosis of breast cancer using infrared images. Computer and Automation Engineering (ICCAE), 2010 The 2nd International Conference on [Volume:3], (pp.564-566). Piscataway, NJ: IEEE

Lipari, C., Head, J., Wang, F., and Elliot, R. (1997). Image analysis of digitized infrared images of the breasts from a first generation infrared imaging system. In Engineering in Medicine and Biology Society, 1997. In Proceedings of the 19th Annual International Conference of the IEEE, (pp. 681–684). Piscataway, NJ: IEEE

Mencattini, A., Salmeri, M., & Casti, P. (2011). Bilateral asymmetry identification for the early detection of breast cancer. In 2011 IEEE International Symposium on Medical Measurements and Applications (MeMeA 2011) Proceedings (pp.613-618). Piscataway, NJ: IEEE

Moghbel, M., Mahmud, HR., Mashohor, S., Iqbal-Bin-Saripan, M. (2012). Random walkers based segmentation method for breast thermography. Biomedical Engineering and Sciences (IECBES), 2012 IEEE EMBS Conference on (pp.627-630). Piscataway, NJ: IEEE

Scales, N., Herry, C., & Frize, M. (2004). Automated image segmentation for breast analysis using infrared images. IEEE Engineering in Medicine & Biology Society Journal, 3, 1737-1740

Thermology (2014). Teletherm TIGER-4 Infrared Thermal Imagers [online]. Retrieved from
Original Research