Color segmentation of breast thermograms can have a crucial performance in tumor detection. There is a relation between blood vessel activity and the surrounding area temperature. Once a cancer increases blood vessel activity, the cancer cells and their surrounding tissue become hotter than normal tissue. Pre-cancer and cancer cells need plenty of nutrients to multiply and survive consequently ; they are highly metabolic tissue and have different thermal patterns compared to the normal one. In this paper, a comparison work is presented for three modeled color segmentation approaches: K-means, mean shift (MS), and fuzzy c-means (FCM) applied to infrared breast images. There are some drawbacks for K-means and MS approaches. Almost empty clusters may be obtained in the seg-mentation results using K-means algorithm. In addition, we frequently confront almost empty clusters with MS algorithm due to its sensitiveness to the window size parameter. Choosing an appropriate window size parameter is not an easy task. On the other hand, the fuzzy inherent breast thermal images aid the FCM technique to obtain more precise outcomes. Malignant tumors show hotter thermal patterns than healthy tissues and even with benign tissues. Segmenting different parts of two breasts in terms of their temperature has potential helping to identify abnormal breast tissues.
CITATION STYLE
Etehadtavakol, M., & Ng, E. Y. K. (2017). Color Segmentation of Breast Thermograms: A Comparative Study (pp. 69–77). https://doi.org/10.1007/978-981-10-3147-2_6
Mendeley helps you to discover research relevant for your work.