Thermography based breast cancer analysis using statistical features and fuzzy classification

Gerald Schaefer^a, Michal Závisek^b, Tomoharu Nakashima^c
a School fo Engineering and Applied Science, Aston University, UK
^bFaculty of Electrical Engineering and Communication, Brno University of Technology, Czech Republic
^cDepartment of Computer Science and Intelligent Systems, Osaka Prefecture University, Japan

 ABSTRACT

Medical thermography has proved to be useful in various medical applications including the detection of breast cancer where it is able to identify the local temperature increase caused by the high metabolic activity of cancer cells.  It has been shown to be particularly well suited for picking up tumours in their early stages or tumours in dense tissue and outperforms other modalities such as mammography for these cases.  In this paper we perform breast cancer analysis based on themography, using a series of statistical features extracted from the thermograms quantifying the bilateral differences between left and right breast areas, coupled with a fuzzy rule-based classification system for diagnosis.  Experimental results on a large dataset of nearly 150 cases confirm the efficacy of our approach that provides a classification accuracy of about 80%.