Image Segmentation and Asymmetry Analysis of Breast Thermograms for Tumor Detection

Abstract

Breast Cancer is the most commonly diagnosed form of cancer in women. Infrared Thermography is a promising technology for breast cancer detection. But analysis of Breast thermograms has often been subjective and has resulted in inconsistency in the diagnosis of breast diseases by thermography. The fast growing tumor has a higher metabolic rate and associated increase in local vascularisation. It will cause the occurrence of some asymmetric heat patterns. Clinical interpretation of a breast thermogram is primarily based on the asymmetry analysis of these heat patterns visually and subjectively. In this paper, a new approach for automatic segmentation of Region of Interest and asymmetry analysis of breast thermograms is implemented. Canny edge detection operator and gradient operator are used to first segment the region of interest. Further asymmetry analysis is performed according to seven extracted features. The abnormality of a breast thermogram is clearly indicated by the features. A GUI is further created in Matlab to make the approach effectual, feasible and for Real Time analysis. 31 thermograms of normal and 11 thermograms of abnormal volunteers were taken.