Computerized breast thermography: study of image segmentation and temperature cyclic variations

Abstract

Breast cancer is a common and dreadful disease in women. The surface temperature and the vascularization pattern of the breast could indicate breast diseases. Establishing the surface isotherm pattern of the breast and the normal range of cyclic variations of temperature distribution can assist in identifying the abnormal infrared images of diseased breasts. This paper investigates the cyclic variation of temperature and vascularization of the normal breast thermograms under a controlled environment. More than 50 Asian women were examined and some of them have been examined continuously for two month. All together, not less than 800 thermograms were obtained. Before these thermograms can be analysed objectively via a computer algorithm, they must be digitized and segmented. The authors present a method to segment thermograms and extract the useful region from the background. After the image processing, these thermograms can be analysed and then the best time to perform an examination can be chosen. All these results are important for establishing a data bank of normal breast thermography, to choose the best time for an examination and as a systematic methodology for evaluating and analysing the abnormal breast thermography in the future.