Detection of the Breast Cancer from Thermal Infrared Images

Abstract

Thermography can be used as part of an early detection tool which gives women of all ages the opportunity to increase their chances of detecting breast diseases at a very early stage. Breast thermography is a noninvasive prognostic procedure which can predict a tumor growth rate in breast cancer patients. The objective of this research is to acquire the potential of the statistical characteristics of the breast thermogram images for the detection of the breast cancer. For this research we use thermal data images from Sardjito hospital at Yogyakarta, from normal and abnormal breast (detected breast cancer). Firstly, download the breast image thermograms from the InsideIR software of Fluke Ti20 and save them as the inputs to our image processing program. Then adjust the format of the images, convert to grayscale images, and crop them to separate the suspected objects from the background. Finally we tabulated the statistical characteristics of the objects which are the means, standard deviations, and entropy to reveal the abnormalities of breast thermograms. The results show that the method are promising to detect the abnormality on the breast thermogram images. The normal breast thermograms have minimum entropies which differ from those abnormal thermograms in the early stage of breast cancer and thesignificantly from the more advanced of breast cancer.