Breast diseases detection and pseudo-coloring presentation for gray infrared breast images

Abstract

Breast cancer is the most common cancer in women (about 30% of all cancers); and is also the second common cancer after lung cancer. One woman out of eight develops breast cancer during lifetime. Breast thermography has a unique role in early detection of breast cancer and in this regards none of the other method such as mammography, ultrasound, CT scan and MRI could countervail it. The role of infrared imaging in early detection of breast cancer as an adjunct tool to mammography has been proved. Thermograms are usually provided in gray level images but findings show that gray images are not appropriate for human interpretation. Human beings can only discern a few dozen gray level values while they can distinguish thousands of colors. So in order to help thermologists to find abnormal regions in the thermograms, it's better to color thermograms. So pseudo-coloring of thermograms is one of the important factors for accurate diagnosis. In this research we offer comparing some common pseudo-coloring algorithms. Also a nonlinear function transform for pseudo-coloring of infrared breast images based on physiological properties of human eye is proposed, and its efficiency is shown by experience.