Texture similarity analysis of breast abnormalities in infrared thermal image

Abstract

The number of breast cancer has been increasing over the decade. Multiple screening tools have been used to detect the cancer, such as mammogram, ultrasound, MRI, CT-scan, PET scan and thermography. Mammogram is the gold standard method for breast cancer screening. However, thermography screening method has caught the attention to be used as alternative screening tools due to its non-contact procedure as well as available for patients below 40 years old. In this study, thermography image will be used as the input image. The proposed method starts with manual segmentation of the region of interest followed by extracting three separate texture features which are Chi-squared histogram distance, Earth Mover histogram distance and contrast computation. Each feature is then tested in terms of its statistical significance.