An Evaluation of Two Mammography Segmentation Techniques

Mammographic mass detection is an important task for early detection of breast cancer diagnosis and treatment. This is however still remains a challenging task. In this paper, we have proposed a multilevel thresholding algorithm for segmenting the tumor. This paper compares two most popular method, namely between class variance (Otsu) and entropy criterion (Kapur’s) methods for segmenting the tumor. Our algorithms are tested on 20 mammograms and showing promising results.