A comparison of two methods for the segmentation of masses in the digital mammograms.

An accurate and standardized technique for breast tumor segmentation is a critical step for monitoring and quantifying breast cancer. The fully automated tumor segmentation in mammograms presents many challenges related to characteristics of an image. In this paper, a comparison of two different semi-automated methods, viz., level set and marker controlled watershed methods that perform an accurate and fast segmentation of tumor is made. The robustness of the proposed methods is demonstrated by the segmentation of a set of 17 mammogram images. Numerical validation of the results is also provided. Copyright (c) 2009 Elsevier Ltd. All rights reserved.