Estimation of Breast Skin-Line Using Least Square Estimation and Watershed Segmentation

Breast cancer has become one of the most dangerous tumors for middle-aged and older women in China recently. Mammography is its most reliable detection method in the clinic, and computer-aided diagnosis (CAD) could assist the radiologists in reading the mammograms. In this paper, a new algorithm was proposed to estimate the skin-line of the breast automatically, which could be divided into four steps. It firstly used iterative thresholding to remove the backgrounds. And then, it applied the least square estimation (LSE) method to approach the horizontal frames, and proposed an elastic thread algorithm to remove them. Finally, it used the watershed algorithm to fine the breast boundary. With the experimental results, the advantages of this method over the conventional ones could be proved.