A Model-based Algorithm for Mass Segmentation in Mammograms

A novel mass segmentation algorithm is proposed in this paper. It establishes two mass models to represent the various masses, uses iterative thresholding to extract the suspicious area, and applies a DWT-based approach to locate the masses. And then, a region growing process restricted by Canny edge detection is carried out to extract the rough mass regions, and finally active contour model is used to segment the masses accurately. The clinical experiment has demonstrated that our algorithm has higher performance than conventional methods