Automatic mass segmentation method in mammograms based on improved VFC snake model - Emerging Trends in Image Processing, Computer Vision, and Pattern Recognition - page 166

FIGURE 3 Edge extraction and mass location results (1024 × 1024 pixels).
2.3.3 Mass location parameter
For a further work, we obtain the mass position coordinate by defining a circle, whose center
corresponds to the center of extracted mass egde, and the radius of which is a middle value of
the distance from boundary pixel to the center position, indicating as: ( cx , cy ) and r . For Figure
3 , the parameter is: (682, 586), r = 46. The parametric circle could be used as the initial contour
of deformable model followed by.
2.4 Mass Segmentation
The results of mass location are rough and exist certain gap with the actual boundary, we util-
ize the Snake model to perform an accurate segmentation further.
2.4.1 Typical VFC Snake model
The Snake model defined a parametric curve guided by external forces and internal forces that
pull it toward the edge of ROI until the energy function achieves the minimum. The curve v ( s )
and the minimizing energy function E ( v ) forms are
(8)
(9)