Mammographic image segmentation using edge based deformable contour models
Xianghua Xie · 2009
Deformable contour models, also known as snakes, are commonly used in image processing and computer vision due to their natural handling of shape variation and independence of operation (once initialized), which make them highly appropriate to segment mass lesions in digital (or digitized) mammographic images. The extracted shape and texture information through contour based segmentation are useful in determining benignancy or malignancy. In this paper, we present a preliminary sudy on comparative analysis of four edge based active contour models in segmenting mass lesions in mammogram images. Two of them are widely used, classic active contour models and the other two are most recent advances in active contouring. Experiments are carried out to compare their accuracy, as well as the ability in handling weak edges and difficult initializations.