Mass detection based on integrated region growing and level set method

In this paper, an automatically method for mass detection was introduced, which combines multiple layers concentric (MLC) and narrow band region-based active contour (NBAC) technique. We used an improved level set method to segment the mass for contour refinement, after the boundary of a mass is found, texture features from Gray Level Cooccurrence Matrix (GLCM) are extracted from the surrounding area of the boundary of the mass. The extracted texture features are used to reduce the false positive. Mammography images from DDSM were used in the experiments and the method was evaluated, it obtained 1.38 FPsI at the sensitivity 79.3%. The result shows the effectiveness of the proposed method.