Segmentation of breast tumors in mammograms by fuzzy region growing

Segmentation of tumor regions in mammograms is not easy due to the low contrast and the fuzzy nature of the boundaries of malignant tumors. General image segmentation procedures do not consider the uncertainty present around the boundaries of a tumor region. In this paper we present a segmentation method based on fuzzy region growing. The procedure starts with a seed pixel, and uses a fuzzy membership function based upon statistical measures of the region being grown. Results of testing with several mammograms indicate that the method can provide boundaries of tumors close to those drawn by an expert radiologist. The regions obtained preserve the transition information present around tumor boundaries. Statistical measures computed from the resulting regions have shown the potential to classify masses and tumors as benign or malignant