A new method for the detection of microcalcifications in mammograms

The presence of microcalcifications clusters, which appear as small bright spots in mammographic images, can be considered as a very important sign for breast cancer diagnosis. They can, however, be hard to detect due to their size and low contrast from surrounding normal tissue. In this paper, a new fuzzy-based method is presented to provide an appropriate segmentation of microcalcifications. This approach consists of five major steps. In these steps, the selection of appropriate parameters for the required operations is performed based on the specific image characteristics. The experimental results show that this method can detect microcalcifications in a fast manner and give attractive performances compared to some other approaches.