Automatic detection and segmentation of microcalcifications on digitized mammograms

We have studied the use of computer-based methods to the detection and segmentation of microcalcifications in digital mammograms. The computer detection system is based on the rhmaxima algorithm applied twice to two filtered images, where we have automated the parameters r and h. The segmentation is based on an algorithm derived from the watershed transform by using different markers for the background and microcalcifications. The potential application of such a computer-aided system to mammographic interpretation is demonstrated by its ability to detect microcalcifications in clinical mammograms.