Case-adaptive decision rule for detection of clustered microcalcifications in mammograms

Microcalcification (MC) detection in mammograms can be hampered by a number of factors ranging from imaging noise to inhomogeneity in breast tissue. Consequently, owning to the variability among subjects in their mammograms, the detection accuracy often varies from case to case even for a well-developed MC detector. To account for this variability, we propose to use a Bayes´ risk approach to define the decision rule in the detector output, for which the probability model of the false-positives (FPs) is determined directly from the image under consideration. In the experiment, we demonstrated the proposed approach on a set of 408 mammograms. The results show that it could reduce the FP rate by as much as 44.16% with true-positive rate at 85%.