Topological Modeling and Classification of Mammographic Microcalcification Clusters

Topological Modeling and Classification of
Mammographic Microcalcification Clusters

Abstract— Topological Modeling and Classification of Mammographic Microcalcification Clusters. Goal:The presence of microcalcification clusters is a primary sign of breast cancer; however, it is difficult and time consuming for radiologists to classify microcalcifications as malig-nant or benign. In this paper, a novel method for the classification of microcalcification clusters in mammograms is proposed. Meth-ods: The topology/connectivity of individual microcalcifications is analyzed within a cluster using multiscale morphology. This is dis-tinct from existing approaches that tend to concentrate on the morphology of individual microcalcifications and/or global < Final Year Projects 2016 > cluster features. A set of microcalcification graphs are gen-erated to represent the topological structure of microcalcification clusters at different scales. Subsequently, graph theoretical fea-tures are extracted, which constitute the topological feature space for modeling and classifying microcalcification clusters. k -nearest-neighbors-based classifiers are employed for classifying microcal-cification clusters.