IDENTIFICATION OF CLUSTERED MICROCALCIFICATIONS ON DIGITIZED MAMMOGRAMS USING MORPHOLOGY AND TOPOGRAPHY-BASED COMPUTER-AIDED DETECTION SCHEMES - A PRELIMINARY EXPERIMENT

RATIONALE AND OBJECTIVES. A mathematical morphology-based computer-aid ed detection (CAD) scheme for the identification of clustered microcal cifications was developed and tested. The potential for improving eith er sensitivity or specificity by combining the results with those prev iously reported was investigated. METHODS. The CAD scheme presented he re is based on mathematical morphology and a series of simple rule-bas ed criteria for the identification of clustered microcalcifications. A database of 105 digitized mammograms was used for training and rule s etting of the scheme. A test set of 191 digitized mammograms was used to evaluate its performance. The same test set had been used to evalua te a multilayer, topography-based scheme. The results obtained by the two schemes were then combined using logical OR and AND operations. RE SULTS. The morphology-based and topography-based CAD schemes performed at sensitivities of 82.9% and 89.5%, with false-positive detection ra tes of 1.3 and 0.4 per image, respectively. A logical OR operation res ulted in 95.4% sensitivity, An AND operation achieved 76.2% sensitivit y, with no false identifications on 93% of images. CONCLUSIONS. By com bining the results of the morphology-based and the topography-based sc hemes, either sensitivity or specificity can he improved.