An automatic method for the identification and interpretation of clusteredmicrocalcifications in mammograms

We investigated a method for a fully automatic identification and interpret ation process Abstract. We investigated a method for a fully au for cluster ed microcalcifications in mammograms. Mammographic films of 100 patients containing microcalcifications with know n histology were digitized and preprocessed using standard techniques. Micr ocalcifications detected by an artificial neural network (ANN) were cluster ed and some cluster features served as the input of another ANN trained to differentiate between typical and atypical clusters, while others were fed into an ANN trained on typical clusters to evaluate these lesions. The measured sensitivity for the detection of grouped microcalcifications w as 0.98. For the task of differentiation between typical and atypical clust ers an Az value of 0.87 was computed, while for the diagnosis an Az value o f 0.87 with a sensitivity of 0.97 and a specificity of 0.47 was obtained. The results show that a fully automatic computer system was developed for t he identification and interpretation of clustered microcalcifications in ma mmograms with the ability to differentiate most benign lesions from maligna nt ones in an automatically selected subset of cases.