An automatic microcalcification detection system based on a hybrid neural network classifier A. Papadopoulos a,* , D.I. Fotiadis b , A. Likas b a Department of Medical Physics, Medical School, University of Ioannina, GR 45110 Ioannina, Greece b Department of Computer Science, University of Ioannina, GR 45110 Ioannina, Greece Received 29 August 2001; received in revised form 19 November 2001; accepted 17 January 2002 Abstract A hybrid intelligent system is presented for the identification of microcalcification clusters in digital mammograms. The proposed method is based on a three-step procedure: (a) preprocessing and segmentation, (b) regions of interest (ROI) specification, and (c) feature extraction and classification. The reduction of false positive cases is performed using an intelligent system containing two sub- systems: a rule-based and a neural network sub-system. In the first step of the classification schema 22 features are automatically computed which refer either to individual microcalcifications or to groups of them. Further reduction in the number of features is achieved through principal component analysis (PCA). The proposed methodology is tested using the Nijmegen and the Mammographic Image Analysis Society (MIAS) mammographic databases. Results are presented as the receiver operating characteristic (ROC) performance and are quantified by the area under the ROC curve (A z ). In particular, the A z value for the Nijmegen dataset is 0.91 and for the MIAS is 0.92. The detection specificity of the two sets is 1.80 and 1.15 false positive clusters per image, at the sensitivity level higher than 0.90, respectively. # 2002 Elsevier Science B.V. All rights reserved. Keywords: Microcalcification detection; Hybrid neural network; Computer-aided detection (CAD); Mammo- graphy 1. Introduction Breast cancer is currently one of the leading causes of death among women worldwide. Regular mammographic screening programs for women of certain age or high-risk groups are taking place in a number of countries on a nation-wide basis or as projects organized from several institutes [1,15,30,31,48]. Although some researchers doubt about the real Artificial Intelligence in Medicine 25 (2002) 149–167 * Corresponding author. Tel.: þ30-651-98803; fax: þ30-651-98889. E-mail address: fotiadis@cs.uoi.gr (A. Papadopoulos). 0933-3657/02/$ – see front matter # 2002 Elsevier Science B.V. All rights reserved. PII:S0933-3657(02)00013-1