A multidisciplinary approach to the design and development of a CAD system for the detection of clustered microcalcifications

Mammography is a noninvasive diagnostic technique widely used for early cancer detection in women breast. The automatic detection and classification of some abnormalities in mammograms is of challenging scientific and technical interest because of the associated research topics and the potential clinical applications. Therefore, the design of a medical CAD (Computer-Aided Diagnosis or Detection) system for the analysis of mammographies involves a team composed by both medical and technical experts. In this paper we show the interaction that occurs between computer scientists and radiologists in the development and evaluation of a CAD system for the detection of clusters of micro-calcifications.