DESCRIPTION LOGIC FOR AUTOMATIC CLASSIFICATION OF MAMMOGRAM REPORTS

In this paper, we present a system for automatic classification of mammography reports, based on a radiological OWL DL ontology. The later describes radiological signs and categories of the BI-RADS classification established by American College of Radiology (ACR) in the OWL DL language. Our system is designed firstly to formalize content of mammogram reports written in free text driving by the ACR Ontology, then to infer relevant classes and corresponding attitude by using subsumption classification. Classification in our work is based on description logic by using OWL DL ontology and description logical reasoning system.