CWLA: A Novel Cognitive Classifier for Breast Mass Diagnosis

A novel cognitive classifier has been introduced todevelop a trustable mammography Computer Aided Diagnosis(CADx) system which is called Cognitive Weighted LinearAggregation (CWLA). A group of in-depth analyzed features areextracted from the preprocessed Regions of Interest (ROIs) andmapped from set of real numbers to a set of linguistic terms. Theproposed classifier primes a knowledge base which is developedaccording to a mammography expert. The semantic comparisonof the extracted features with the expectations of the knowledgebase, which is called cognitive resonance, leads to a primaryclustering. Finally, the linguistic terms are remapped onto the setof real numbers and the final assessment comes out from theweighted linear aggregation of clustered categories. Since theoutput of the system comes with reason, the system is reliable.The achieved area under Receiver Operational Characteristics(ROC) curve (Az) and False Positive Rate (FPR) are 0.858 and5.26%, respectively.

Keywords:

cognitive pattern recognition , cognitive classifier , computer aided diagnosis system , mammography ,