FUZZY-LOGIC IN COMPUTER-AIDED BREAST-CANCER DIAGNOSIS - ANALYSIS OF LOBULATION

This paper illustrates how a fuzzy logic approach can be used to forma lize terms in the American College of Radiology (ACR) Breast Imaging L exicon. In current practice, radiologists make a relatively subjective determination for many terms from the lexicon related to breast cance r diagnosis. Lobulation and microlobulation of nodules are two importa nt features in the ACR lexicon. We offer an approach for formalizing t he distinction of these features and also formalize the description of intermediate cases between lobulated and microlobulated masses. In th is paper it is shown that fuzzy logic can be an effective tool in deal ing with this kind of problem. The proposed formalization creates a ba sis for the next three steps: (i) extended verification with blinded c omparison studies, (ii) the automatic extraction of the related primit ives from the image, and (iii) the detection of lobulated and microlob ulated masses based on these primitives. (C) 1997 Elsevier Science B.V .