"Fuzzy Logic in Digital Mammography: Analysis of Lobulation"
Proceedings of the FUZZ-IEEE '96 Inter'l Conference,
New Orleans, LA, September 8-11, Vol. 3, pp. 1726-1731, 1996.
by Kovalerchuk, B., E. Triantaphyllou, J.F. Ruiz, and J. Clayton
Abstract:
This paper illustrates how the fuzzy logic approach can be used to formalize the
American College of Radiology (ACR) breast imaging reporting lexicon.
In current practice radiologists make a relatively subjective determination for
many terms from the lexicon related to breast cancer diagnosis. Lobulation and
microlobulation of nodules are important features in breast cancer diagnosis based on
mammographic analysis by using the ACR lexicon. We offer an approach for formalizing the
distinction of these features and also formalize the description of the intermediate cases
between lobulated and microlobulated masses. In this paper it is shown that fuzzy logic
can be an effective tool in dealing with this kind of problems. The proposed formalization
creates a base for the next two steps: (i) the automatic extraction of the related primitives
from the image, and (ii) the detection of lobulated and microlobulated masses based on the primitives.
Topic Category: Decision analysis
Key Words:
Fuzzy logic, feature formalization, breast cancer, image recognition.
(size = 840 KB)
