Case-level detection of mammographic masses

Issue title: Proceedings of the twelfth International Symposium on Interdisciplinary Electromagnetic, Mechanic and Biomedical Problems, ISEM Bad Gastein

Article type: Research Article

Authors: Takács, Gábor^{a; *} | Pataki, Béla^a

Affiliations: [a] Department of Measurement and Information Systems, Budapest University of Technology and Economics, Magyar tudósok körútja 2., H-1117 Budapest, Hungary

Correspondence: [*] Corresponding author. Tel.: +36 1 463 2458; Fax: +36 1 463 4112; E-mail: [email protected]

Abstract: Breast cancer is one of the most frequent cancerous diseases among women. Currently mammography (X-ray examination) is the most efficient method for early detection. A CAD system for detecting cancer-predicting masses in digitalized mammograms is presented in this paper. Two size classes were defined and different algorithms were used for small and large mass detection. The last processing step was a false mark filtering, based on the comparison of the two views of the same breast. The system was tested with 935 mammographic cases, each containing 4 images.

Keywords: Mammography, mass detection, medical image processing, computer-aided diagnosis (CAD)

DOI: 10.3233/JAE-2007-839

Journal: International Journal of Applied Electromagnetics and Mechanics, vol. 25, no. 1-4, pp. 395-400, 2007