A method for detection of malignant masses in digitized mammograms using a fuzzy segmentation algorithm

Author

Sameti, Mohammad ; Ward, Rabab K. ; Morgan-Parkes, Jacqueline ; Palcic, Branko

Author_Institution

Dept. of Cancer Imaging, British Columbia Cancer Res. Centre, Vancouver, BC, Canada

Volume

2

fYear

1997

fDate

30 Oct-2 Nov 1997

Firstpage

513

Abstract

An algorithm for detection of masses in digitized mammograms is developed. In the first step, the algorithm employs a segmentation method based on the idea of fuzzy sets to divide a mammogram into different regions and produces some mass candidates. In the second step, some discrete texture features are calculated for the area of each mass candidate. Two of those feature were sufficient to produce a 94% true-positive detection rate with a low 0.24 false-positives per image for a data set of 35 mammograms with a malignant mass in each

Keywords

cancer; fuzzy set theory; image segmentation; image texture; mammography; medical image processing; CAD algorithm; computer-aided diagnosis; digitized mammograms; discrete texture features; fuzzy segmentation algorithm; malignant masses detection algorithm; mass candidate; medical diagnostic imaging; true-positive detection rate; Breast cancer; Cancer detection; Councils; Fuzzy sets; Image segmentation; Image texture analysis; Iterative algorithms; Lesions; Mammography; Pixel;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 1997. Proceedings of the 19th Annual International Conference of the IEEE

Conference_Location

Chicago, IL

ISSN

1094-687X

Print_ISBN

0-7803-4262-3

Type

conf

DOI

10.1109/IEMBS.1997.757658

Filename

757658