Comparison of texture based algorithms for the detection of masses in digitised mammograms

Author

Pfisterer, Richard ; Aghdasi, Farzin

Author_Institution

Dept. of Electr. Eng., Univ. of the Witwatersrand, Johannesburg, South Africa

Volume

1

fYear

1999

fDate

1999

Firstpage

383

Abstract

A comparison of methods to detect masses in digitised mammograms based on textural information is investigated. Masses in mammograms are usually “smoother” with lower textural content than the surrounding tissue. Our algorithms enhance and segment the image based on texture. We implemented four algorithms: 1) hexagonal wavelets, 2) Laws texture energy masks 3) wavelet enhanced Laws, and 4) steerable Alters enhanced Laws. We tested each of these algorithms on a standard database, and varied parameters showing interesting properties in each one

Keywords

biological tissues; image enhancement; image segmentation; image texture; mammography; medical image processing; wavelet transforms; Laws texture energy masks; digitised mammograms; hexagonal wavelets; lower textural content; mass detection; standard database; steerable Alters enhanced Laws; surrounding tissue; textural information; texture based algorithms; wavelet enhanced Laws; Breast cancer; Cancer detection; Filters; Image databases; Image edge detection; Image segmentation; Lesions; Testing; X-ray detection; X-ray detectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Africon, 1999 IEEE

Conference_Location

Cape Town

Print_ISBN

0-7803-5546-6

Type

conf

DOI

10.1109/AFRCON.1999.820871

Filename

820871