A wavelet neural network for the detection of microcalcifications in multiscale enhanced digitised mammograms

Author

Aydin Alayhoglu, B. ; Aghdasi, Farzin

Author_Institution

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

Volume

1

fYear

1999

fDate

1999

Firstpage

389

Abstract

The detection of microcalcification clusters (MCCs) during mammographic examination is vital for the correct diagnosis of breast cancer in asymptomatic women. Automated detection methods augment the diagnostic process by providing the radiologist with a second opinion. Detection schemes making use of a neural network classifier, with input feature vectors containing spatial, spectral and multiscale image attributes, are investigated. A wavelet-based image enhancement technique is implemented to improve the detection performance

Keywords

cancer; image classification; image enhancement; mammography; medical image processing; neural nets; wavelet transforms; asymptomatic women; automated detection methods; breast cancer diagnosis; detection performance; input feature vectors; microcalcification clusters; microcalcification detection; multiscale enhanced digitised mammograms; multiscale image attributes; neural network classifier,; spatial image attributes; spectral image attributes; wavelet neural network; wavelet-based image enhancement technique; Attenuation; Breast cancer; Cancer detection; Image enhancement; Intelligent networks; Mammography; Neural networks; Radiography; Tumors; Wavelet transforms;

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.1999.820874

Filename

820874