A hybrid system for detecting masses in mammographic images

Author

Székely, Nora ; Tóth, Norbert ; Pataki, Béla

Author_Institution

Dept. of Meas. & Inf. Syst., Budapest Univ. of Technol. & Econ., Hungary

Volume

3

fYear

2004

fDate

18-20 May 2004

Firstpage

2065

Abstract

This paper discusses a hybrid system for detecting masses in mammographic images. The proposed approach analyses the mammograms in three major steps. First a global segmentation method is applied to find the regions of interest. This step uses texture features, decision trees and a multiresolution Markov random field model. The second stage works on the output of the previous algorithm. Here a combination of three different local segmentation methods is used, and then some relevant features are extracted. Some of them refer to the shape of the object, others are simple texture parameters. Based on these features the final decision is made.

Keywords

Markov processes; decision trees; feature extraction; image segmentation; image texture; mammography; medical image processing; principal component analysis; decision trees; feature extraction; global segmentation method; hybrid system; local segmentation methods; mammographic images; masses detection; multiresolution Markov random field model; regions of interest; texture features; Biomedical imaging; Biomedical measurements; Breast cancer; Cancer detection; Image analysis; Image segmentation; Information systems; Lesions; Mammography; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation and Measurement Technology Conference, 2004. IMTC 04. Proceedings of the 21st IEEE

ISSN

1091-5281

Print_ISBN

0-7803-8248-X

Type

conf

DOI

10.1109/IMTC.2004.1351496

Filename

1351496