Segmentation of mammograms into distinct morphological texture regions

Author

Baeg, S. ; Popov, A.T. ; Karnat, V.C. ; Batman, S. ; Sivakumar, K. ; Kehtarnavaz, N. ; Dougherty, E.R. ; Shah, R.B.

Author_Institution

CAMDI Lab., Texas A&M Univ., College Station, TX, USA

fYear

1998

fDate

12-14 Jun 1998

Firstpage

20

Lastpage

25

Abstract

Presents a comprehensive discussion on the segmentation of mammograms using morphological texture features. These features are derived from morphological granulometries with various structuring elements. Each structuring element captures a specific texture content. The segmentation is carried out in an unsupervised manner by applying the KL (Karhunen-Loeve) transform feature reduction and Voronoi clustering on the extracted morphological texture features. The evaluation of the segmentation outcome by a trained radiologist is provided

Keywords

computational geometry; diagnostic radiography; feature extraction; image segmentation; image texture; mathematical morphology; medical image processing; transforms; Karhunen-Loeve transform; Voronoi clustering; feature extraction; feature reduction; mammogram segmentation; morphological granulometry; morphological texture regions; radiologist evaluation; structuring elements; texture content capture; unsupervised image segmentation; Biomedical imaging; Breast cancer; Feature extraction; Gray-scale; Image segmentation; Karhunen-Loeve transforms; Laboratories; Mammography; Medical diagnostic imaging; Military computing;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer-Based Medical Systems, 1998. Proceedings. 11th IEEE Symposium on

Conference_Location

Lubbock, TX

ISSN

1063-7125

Print_ISBN

0-8186-8564-6

Type

conf

DOI

10.1109/CBMS.1998.701209

Filename

701209