Image segmentation of uterine cervix images for indexing in PACS

Author

Gordon, Shiri ; Zimmerman, Gali ; Greenspan, Hayit

Author_Institution

Dept. of Biomedical Eng., Tel Aviv Univ., Israel

fYear

2004

fDate

24-25 June 2004

Firstpage

298

Abstract

The National Cancer Institute has collected a large database of digitized 35 mm slides of the uterine cervix, the idea being to build a system enabling to study the evolution of lesions related to cervical cancer. In taking the first few steps towards this goal, the objective of this work is to develop and evaluate methodologies required for visual-based (i.e. content-based) indexing and retrieval that substantially improve information management of such a database. In this paper we model the properties of three tissue types using color and texture features, and use these models for image segmentation. Statistical modeling and segmentation tools are used for the task.

Keywords

PACS; biological tissues; cancer; content-based retrieval; database indexing; feature extraction; gynaecology; image retrieval; image segmentation; image texture; medical image processing; very large databases; 35 mm; PACS; color feature; content-based retrieval; image segmentation; indexing; information management; large database; lesions; statistical modeling; texture feature; tissue types; uterine cervix images; visual-based indexing; Cervical cancer; Content based retrieval; Image databases; Image segmentation; Indexing; Information management; Information retrieval; Lesions; Picture archiving and communication systems; Visual databases;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer-Based Medical Systems, 2004. CBMS 2004. Proceedings. 17th IEEE Symposium on

ISSN

1063-7125

Print_ISBN

0-7695-2104-5

Type

conf

DOI

10.1109/CBMS.2004.1311731

Filename

1311731