A hybrid watershed method for cell image segmentation

Author

Ao, Jingqi ; Mitra, Sunanda ; Long, Rodney ; Nutter, Brian ; Antani, Sameer

Author_Institution

Texas Tech Univ., Lubbock, TX, USA

fYear

2012

fDate

22-24 April 2012

Firstpage

29

Lastpage

32

Abstract

In cytological evaluation of cells, the nuclear characteristics present significant opportunities for early detection of abnormalities arising from various types of cancer. Accurate representation of cell nuclear structure by traditional manual inspection is difficult and time-consuming. In this paper, we introduce a new semi-automated cell segmentation algorithm combining a histogram-based global approach with local watershed segmentation. The procedure requires very little prior knowledge or user interaction. Preliminary results of accurate segmentation of the nucleus from the cell are presented to demonstrate potential application of this algorithm in cytological evaluation of abnormal nuclear structure.

Keywords

cancer; cellular biophysics; image segmentation; medical image processing; abnormal nuclear structure; cancer; cell cytological evaluation; cell nuclear structure representation; early abnormality detection; histogram-based global approach; hybrid watershed method; local watershed segmentation; nuclear characteristics; semi-automated cell image segmentation algorithm; Biomedical imaging; Clustering algorithms; Cost function; Histograms; Image color analysis; Image segmentation; Manuals; cell segmentation; cytopathology; global histogram; local watershed;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Analysis and Interpretation (SSIAI), 2012 IEEE Southwest Symposium on

Conference_Location

Santa Fe, NM

Print_ISBN

978-1-4673-1831-0

Electronic_ISBN

978-1-4673-1829-7

Type

conf

DOI

10.1109/SSIAI.2012.6202445

Filename

6202445