A K-Means Segmentation Method for Finding 2-D Object Areas Based on 3-D Image Stacks Obtained by Confocal Microscopy

Author

Niemisto, A. ; Korpelainen, T. ; Saleem, R. ; Yli-Harja, O. ; Aitchison, J. ; Shmulevich, I.

Author_Institution

Inst. for Syst. Biol., Seattle

fYear

2007

fDate

22-26 Aug. 2007

Firstpage

5559

Lastpage

5562

Abstract

A segmentation method for three-dimensional image stacks obtained by confocal microscopy is proposed. The method can be used to find two-dimensional object areas based on an image stack. The segmentation method is based on K- means clustering, global thresholding, and mathematical morphology. As a case study, the proposed method is applied to 244 image stacks of the yeast Saccharomyces cerevisiae. Quantitative comparisons with manually obtained results as well as with results obtained by a two-dimensional segmentation method are used to illustrate how the additional information provided by three-dimensional image stacks can improve segmentation results.

Keywords

biological techniques; cellular biophysics; image segmentation; optical microscopy; K-means clustering; K-means segmentation method; confocal microscopy; global thresholding; mathematical morphology; three-dimensional image stacks; two-dimensional object areas; yeast; Biomedical signal processing; Fungi; Image analysis; Image segmentation; Microscopy; Morphology; Pixel; Sugar; Systems biology; USA Councils; Image analysis; K-means clustering; confocal microscope; image stack; mathematical morphology; segmentation; three-dimensional; thresholding; yeast; Algorithms; Anatomy, Cross-Sectional; Artificial Intelligence; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Microscopy, Confocal; Pattern Recognition, Automated; Reproducibility of Results; Saccharomyces cerevisiae; Sensitivity and Specificity;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE

Conference_Location

Lyon

ISSN

1557-170X

Print_ISBN

978-1-4244-0787-3

Type

conf

DOI

10.1109/IEMBS.2007.4353606

Filename

4353606