Extraction of the number of peroxisomes in yeast cells by automated image analysis

Antti Niemistö; Jyrki Selinummi; Ramsey Saleem; Ilya Shmulevich; John Aitchison; Olli Yli-Harja

doi:10.1109/IEMBS.2006.259890

Extraction of the number of peroxisomes in yeast cells by automated image analysis

Conf Proc IEEE Eng Med Biol Soc. 2006:2006:2353-6. doi: 10.1109/IEMBS.2006.259890.

Authors

Antti Niemistö¹, Jyrki Selinummi, Ramsey Saleem, Ilya Shmulevich, John Aitchison, Olli Yli-Harja

Affiliation

¹ Institute of Signal Processing, Tampere University of Technology, Finland.

PMID: 17945710
DOI: 10.1109/IEMBS.2006.259890

Abstract

An automated image analysis method for extracting the number of peroxisomes in yeast cells is presented. Two images of the cell population are required for the method: a bright field microscope image from which the yeast cells are detected and the respective fluorescent image from which the number of peroxisomes in each cell is found. The segmentation of the cells is based on clustering the local mean-variance space. The watershed transformation is thereafter employed to separate cells that are clustered together. The peroxisomes are detected by thresholding the fluorescent image. The method is tested with several images of a budding yeast Saccharomyces cerevisiae population, and the results are compared with manually obtained results.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms*
Artificial Intelligence*
Image Enhancement / methods
Image Interpretation, Computer-Assisted / methods*
Imaging, Three-Dimensional / methods*
Microscopy, Confocal / methods*
Pattern Recognition, Automated / methods*
Peroxisomes / ultrastructure*
Reproducibility of Results
Saccharomyces cerevisiae / cytology*
Sensitivity and Specificity