Automated recognition of mitotic patterns in fluorescence microscopy images of human cells

Nathalie Harder, Beate Neumann, Michael Held, Urban Liebel, Holger Erfle, Jan Ellenberg, Roland Eils, Karl Rohr

Abstract

High-throughput screens of the gene function provide rapidly increasing amounts of data. In particular, the analysis of image data acquired in genome-wide cell phenotype screens constitutes a substantial bottleneck in the evaluation process and motivates the development of automated image analysis tools for large-scale experiments. Here we introduce a computational scheme to process multi-cell images as they are produced in high-throughput screens. We describe an approach to automatically segment and classify cell nuclei into different mitotic phenotypes. This enables automated identification of cell cultures that show an abnormal mitotic behavior. Our scheme proves a high classification accuracy, suggesting a promising future for automating the evaluation of high-throughput experiments
BibTeX
@inproceedings{harder2006automated,
  author = {Nathalie Harder and Beate Neumann and Michael Held and Urban Liebel and Holger Erfle and Jan Ellenberg and Roland Eils and Karl Rohr},
  title = {{Automated recognition of mitotic patterns in fluorescence microscopy images of human cells}},
  booktitle = {Bildverarbeitung für die Medizin},
  year = {2006},
  doi = {10.1007/3-540-32137-3\_76},
}

Loading related content...

Figure