Technical Program

Paper Detail

Paper:	SA-PM-OS1.1
Session:	Cellular and Molecular Image Analysis
Time:	Saturday, April 8, 14:50 - 15:10
Presentation:	Oral
Title:	Automated Recognition of Mitotic Patterns in Fluorescence Microscopy Images of Human Cells
Authors:	Nathalie Harder; German Cancer Research Center
	Beate Neumann; European Molecular Biology Laboratory
	Michael Held; European Molecular Biology Laboratory
	Urban Liebel; European Molecular Biology Laboratory
	Holger Erfle; European Molecular Biology Laboratory
	Jan Ellenberg; European Molecular Biology Laboratory
	Roland Eils; German Cancer Research Center
	Karl Rohr; German Cancer Research Center
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.

ISBI 2006 is sponsored by

and organized in cooperation with