Image processing solutions
Mitotic index determination
Mitotic index is a key parameter describing the mitosis. Automatic determination of this parameter directly from microscopy image is crucial in many biological experiments. We have been developing an algorithm that makes use of multimodality (time lapse movies with phase contrast and fluorescence images) and detects three types of cells: normal, mitotic and dead ones. For normal cell cultures the mitotic index does not exceed 5% (cf. left Fig.). Greater values demonstrate disturbance in the mitosis and give biologists a significant feedback how the biological experiments influence the cell division. The automatic quantification of mitotic and normal cells is necessary for determination of genes that influence the mitosis. Dead cells should be also detected and excluded from considerations.
Miroslaw L, Chorazyczewski A., Buchholz F., Kittler R., Correlation-based method for Automatic Mitotic Cell Detection in Phase Contrast Microscopy.Proc.4th Int. Conf.Computer Recognition Systems CORES 2005;pp. 627-35: Springer Verlag Berlin Hildelberg 2005.
More information can be obtained from
lukasz.miroslaw@vratis.com
Detection of mitotic cells
We have proposed a simple and fast method to detect mitotic cells from
two cell lines imaged in two phase contrast techniques. Detection
algorithm is based on a template matching approach followed by a
validation step that takes into account a priori information about
mitotic cells.
 |
 |
Results
The method performs well for a given set of fluorescence/phase contrast images. Access to both modalities allows for the construction an algorithm that makes use of both modalities to detect normal and dead cells. Hence, the statistics about the variation of the mitotic index in time can be computed.
Currently, cell tracking is being developed to provide more detailed statistics about the cell division process.
The project was conducted in co-operation with Max Planck Institute of Cell Biology and Genetics.