Morphological deterministic operators and stochastic models for image segmentation and quantification of multi-fluorescence labelled cell populations
J. Angulo (Centre de Morphologie Mathématique-Ecoles des Mines de Paris, France)
In fluorescence-labelled cell assays for high content screening applications, image processing tools are necessary to have automatic algorithms for segmenting the cell structures individually and for quantifying their number, shape distribution, spatial organisation, texture parameters, etc. Mathematical morphology is a non-linear image processing technique which is proven to be a very powerful tool in biomedical microscopy image analysis. This paper presents the application of deterministic morphological operators and random models for segmenting and describing cells of different size/shape, contrast, overlapping effects, etc. The methods are illustrated with multivariate cell images from different biomedical applications.