APPLYING WATERSHED ALGORITHMS TO THE SEGMENTATION OF CLUSTERED NUCLEI

Cluster division is a critical issue in fluorescence microscopy-based analytical cytology when preparation protocols do not provide appropri ate separation of objects. Overlooking clustered nuclei and analyzing only isolated nuclei may dramatically increase analysis time or affect the statistical validation of the results. Automatic segmentation of clustered nuclei requires the implementation of specific image segment ation tools. Most algorithms are inspired by one of the two following strategies: 1) cluster division by the detection of internuclei gradie nts; or 2) division by definition of domains of influence (geometrical approach). Both strategies lead to completely different implementatio ns, and usually algorithms based on a single view strategy fail to cor rectly segment most clustered nuclei, or perform well just for a speci fic type of sample. An algorithm based on morphological watersheds has been implemented and tested on the segmentation of microscopic nuclei clusters. This algorithm provides a tool that can be used for the imp lementation of both gradient- and domain-based algorithms, and, more i mportantly, for the implementation of mixed (gradient- and shape-based ) algorithms. Using this algorithm, almost 90% of the test clusters we re correctly segmented in peripheral blood and bone marrow preparation s. The algorithm was valid for both types of samples, using the approp riate markers and transformations. (C) 1997 Wiley-Liss, Inc.