Ontology-based lymphocyte population description using mathematical morphology on colour blood images.

Despite modern technologies (immunophenotyping, molecular probing, etc.) cytomorphologic examination of stained peripheral blood smears by microscopy remains the main way of diagnosis in a large variety of diseases (e.g. leukaemic disorders). Using tools from mathematical morphology for processing peripheral blood colour images, we have developed an image-based approach, to provide an objective and understandable description of lymphocyte populations according to a specifically designed ontology. This ontology-based framework needs a conceptualisation of the problem from a morphological viewpoint, the introduction of an adapted language, the generation of representative image databases, the development of image processing and data classification algorithms to automate the procedure and the validation of the system by human expertise. In this paper we present the main concepts, algorithms and some results to illustrate the high-performance of the approach. The aim of our work is to reconcile the automatisation with the medical expertise, so that they can reinforce each other.