Segmentation of cytological images using color and mathematical morphology
Olivier Lezoray,
Laboratoire Universitaire des Sciences Appliquées de Cherbourg (L.U.S.A.C), E.I.C, Site Universitaire, B.P. 78, 50130 Octeville, France; Department of Pathology, « Centre Hospitalier Louis Pasteur » of Cherbourg, Rue du Val de Saire, 50100 Cherbourg, France
Abderrahim Elmoataz,
Laboratoire Universitaire des Sciences Appliquées de Cherbourg (L.U.S.A.C), E.I.C, Site Universitaire, B.P. 78, 50130 Octeville, France ; Groupe de Recherche en Informatique, Image et Instrumentation de Caen (G.R.E.Y.C), I.S.M.R.A., Bd du Maréchal Juin, 14050 Caen Cedex, France
Hubert Cardot,
Laboratoire Universitaire des Sciences Appliquées de Cherbourg (L.U.S.A.C), E.I.C, Site Universitaire, B.P. 78, 50130 Octeville, France
Gilles Gougeon,
Laboratoire Universitaire des Sciences Appliquées de Cherbourg (L.U.S.A.C), E.I.C, Site Universitaire, B.P. 78, 50130 Octeville, France
Michel Lecluse,
Department of Pathology, « Centre Hospitalier Louis Pasteur » of Cherbourg, Rue du Val de Saire, 50100 Cherbourg, France
Hubert Elie,
Department of Pathology, « Centre Hospitalier Louis Pasteur » of Cherbourg, Rue du Val de Saire, 50100 Cherbourg, France
Marinette Revenu,
Groupe de Recherche en Informatique, Image et Instrumentation de Caen (G.R.E.Y.C), I.S.M.R.A., Bd du Maréchal Juin, 14050 Caen Cedex, France
Abstract
Screening is a manual activity which involves its subjectivity. A semi-automated computer-based system could contribute to the detection of screening errors by the way of a greater reliability. We intend to design such a system operating on color images from serous cytology. The aim of this paper is to present the strategy of the first part of the system: segmentation. It is based on mathematical morphology tools such as watersheds using color infom1ation in several color spaces. An extension of watershed to an optimal region-growing operator has been used. A pool of cells has been evaluated by experts to score the segmentation success rate. All cells have been isolated whatever their spatial configuration may be. The average success rate is 94.5% for the nuclei and 93% for the cytoplasm. Our morphological color segmentation of cytological serous images is accurate and provides a good tool for the extraction of cells.
Keywords : cluster division, color, cytology, image analysis, mathematical morphology, region growing, watersheds
Pour citer cet article
Olivier Lezoray, Abderrahim Elmoataz, Hubert Cardot, Gilles Gougeon, Michel Lecluse, Hubert Elie & Marinette Revenu, «Segmentation of cytological images using color and mathematical morphology», Acta Stereologica [En ligne], Volume 18 (1999), Number 1 - May 1999, 1-14 URL : https://popups.uliege.be/0351-580x/index.php?id=49.
