PDE Based image segmentation for biomedical applications

Sophie Schüpp (1) , Abderrahim Elmoataz (1) , Jalal M. Fadili (1) , Daniel Bloyet (2)

1 Equipe Image - Laboratoire GREYC - UMR6072
2 GREYC - Groupe de Recherche en Informatique, Image et Instrumentation de Caen

In medical microscopy, image analysis offers to pathologist a modern tool, which can be applied to several problems in cancerology: quantification of DNA content, quantification of immunostaining, counting of nuclear mitosis, characterisation of tumour tissue architecture. However, these problems need a quantitative and automatic segmentation. In most cases, the segmentation concerns the extraction of cell nuclei or cell clusters. In this paper we address the problem of automatically segmenting intensity or color images from medical microscopy. An automatic segmentation method combining fuzzy clustering multiple active contour models is presented. Automatic and fast initialization algorithm based on fuzzy clustering and morphological tools is used to robustly identify and classify all possible seed regions in the color image. These seeds are propagated outward simultaneously to localize the final contours of all objects. A fast level set formulation is used to model the multiple contour evolution. We illustrate our method by presenting two representatives problems in cytology and histology.

Domaines: Traitement des images [eess.IV]

Sophie Schüpp, Abderrahim Elmoataz, Jalal M. Fadili, Daniel Bloyet. PDE Based image segmentation for biomedical applications. International Conference on Image and Signal Processing, 2001, Agadir, Morocco. pp.204-215. ⟨hal-01016088⟩