Title : 
PdEs-based morphology on graphs for cytological slides segmentation and clustering
         
        
            Author : 
Desquesnes, Xavier ; Elmoataz, Abderrahim ; Lézoray, Olivier
         
        
            Author_Institution : 
ENSICAEN, Univ. de Caen Basse Normandie, Caen, France
         
        
        
        
        
        
            Abstract : 
In this paper, we propose a new graph-based approach to address the problem of cytological computer-aided diagnostic. Such approach uses our previously introduced formalism of PdEs-based morphology and geometric diffusion on graphs. The approach is illustrated through two applications in cytopathology (involving Feulgen and Papanicolaou colorations), with examples of nucleus extraction and classification.
         
        
            Keywords : 
cellular biophysics; computer graphics; diseases; image classification; image segmentation; medical computing; medical image processing; pattern clustering; Feulgen colorations; Papanicolaou colorations; PdEs-based morphology; clustering; computer-aided diagnostic; cytological slides; cytopathology; formalism; geometric diffusion; graphs; nucleus classification; nucleus extraction; segmentation; Equations; Feature extraction; Image color analysis; Image segmentation; Level set; Mathematical model; Morphology; PdEs; classification; cytology; morphology; segmentation; weighted graphs;
         
        
        
        
            Conference_Titel : 
Biomedical Imaging (ISBI), 2012 9th IEEE International Symposium on
         
        
            Conference_Location : 
Barcelona
         
        
        
            Print_ISBN : 
978-1-4577-1857-1
         
        
        
            DOI : 
10.1109/ISBI.2012.6235886