Title :
Automated extraction of nuclear boundaries
Author :
Wang, H. ; Ong, S.H.
Author_Institution :
Dept. of Electr. Eng., Nat. Univ. of Singapore, Singapore
Abstract :
The authors present an automated method for the extraction of cell nuclei in images of kidney tissue sections. There are two stages in the segmentation strategy: (a) coarse segmentation by thresholding and morphological processing, and (b) accurate extraction of the nuclear boundary by region growing. The segmentation procedure is performed in a global manner and computationally less expensive than local approaches. Results obtained by applying the algorithm to several tissue images confirm its reliability
Keywords :
cellular biophysics; edge detection; feature extraction; image segmentation; kidney; medical image processing; optical microscopy; accurate extraction; automated extraction; automated method; cell nuclei extraction; coarse segmentation; diagnostic interpretation; kidney tissue images; morphological processing; nuclear boundaries; segmentation strategy; thresholding; Anisotropic magnetoresistance; Electrons; Histograms; Image resolution; Image segmentation; Image texture analysis; Inspection; Machine vision; Manuals; Shape;
Conference_Titel :
Biomedical Engineering Days, 1998. Proceedings of the 1998 2nd International Conference
Conference_Location :
Istanbul
Print_ISBN :
0-7803-4242-9
DOI :
10.1109/IBED.1998.710576
