Title :
Efficient segmentation of cellular images using gradient-based methods and simple morphological filters
Author :
Sweeney, Nina ; Sweeney, Brian V.
Author_Institution :
Div. of Quantitative Pathology, Armed Forces Inst. of Pathology, Washington, DC, USA
fDate :
30 Oct-2 Nov 1997
Abstract :
This paper presents an algorithm for segmenting two-dimensional (2-D) microscope images of overlapping regions of cell nuclei. Algorithms for segmenting such images must be fast as well as capable of handling subtle variability between objects if they are to be of practical clinical use. The authors attempt to address these issues by the application of techniques that exploit local features, extract object boundaries, perform skeletonization using the distance transform and gradient operators, and evaluate junction segment candidates based on boundary criteria
Keywords :
cellular biophysics; edge detection; image segmentation; image thinning; medical image processing; optical microscopy; algorithm; boundary criteria; cellular images segmentation; cytological images analysis; distance transform; gradient operators; gradient-based methods; junction segment candidates; local features; object boundaries extraction; overlapping regions; practical clinical use; simple morphological filters; skeletonization; subtle variability between objects; Breast; Clustering algorithms; Electronic mail; Feature extraction; Image segmentation; Laboratories; Optical filters; Pathology; Performance evaluation; Skeleton;
Conference_Titel :
Engineering in Medicine and Biology Society, 1997. Proceedings of the 19th Annual International Conference of the IEEE
Conference_Location :
Chicago, IL
Print_ISBN :
0-7803-4262-3
DOI :
10.1109/IEMBS.1997.757807