Efficient multi-object segmentation of 3D medical images using clustering and graph cuts

Abstract : We propose an application of multi-label ''Graph Cut" optimization algorithms to the simultaneous segmentation of multiple anatomical structures, initialized via an over-segmentation of the image computed by a fast centroidal Voronoi diagram (CVD) clustering algorithm. With respect to comparable segmentations computed directly on the voxels of image volumes, we demonstrate performance improvements on both execution speed and memory footprint by, at least, an order of magnitude, making it possible to process large volumes on commodity hardware which could not be processed pixel-wise.
Document type :
Conference papers
18th IEEE International Conference on Image Processing (ICIP 2011), Sep 2011, Bruxelles, Belgium. pp.2149-2152, 2011, <10.1109/ICIP.2011.6116036>


https://hal.archives-ouvertes.fr/hal-00658028
Contributor : Sébastien Valette <>
Submitted on : Monday, January 9, 2012 - 5:04:58 PM
Last modification on : Tuesday, November 17, 2015 - 5:31:26 PM
Document(s) archivé(s) le : Tuesday, April 10, 2012 - 2:37:35 AM

Files

kechichian-et-al-icip-2011.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Razmig Kéchichian, Sébastien Valette, Michel Desvignes, Rémy Prost. Efficient multi-object segmentation of 3D medical images using clustering and graph cuts. 18th IEEE International Conference on Image Processing (ICIP 2011), Sep 2011, Bruxelles, Belgium. pp.2149-2152, 2011, <10.1109/ICIP.2011.6116036>. <hal-00658028>

Export

Share

Metrics

Record views

228

Document downloads

186