Show simple item record

dc.contributor.authorRathi, Yogesh
dc.contributor.authorDambreville, Samuel
dc.contributor.authorNiethammer, Marc
dc.contributor.authorMalcolm, James G.
dc.contributor.authorLevitt, James
dc.contributor.authorTannenbaum, Allen R.
dc.date.accessioned2009-06-22T20:28:47Z
dc.date.available2009-06-22T20:28:47Z
dc.date.issued2008-02
dc.identifier.citationYogesh Rathi, Samuel Dambreville, Marc Niethammer, James Malcolm, James Levitt, Martha E. Shenton, and Allen Tannenbaum, "Segmenting images analytically in shape space," Medical Imaging 2008: Image Processing, Joseph M. Reinhardt, Josien P. W. Pluim, Editors, Proc. SPIE, Vol. 6914, 691405 (2008)en
dc.identifier.issn0277-786X
dc.identifier.urihttp://hdl.handle.net/1853/28594
dc.description©2008 SPIE--The International Society for Optical Engineering. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited. The electronic version of this article is the complete one and can be found online at: http://dx.doi.org/10.1117/12.769511en
dc.descriptionPresented at Medical Imaging 2008: Image Processing, February 17-19, 2008, San Diego, CA, USA.
dc.descriptionDOI: 10.1117/12.769511
dc.description.abstractThis paper presents a novel analytic technique to perform shape-driven segmentation. In our approach, shapes are represented using binary maps, and linear PCA is utilized to provide shape priors for segmentation. Intensity based probability distributions are then employed to convert a given test volume into a binary map representation, and a novel energy functional is proposed whose minimum can be analytically computed to obtain the desired segmentation in the shape space. We compare the proposed method with the log-likelihood based energy to elucidate some key differences. Our algorithm is applied to the segmentation of brain caudate nucleus and hippocampus from MRI data, which is of interest in the study of schizophrenia and Alzheimer's disease. Our validation (we compute the Hausdorff distance and the DICE coefficient between the automatic segmentation and ground-truth) shows that the proposed algorithm is very fast, requires no initialization and outperforms the log-likelihood based energy.en
dc.language.isoen_USen
dc.publisherGeorgia Institute of Technologyen
dc.subjectAlgorithms
dc.subjectShape-driven segmentation
dc.subjectPrincipal component analysis
dc.subjectAutomatic segmentation algorithms
dc.subjectImage segmentation
dc.titleSegmenting Images Analytically in Shape Spaceen
dc.typeProceedingsen
dc.contributor.corporatenameGeorgia Institute of Technology. Dept. of Biomedical Engineering
dc.contributor.corporatenameEmory University. Dept. of Biomedical Engineering
dc.contributor.corporatenameGeorgia Institute of Technology. School of Electrical and Computer Engineering
dc.contributor.corporatenameBrigham and Women’s Hospital
dc.contributor.corporatenameHarvard Medical School
dc.publisher.originalSociety of Photo-Optical Instrumentation Engineers


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record