Improvement of simplex meshes model for 3D hippocampus segmentation

M. M. Karimi, N. Batmanghelich, H. Soltanian-Zadeh, C. Lucas

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we used a deformable surface model, called simplex meshes, for hippocampus segmentation in brain MRI. Major problems of the hippocampus segmentation are weak edges and noise that may cause deformable model to move in wrong ways. To overcome these problems, we used simplex meshes model, which has the capability to move roughly. To initialize the primary shape we projected an atlas to the real data using a registration algorithm. We selected some parts of the initial shape and exerted forces to the vertices of this shape, which is proportion to the distance to these parts. Displacement of these parts helps model to overcome weak edges and also prevents self-cutting of the vertices. Finally, we did a final tuning to reach to the small details of the edges.

Original languageEnglish
Title of host publicationProceedings of the Fourth IASTED International Conference on Visualization, Imaging, and Image Processing
EditorsJ.J. Villanueva
Pages631-635
Number of pages5
Publication statusPublished - 2004
Externally publishedYes
EventProceedings of the Fourth IASTED International Conference on Visualization, Imaging, and Image Processing - Marbella, Spain
Duration: 6 Sep 20048 Sep 2004

Other

OtherProceedings of the Fourth IASTED International Conference on Visualization, Imaging, and Image Processing
CountrySpain
CityMarbella
Period6/9/048/9/04

Fingerprint

Magnetic resonance imaging
Brain
Tuning

Keywords

  • Brain segmentation
  • Deformable surface
  • Magnetic Resonance Imaging (MRI)
  • Simplex meshes

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Karimi, M. M., Batmanghelich, N., Soltanian-Zadeh, H., & Lucas, C. (2004). Improvement of simplex meshes model for 3D hippocampus segmentation. In J. J. Villanueva (Ed.), Proceedings of the Fourth IASTED International Conference on Visualization, Imaging, and Image Processing (pp. 631-635). [452-807]

Improvement of simplex meshes model for 3D hippocampus segmentation. / Karimi, M. M.; Batmanghelich, N.; Soltanian-Zadeh, H.; Lucas, C.

Proceedings of the Fourth IASTED International Conference on Visualization, Imaging, and Image Processing. ed. / J.J. Villanueva. 2004. p. 631-635 452-807.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Karimi, MM, Batmanghelich, N, Soltanian-Zadeh, H & Lucas, C 2004, Improvement of simplex meshes model for 3D hippocampus segmentation. in JJ Villanueva (ed.), Proceedings of the Fourth IASTED International Conference on Visualization, Imaging, and Image Processing., 452-807, pp. 631-635, Proceedings of the Fourth IASTED International Conference on Visualization, Imaging, and Image Processing, Marbella, Spain, 6/9/04.
Karimi MM, Batmanghelich N, Soltanian-Zadeh H, Lucas C. Improvement of simplex meshes model for 3D hippocampus segmentation. In Villanueva JJ, editor, Proceedings of the Fourth IASTED International Conference on Visualization, Imaging, and Image Processing. 2004. p. 631-635. 452-807
Karimi, M. M. ; Batmanghelich, N. ; Soltanian-Zadeh, H. ; Lucas, C. / Improvement of simplex meshes model for 3D hippocampus segmentation. Proceedings of the Fourth IASTED International Conference on Visualization, Imaging, and Image Processing. editor / J.J. Villanueva. 2004. pp. 631-635
@inproceedings{3a6708a872744df6a25423445d8482c3,
title = "Improvement of simplex meshes model for 3D hippocampus segmentation",
abstract = "In this paper, we used a deformable surface model, called simplex meshes, for hippocampus segmentation in brain MRI. Major problems of the hippocampus segmentation are weak edges and noise that may cause deformable model to move in wrong ways. To overcome these problems, we used simplex meshes model, which has the capability to move roughly. To initialize the primary shape we projected an atlas to the real data using a registration algorithm. We selected some parts of the initial shape and exerted forces to the vertices of this shape, which is proportion to the distance to these parts. Displacement of these parts helps model to overcome weak edges and also prevents self-cutting of the vertices. Finally, we did a final tuning to reach to the small details of the edges.",
keywords = "Brain segmentation, Deformable surface, Magnetic Resonance Imaging (MRI), Simplex meshes",
author = "Karimi, {M. M.} and N. Batmanghelich and H. Soltanian-Zadeh and C. Lucas",
year = "2004",
language = "English",
isbn = "0889864152",
pages = "631--635",
editor = "J.J. Villanueva",
booktitle = "Proceedings of the Fourth IASTED International Conference on Visualization, Imaging, and Image Processing",

}

TY - GEN

T1 - Improvement of simplex meshes model for 3D hippocampus segmentation

AU - Karimi, M. M.

AU - Batmanghelich, N.

AU - Soltanian-Zadeh, H.

AU - Lucas, C.

PY - 2004

Y1 - 2004

N2 - In this paper, we used a deformable surface model, called simplex meshes, for hippocampus segmentation in brain MRI. Major problems of the hippocampus segmentation are weak edges and noise that may cause deformable model to move in wrong ways. To overcome these problems, we used simplex meshes model, which has the capability to move roughly. To initialize the primary shape we projected an atlas to the real data using a registration algorithm. We selected some parts of the initial shape and exerted forces to the vertices of this shape, which is proportion to the distance to these parts. Displacement of these parts helps model to overcome weak edges and also prevents self-cutting of the vertices. Finally, we did a final tuning to reach to the small details of the edges.

AB - In this paper, we used a deformable surface model, called simplex meshes, for hippocampus segmentation in brain MRI. Major problems of the hippocampus segmentation are weak edges and noise that may cause deformable model to move in wrong ways. To overcome these problems, we used simplex meshes model, which has the capability to move roughly. To initialize the primary shape we projected an atlas to the real data using a registration algorithm. We selected some parts of the initial shape and exerted forces to the vertices of this shape, which is proportion to the distance to these parts. Displacement of these parts helps model to overcome weak edges and also prevents self-cutting of the vertices. Finally, we did a final tuning to reach to the small details of the edges.

KW - Brain segmentation

KW - Deformable surface

KW - Magnetic Resonance Imaging (MRI)

KW - Simplex meshes

UR - http://www.scopus.com/inward/record.url?scp=11144279173&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11144279173&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0889864152

SN - 9780889864153

SP - 631

EP - 635

BT - Proceedings of the Fourth IASTED International Conference on Visualization, Imaging, and Image Processing

A2 - Villanueva, J.J.

ER -