A 3-D deformable surface method for automatic hippocampus-amygdala complex segmentation

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

Research output: Contribution to journalArticle

Abstract

In this paper, we propose an atlas-based method for hippocampus-amygdala complex segmentation. An atlas is registered on all subjects and its transformation is calculated for each subject. This transformation is applied to the structural segmentation of the complex in atlas to construct an initial surface for the hippocampus-amygdala complex of each subject. A possibility approach is introduced for the segmentation process. Two different kinds of deformation based on edges and information obtained from tissue segmentation are used to find different parts of the complex. A new energy is defined to use tissue information. This energy is adopted to expand the model to embed dominant gray matter points in the volume and also withdraw from dominant white matter and CSF points. The initial shape is divided into several parts. In the normal direction of the center of each part, we construct a profile which search for the best poult that maximizes this new energy. This algorithm is reliable for finding the overall shape of the complex. It overcomes the poor features of the complex such as weak edges and noise. The algorithm is examined on 5 different subjects and validated using two different validation methods.

Original languageEnglish
Pages (from-to)3725-3729
Number of pages5
JournalIEEE Nuclear Science Symposium Conference Record
Volume6
Publication statusPublished - 2004
Externally publishedYes

Fingerprint

hippocampus
Atlases
Amygdala
Hippocampus
Tissue
search profiles
Noise
energy

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Industrial and Manufacturing Engineering

Cite this

A 3-D deformable surface method for automatic hippocampus-amygdala complex segmentation. / Karimi, M. M.; Batmanghelich, N.; Soltanian-Zadeh, H.; Lucas, C.

In: IEEE Nuclear Science Symposium Conference Record, Vol. 6, 2004, p. 3725-3729.

Research output: Contribution to journalArticle

@article{7421eb1485684df291c441087ae640dc,
title = "A 3-D deformable surface method for automatic hippocampus-amygdala complex segmentation",
abstract = "In this paper, we propose an atlas-based method for hippocampus-amygdala complex segmentation. An atlas is registered on all subjects and its transformation is calculated for each subject. This transformation is applied to the structural segmentation of the complex in atlas to construct an initial surface for the hippocampus-amygdala complex of each subject. A possibility approach is introduced for the segmentation process. Two different kinds of deformation based on edges and information obtained from tissue segmentation are used to find different parts of the complex. A new energy is defined to use tissue information. This energy is adopted to expand the model to embed dominant gray matter points in the volume and also withdraw from dominant white matter and CSF points. The initial shape is divided into several parts. In the normal direction of the center of each part, we construct a profile which search for the best poult that maximizes this new energy. This algorithm is reliable for finding the overall shape of the complex. It overcomes the poor features of the complex such as weak edges and noise. The algorithm is examined on 5 different subjects and validated using two different validation methods.",
author = "Karimi, {M. M.} and N. Batmanghelich and H. Soltanian-Zadeh and C. Lucas",
year = "2004",
language = "English",
volume = "6",
pages = "3725--3729",
journal = "IEEE Nuclear Science Symposium Conference Record",
issn = "1095-7863",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - A 3-D deformable surface method for automatic hippocampus-amygdala complex segmentation

AU - Karimi, M. M.

AU - Batmanghelich, N.

AU - Soltanian-Zadeh, H.

AU - Lucas, C.

PY - 2004

Y1 - 2004

N2 - In this paper, we propose an atlas-based method for hippocampus-amygdala complex segmentation. An atlas is registered on all subjects and its transformation is calculated for each subject. This transformation is applied to the structural segmentation of the complex in atlas to construct an initial surface for the hippocampus-amygdala complex of each subject. A possibility approach is introduced for the segmentation process. Two different kinds of deformation based on edges and information obtained from tissue segmentation are used to find different parts of the complex. A new energy is defined to use tissue information. This energy is adopted to expand the model to embed dominant gray matter points in the volume and also withdraw from dominant white matter and CSF points. The initial shape is divided into several parts. In the normal direction of the center of each part, we construct a profile which search for the best poult that maximizes this new energy. This algorithm is reliable for finding the overall shape of the complex. It overcomes the poor features of the complex such as weak edges and noise. The algorithm is examined on 5 different subjects and validated using two different validation methods.

AB - In this paper, we propose an atlas-based method for hippocampus-amygdala complex segmentation. An atlas is registered on all subjects and its transformation is calculated for each subject. This transformation is applied to the structural segmentation of the complex in atlas to construct an initial surface for the hippocampus-amygdala complex of each subject. A possibility approach is introduced for the segmentation process. Two different kinds of deformation based on edges and information obtained from tissue segmentation are used to find different parts of the complex. A new energy is defined to use tissue information. This energy is adopted to expand the model to embed dominant gray matter points in the volume and also withdraw from dominant white matter and CSF points. The initial shape is divided into several parts. In the normal direction of the center of each part, we construct a profile which search for the best poult that maximizes this new energy. This algorithm is reliable for finding the overall shape of the complex. It overcomes the poor features of the complex such as weak edges and noise. The algorithm is examined on 5 different subjects and validated using two different validation methods.

UR - http://www.scopus.com/inward/record.url?scp=23844439970&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=23844439970&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:23844439970

VL - 6

SP - 3725

EP - 3729

JO - IEEE Nuclear Science Symposium Conference Record

JF - IEEE Nuclear Science Symposium Conference Record

SN - 1095-7863

ER -