Segmentation and labeling of visible human dataset based on atlas

H. Duan, Ou Tan, C. Jia, W. Lu

Research output: Contribution to journalArticle

Abstract

We proposed an automatic segmentation and classification method of multimodal human brain image based on a computerized brain atlas-TT Atlas. It could be divided into two steps. Firstly, the object brain data set was registered with the TT atlas by a 3D image matching method. With the help of anatomy structure information of the computerized atlas, we can segment and classify the brain data coarsely. Secondly, the segmentation result was taken as the input of a fuzzy clustering segmentation. In order to use the anatomic structure information directly, a new fuzzy cluster method with a shape factor was introduced. The method is mostly automatically except selection of some intrinsic point pairs for global linear matching method in the first step. At last, this method was used for classification of brain image from VHD.

Original languageEnglish (US)
Pages (from-to)248-253
Number of pages6
JournalChinese Journal of Biomedical Engineering
Volume20
Issue number3
StatePublished - 2001
Externally publishedYes

Fingerprint

Atlases
Labeling
Brain
Image matching
Fuzzy clustering
Cluster Analysis
Datasets
Anatomy

Keywords

  • Automatic image segmentation
  • FCM clustering
  • Image matching
  • TT atlas
  • Visible human project

ASJC Scopus subject areas

  • Biophysics
  • Bioengineering

Cite this

Segmentation and labeling of visible human dataset based on atlas. / Duan, H.; Tan, Ou; Jia, C.; Lu, W.

In: Chinese Journal of Biomedical Engineering, Vol. 20, No. 3, 2001, p. 248-253.

Research output: Contribution to journalArticle

@article{e75a0d9f902e454d9fd78da999066745,
title = "Segmentation and labeling of visible human dataset based on atlas",
abstract = "We proposed an automatic segmentation and classification method of multimodal human brain image based on a computerized brain atlas-TT Atlas. It could be divided into two steps. Firstly, the object brain data set was registered with the TT atlas by a 3D image matching method. With the help of anatomy structure information of the computerized atlas, we can segment and classify the brain data coarsely. Secondly, the segmentation result was taken as the input of a fuzzy clustering segmentation. In order to use the anatomic structure information directly, a new fuzzy cluster method with a shape factor was introduced. The method is mostly automatically except selection of some intrinsic point pairs for global linear matching method in the first step. At last, this method was used for classification of brain image from VHD.",
keywords = "Automatic image segmentation, FCM clustering, Image matching, TT atlas, Visible human project",
author = "H. Duan and Ou Tan and C. Jia and W. Lu",
year = "2001",
language = "English (US)",
volume = "20",
pages = "248--253",
journal = "Zhongguo Shengwu Yixue Gongcheng Xuebao/Chinese Journal of Biomedical Engineering",
issn = "0258-8021",
publisher = "Chinese Academy of Medical Sciences",
number = "3",

}

TY - JOUR

T1 - Segmentation and labeling of visible human dataset based on atlas

AU - Duan, H.

AU - Tan, Ou

AU - Jia, C.

AU - Lu, W.

PY - 2001

Y1 - 2001

N2 - We proposed an automatic segmentation and classification method of multimodal human brain image based on a computerized brain atlas-TT Atlas. It could be divided into two steps. Firstly, the object brain data set was registered with the TT atlas by a 3D image matching method. With the help of anatomy structure information of the computerized atlas, we can segment and classify the brain data coarsely. Secondly, the segmentation result was taken as the input of a fuzzy clustering segmentation. In order to use the anatomic structure information directly, a new fuzzy cluster method with a shape factor was introduced. The method is mostly automatically except selection of some intrinsic point pairs for global linear matching method in the first step. At last, this method was used for classification of brain image from VHD.

AB - We proposed an automatic segmentation and classification method of multimodal human brain image based on a computerized brain atlas-TT Atlas. It could be divided into two steps. Firstly, the object brain data set was registered with the TT atlas by a 3D image matching method. With the help of anatomy structure information of the computerized atlas, we can segment and classify the brain data coarsely. Secondly, the segmentation result was taken as the input of a fuzzy clustering segmentation. In order to use the anatomic structure information directly, a new fuzzy cluster method with a shape factor was introduced. The method is mostly automatically except selection of some intrinsic point pairs for global linear matching method in the first step. At last, this method was used for classification of brain image from VHD.

KW - Automatic image segmentation

KW - FCM clustering

KW - Image matching

KW - TT atlas

KW - Visible human project

UR - http://www.scopus.com/inward/record.url?scp=0034933508&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034933508&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0034933508

VL - 20

SP - 248

EP - 253

JO - Zhongguo Shengwu Yixue Gongcheng Xuebao/Chinese Journal of Biomedical Engineering

JF - Zhongguo Shengwu Yixue Gongcheng Xuebao/Chinese Journal of Biomedical Engineering

SN - 0258-8021

IS - 3

ER -