Groupwise registration based on hierarchical image clustering and atlas synthesis

Qian Wang, Liya Chen, Pew Thian Yap, Guorong Wu, Dinggang Shen

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

Groupwise registration has recently been proposed for simultaneous and consistent registration of all images in a group. Since many deformation parameters need to be optimized for each image under registration, the number of images that can be effectively handled by conventional groupwise registration methods is limited. Moreover, the robustness of registration is at stake due to significant intersubject variability. To overcome these problems, we present a groupwise registration framework, which is based on a hierarchical image clustering and atlas synthesis strategy. The basic idea is to decompose a large-scale groupwise registration problem into a series of small-scale problems, each of which is relatively easy to solve using a general computer. In particular, we employ a method called affinity propagation, which is designed for fast and robust clustering, to hierarchically cluster images into a pyramid of classes. Intraclass registration is then performed to register all images within individual classes, resulting in a representative center image for each class. These center images of different classes are further registered, from the bottom to the top in the pyramid. Once the registration reaches the summit of the pyramid, a single center image, or an atlas, is synthesized. Utilizing this strategy, we can efficiently and effectively register a large image group, construct their atlas, and, at the same time, establish shape correspondences between each image and the atlas. We have evaluated our framework using real and simulated data, and the results indicate that our framework achieves better robustness and registration accuracy compared to conventional methods.

Original languageEnglish
Pages (from-to)1128-1140
Number of pages13
JournalHuman Brain Mapping
Volume31
Issue number8
DOIs
Publication statusPublished - 2010 Aug 1
Externally publishedYes

Fingerprint

Atlases
Cluster Analysis

Keywords

  • Groupwise registration
  • Hierarchical registration
  • Image clustering

ASJC Scopus subject areas

  • Clinical Neurology
  • Anatomy
  • Neurology
  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology

Cite this

Groupwise registration based on hierarchical image clustering and atlas synthesis. / Wang, Qian; Chen, Liya; Yap, Pew Thian; Wu, Guorong; Shen, Dinggang.

In: Human Brain Mapping, Vol. 31, No. 8, 01.08.2010, p. 1128-1140.

Research output: Contribution to journalArticle

Wang, Qian ; Chen, Liya ; Yap, Pew Thian ; Wu, Guorong ; Shen, Dinggang. / Groupwise registration based on hierarchical image clustering and atlas synthesis. In: Human Brain Mapping. 2010 ; Vol. 31, No. 8. pp. 1128-1140.
@article{1dbf990babd14762806d4c5762ac87b0,
title = "Groupwise registration based on hierarchical image clustering and atlas synthesis",
abstract = "Groupwise registration has recently been proposed for simultaneous and consistent registration of all images in a group. Since many deformation parameters need to be optimized for each image under registration, the number of images that can be effectively handled by conventional groupwise registration methods is limited. Moreover, the robustness of registration is at stake due to significant intersubject variability. To overcome these problems, we present a groupwise registration framework, which is based on a hierarchical image clustering and atlas synthesis strategy. The basic idea is to decompose a large-scale groupwise registration problem into a series of small-scale problems, each of which is relatively easy to solve using a general computer. In particular, we employ a method called affinity propagation, which is designed for fast and robust clustering, to hierarchically cluster images into a pyramid of classes. Intraclass registration is then performed to register all images within individual classes, resulting in a representative center image for each class. These center images of different classes are further registered, from the bottom to the top in the pyramid. Once the registration reaches the summit of the pyramid, a single center image, or an atlas, is synthesized. Utilizing this strategy, we can efficiently and effectively register a large image group, construct their atlas, and, at the same time, establish shape correspondences between each image and the atlas. We have evaluated our framework using real and simulated data, and the results indicate that our framework achieves better robustness and registration accuracy compared to conventional methods.",
keywords = "Groupwise registration, Hierarchical registration, Image clustering",
author = "Qian Wang and Liya Chen and Yap, {Pew Thian} and Guorong Wu and Dinggang Shen",
year = "2010",
month = "8",
day = "1",
doi = "10.1002/hbm.20923",
language = "English",
volume = "31",
pages = "1128--1140",
journal = "Human Brain Mapping",
issn = "1065-9471",
publisher = "Wiley-Liss Inc.",
number = "8",

}

TY - JOUR

T1 - Groupwise registration based on hierarchical image clustering and atlas synthesis

AU - Wang, Qian

AU - Chen, Liya

AU - Yap, Pew Thian

AU - Wu, Guorong

AU - Shen, Dinggang

PY - 2010/8/1

Y1 - 2010/8/1

N2 - Groupwise registration has recently been proposed for simultaneous and consistent registration of all images in a group. Since many deformation parameters need to be optimized for each image under registration, the number of images that can be effectively handled by conventional groupwise registration methods is limited. Moreover, the robustness of registration is at stake due to significant intersubject variability. To overcome these problems, we present a groupwise registration framework, which is based on a hierarchical image clustering and atlas synthesis strategy. The basic idea is to decompose a large-scale groupwise registration problem into a series of small-scale problems, each of which is relatively easy to solve using a general computer. In particular, we employ a method called affinity propagation, which is designed for fast and robust clustering, to hierarchically cluster images into a pyramid of classes. Intraclass registration is then performed to register all images within individual classes, resulting in a representative center image for each class. These center images of different classes are further registered, from the bottom to the top in the pyramid. Once the registration reaches the summit of the pyramid, a single center image, or an atlas, is synthesized. Utilizing this strategy, we can efficiently and effectively register a large image group, construct their atlas, and, at the same time, establish shape correspondences between each image and the atlas. We have evaluated our framework using real and simulated data, and the results indicate that our framework achieves better robustness and registration accuracy compared to conventional methods.

AB - Groupwise registration has recently been proposed for simultaneous and consistent registration of all images in a group. Since many deformation parameters need to be optimized for each image under registration, the number of images that can be effectively handled by conventional groupwise registration methods is limited. Moreover, the robustness of registration is at stake due to significant intersubject variability. To overcome these problems, we present a groupwise registration framework, which is based on a hierarchical image clustering and atlas synthesis strategy. The basic idea is to decompose a large-scale groupwise registration problem into a series of small-scale problems, each of which is relatively easy to solve using a general computer. In particular, we employ a method called affinity propagation, which is designed for fast and robust clustering, to hierarchically cluster images into a pyramid of classes. Intraclass registration is then performed to register all images within individual classes, resulting in a representative center image for each class. These center images of different classes are further registered, from the bottom to the top in the pyramid. Once the registration reaches the summit of the pyramid, a single center image, or an atlas, is synthesized. Utilizing this strategy, we can efficiently and effectively register a large image group, construct their atlas, and, at the same time, establish shape correspondences between each image and the atlas. We have evaluated our framework using real and simulated data, and the results indicate that our framework achieves better robustness and registration accuracy compared to conventional methods.

KW - Groupwise registration

KW - Hierarchical registration

KW - Image clustering

UR - http://www.scopus.com/inward/record.url?scp=77955064096&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955064096&partnerID=8YFLogxK

U2 - 10.1002/hbm.20923

DO - 10.1002/hbm.20923

M3 - Article

C2 - 20063349

AN - SCOPUS:77955064096

VL - 31

SP - 1128

EP - 1140

JO - Human Brain Mapping

JF - Human Brain Mapping

SN - 1065-9471

IS - 8

ER -