ABSORB: Atlas building by self-organized registration and bundling

Hongjun Jia, Guorong Wu, Qian Wang, Dinggang Shen

Research output: Contribution to journalArticle

74 Citations (Scopus)

Abstract

To achieve more accurate and consistent registration in an image population, a novel hierarchical groupwise registration framework, called Atlas Building by Self-Organized Registration and Bundling (ABSORB), is proposed in this paper. In this new framework, the global structure, i.e., the relative distribution of subject images is always preserved during the registration process by constraining each subject image to deform only locally with respect to its neighbors within the learned image manifold. To achieve this goal, two novel strategies, i.e., the self-organized registration by warping one image towards a set of its eligible neighbors and image bundling to cluster similar images, are specially proposed. By using these two strategies, this new framework can perform groupwise registration in a hierarchical way. Specifically, in the high level, it will perform on a much smaller dataset formed by the representative subject images of all subgroups that are generated in the previous levels of registration. Compared to the other groupwise registration methods, our proposed framework has several advantages: (1) it explores the local data distribution and uses the obtained distribution information to guide the registration; (2) the possible registration error can be greatly reduced by requiring each individual subject to move only towards its nearby subjects with similar structures; (3) it can produce a smoother registration path, in general, from each subject image to the final built atlas than other groupwise registration methods. Experimental results on both synthetic and real datasets show that the proposed framework can achieve substantial improvements, compared to the other two widely used groupwise registration methods, in terms of both registration accuracy and robustness.

Original languageEnglish
Pages (from-to)1057-1070
Number of pages14
JournalNeuroImage
Volume51
Issue number3
DOIs
Publication statusPublished - 2010 Jul 1
Externally publishedYes

Fingerprint

Atlases
Information Dissemination
Population
Datasets

Keywords

  • Atlas building
  • Groupwise registration
  • Hierarchical registration
  • Image bundling
  • Self-organized registration

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

ABSORB : Atlas building by self-organized registration and bundling. / Jia, Hongjun; Wu, Guorong; Wang, Qian; Shen, Dinggang.

In: NeuroImage, Vol. 51, No. 3, 01.07.2010, p. 1057-1070.

Research output: Contribution to journalArticle

Jia, Hongjun ; Wu, Guorong ; Wang, Qian ; Shen, Dinggang. / ABSORB : Atlas building by self-organized registration and bundling. In: NeuroImage. 2010 ; Vol. 51, No. 3. pp. 1057-1070.
@article{6193a3f5f15b4b0a8e1e445160b5575b,
title = "ABSORB: Atlas building by self-organized registration and bundling",
abstract = "To achieve more accurate and consistent registration in an image population, a novel hierarchical groupwise registration framework, called Atlas Building by Self-Organized Registration and Bundling (ABSORB), is proposed in this paper. In this new framework, the global structure, i.e., the relative distribution of subject images is always preserved during the registration process by constraining each subject image to deform only locally with respect to its neighbors within the learned image manifold. To achieve this goal, two novel strategies, i.e., the self-organized registration by warping one image towards a set of its eligible neighbors and image bundling to cluster similar images, are specially proposed. By using these two strategies, this new framework can perform groupwise registration in a hierarchical way. Specifically, in the high level, it will perform on a much smaller dataset formed by the representative subject images of all subgroups that are generated in the previous levels of registration. Compared to the other groupwise registration methods, our proposed framework has several advantages: (1) it explores the local data distribution and uses the obtained distribution information to guide the registration; (2) the possible registration error can be greatly reduced by requiring each individual subject to move only towards its nearby subjects with similar structures; (3) it can produce a smoother registration path, in general, from each subject image to the final built atlas than other groupwise registration methods. Experimental results on both synthetic and real datasets show that the proposed framework can achieve substantial improvements, compared to the other two widely used groupwise registration methods, in terms of both registration accuracy and robustness.",
keywords = "Atlas building, Groupwise registration, Hierarchical registration, Image bundling, Self-organized registration",
author = "Hongjun Jia and Guorong Wu and Qian Wang and Dinggang Shen",
year = "2010",
month = "7",
day = "1",
doi = "10.1016/j.neuroimage.2010.03.010",
language = "English",
volume = "51",
pages = "1057--1070",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "3",

}

TY - JOUR

T1 - ABSORB

T2 - Atlas building by self-organized registration and bundling

AU - Jia, Hongjun

AU - Wu, Guorong

AU - Wang, Qian

AU - Shen, Dinggang

PY - 2010/7/1

Y1 - 2010/7/1

N2 - To achieve more accurate and consistent registration in an image population, a novel hierarchical groupwise registration framework, called Atlas Building by Self-Organized Registration and Bundling (ABSORB), is proposed in this paper. In this new framework, the global structure, i.e., the relative distribution of subject images is always preserved during the registration process by constraining each subject image to deform only locally with respect to its neighbors within the learned image manifold. To achieve this goal, two novel strategies, i.e., the self-organized registration by warping one image towards a set of its eligible neighbors and image bundling to cluster similar images, are specially proposed. By using these two strategies, this new framework can perform groupwise registration in a hierarchical way. Specifically, in the high level, it will perform on a much smaller dataset formed by the representative subject images of all subgroups that are generated in the previous levels of registration. Compared to the other groupwise registration methods, our proposed framework has several advantages: (1) it explores the local data distribution and uses the obtained distribution information to guide the registration; (2) the possible registration error can be greatly reduced by requiring each individual subject to move only towards its nearby subjects with similar structures; (3) it can produce a smoother registration path, in general, from each subject image to the final built atlas than other groupwise registration methods. Experimental results on both synthetic and real datasets show that the proposed framework can achieve substantial improvements, compared to the other two widely used groupwise registration methods, in terms of both registration accuracy and robustness.

AB - To achieve more accurate and consistent registration in an image population, a novel hierarchical groupwise registration framework, called Atlas Building by Self-Organized Registration and Bundling (ABSORB), is proposed in this paper. In this new framework, the global structure, i.e., the relative distribution of subject images is always preserved during the registration process by constraining each subject image to deform only locally with respect to its neighbors within the learned image manifold. To achieve this goal, two novel strategies, i.e., the self-organized registration by warping one image towards a set of its eligible neighbors and image bundling to cluster similar images, are specially proposed. By using these two strategies, this new framework can perform groupwise registration in a hierarchical way. Specifically, in the high level, it will perform on a much smaller dataset formed by the representative subject images of all subgroups that are generated in the previous levels of registration. Compared to the other groupwise registration methods, our proposed framework has several advantages: (1) it explores the local data distribution and uses the obtained distribution information to guide the registration; (2) the possible registration error can be greatly reduced by requiring each individual subject to move only towards its nearby subjects with similar structures; (3) it can produce a smoother registration path, in general, from each subject image to the final built atlas than other groupwise registration methods. Experimental results on both synthetic and real datasets show that the proposed framework can achieve substantial improvements, compared to the other two widely used groupwise registration methods, in terms of both registration accuracy and robustness.

KW - Atlas building

KW - Groupwise registration

KW - Hierarchical registration

KW - Image bundling

KW - Self-organized registration

UR - http://www.scopus.com/inward/record.url?scp=77952419496&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77952419496&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2010.03.010

DO - 10.1016/j.neuroimage.2010.03.010

M3 - Article

C2 - 20226255

AN - SCOPUS:77952419496

VL - 51

SP - 1057

EP - 1070

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 3

ER -