A novel framework for longitudinal atlas construction with groupwise registration of subject image sequences

Shu Liao, Hongjun Jia, Guorong Wu, Dinggang Shen

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Longitudinal atlas construction plays an important role in medical image analysis. Given a set of longitudinal images from different subjects, the task of longitudinal atlas construction is to build an atlas sequence which can represent the trend of anatomical changes of the population. The major challenge for longitudinal atlas construction is how to effectively incorporate both the subject-specific information and population information to build the unbiased atlases. In this paper, a novel groupwise longitudinal atlas construction framework is proposed to address this challenge, and the main contributions of the proposed framework lie in the following aspects: (1) The subject-specific longitudinal information is captured by building the growth model for each subject. (2) The longitudinal atlas sequence is constructed by performing groupwise registration among all the subject image sequences, and only one transformation is needed to transform each subject's image sequence to the atlas space. The constructed longitudinal atlases are unbiased and no explicit template is assumed. (3) The proposed method is general, where the number of longitudinal images of each subject and the time points at which they are taken can be different. The proposed method is extensively evaluated on two longitudinal databases, namely the BLSA and ADNI databases, to construct the longitudinal atlas sequence. It is also compared with a state-of-the-art longitudinal atlas construction algorithm based on kernel regression on the temporal domain. Experimental results demonstrate that the proposed method consistently achieves higher registration accuracies and more consistent spatial-temporal correspondences than the compared method on both databases.

Original languageEnglish
Pages (from-to)1275-1289
Number of pages15
JournalNeuroImage
Volume59
Issue number2
DOIs
Publication statusPublished - 2012 Jan 16
Externally publishedYes

Fingerprint

Atlases
Databases
Population

Keywords

  • Groupwise registration
  • Longitudinal atlas construction
  • Unbiased atlas

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

A novel framework for longitudinal atlas construction with groupwise registration of subject image sequences. / Liao, Shu; Jia, Hongjun; Wu, Guorong; Shen, Dinggang.

In: NeuroImage, Vol. 59, No. 2, 16.01.2012, p. 1275-1289.

Research output: Contribution to journalArticle

@article{200da1b6fa294708bee7041573f68d30,
title = "A novel framework for longitudinal atlas construction with groupwise registration of subject image sequences",
abstract = "Longitudinal atlas construction plays an important role in medical image analysis. Given a set of longitudinal images from different subjects, the task of longitudinal atlas construction is to build an atlas sequence which can represent the trend of anatomical changes of the population. The major challenge for longitudinal atlas construction is how to effectively incorporate both the subject-specific information and population information to build the unbiased atlases. In this paper, a novel groupwise longitudinal atlas construction framework is proposed to address this challenge, and the main contributions of the proposed framework lie in the following aspects: (1) The subject-specific longitudinal information is captured by building the growth model for each subject. (2) The longitudinal atlas sequence is constructed by performing groupwise registration among all the subject image sequences, and only one transformation is needed to transform each subject's image sequence to the atlas space. The constructed longitudinal atlases are unbiased and no explicit template is assumed. (3) The proposed method is general, where the number of longitudinal images of each subject and the time points at which they are taken can be different. The proposed method is extensively evaluated on two longitudinal databases, namely the BLSA and ADNI databases, to construct the longitudinal atlas sequence. It is also compared with a state-of-the-art longitudinal atlas construction algorithm based on kernel regression on the temporal domain. Experimental results demonstrate that the proposed method consistently achieves higher registration accuracies and more consistent spatial-temporal correspondences than the compared method on both databases.",
keywords = "Groupwise registration, Longitudinal atlas construction, Unbiased atlas",
author = "Shu Liao and Hongjun Jia and Guorong Wu and Dinggang Shen",
year = "2012",
month = "1",
day = "16",
doi = "10.1016/j.neuroimage.2011.07.095",
language = "English",
volume = "59",
pages = "1275--1289",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "2",

}

TY - JOUR

T1 - A novel framework for longitudinal atlas construction with groupwise registration of subject image sequences

AU - Liao, Shu

AU - Jia, Hongjun

AU - Wu, Guorong

AU - Shen, Dinggang

PY - 2012/1/16

Y1 - 2012/1/16

N2 - Longitudinal atlas construction plays an important role in medical image analysis. Given a set of longitudinal images from different subjects, the task of longitudinal atlas construction is to build an atlas sequence which can represent the trend of anatomical changes of the population. The major challenge for longitudinal atlas construction is how to effectively incorporate both the subject-specific information and population information to build the unbiased atlases. In this paper, a novel groupwise longitudinal atlas construction framework is proposed to address this challenge, and the main contributions of the proposed framework lie in the following aspects: (1) The subject-specific longitudinal information is captured by building the growth model for each subject. (2) The longitudinal atlas sequence is constructed by performing groupwise registration among all the subject image sequences, and only one transformation is needed to transform each subject's image sequence to the atlas space. The constructed longitudinal atlases are unbiased and no explicit template is assumed. (3) The proposed method is general, where the number of longitudinal images of each subject and the time points at which they are taken can be different. The proposed method is extensively evaluated on two longitudinal databases, namely the BLSA and ADNI databases, to construct the longitudinal atlas sequence. It is also compared with a state-of-the-art longitudinal atlas construction algorithm based on kernel regression on the temporal domain. Experimental results demonstrate that the proposed method consistently achieves higher registration accuracies and more consistent spatial-temporal correspondences than the compared method on both databases.

AB - Longitudinal atlas construction plays an important role in medical image analysis. Given a set of longitudinal images from different subjects, the task of longitudinal atlas construction is to build an atlas sequence which can represent the trend of anatomical changes of the population. The major challenge for longitudinal atlas construction is how to effectively incorporate both the subject-specific information and population information to build the unbiased atlases. In this paper, a novel groupwise longitudinal atlas construction framework is proposed to address this challenge, and the main contributions of the proposed framework lie in the following aspects: (1) The subject-specific longitudinal information is captured by building the growth model for each subject. (2) The longitudinal atlas sequence is constructed by performing groupwise registration among all the subject image sequences, and only one transformation is needed to transform each subject's image sequence to the atlas space. The constructed longitudinal atlases are unbiased and no explicit template is assumed. (3) The proposed method is general, where the number of longitudinal images of each subject and the time points at which they are taken can be different. The proposed method is extensively evaluated on two longitudinal databases, namely the BLSA and ADNI databases, to construct the longitudinal atlas sequence. It is also compared with a state-of-the-art longitudinal atlas construction algorithm based on kernel regression on the temporal domain. Experimental results demonstrate that the proposed method consistently achieves higher registration accuracies and more consistent spatial-temporal correspondences than the compared method on both databases.

KW - Groupwise registration

KW - Longitudinal atlas construction

KW - Unbiased atlas

UR - http://www.scopus.com/inward/record.url?scp=83055188093&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=83055188093&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2011.07.095

DO - 10.1016/j.neuroimage.2011.07.095

M3 - Article

C2 - 21884801

AN - SCOPUS:83055188093

VL - 59

SP - 1275

EP - 1289

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 2

ER -