Hierarchical unbiased graph shrinkage (HUGS): A novel groupwise registration for large data set

Shihui Ying, Guorong Wu, Qian Wang, Dinggang Shen

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

Normalizing all images in a large data set into a common space is a key step in many clinical and research studies, e.g., for brain development, maturation, and aging. Recently, groupwise registration has been developed for simultaneous alignment of all images without selecting a particular image as template, thus potentially avoiding bias in the registration. However, most conventional groupwise registration methods do not explore the data distribution during the image registration. Thus, their performance could be affected by large inter-subject variations in the data set under registration. To solve this potential issue, we propose to use a graph to model the distribution of all image data sitting on the image manifold, with each node representing an image and each edge representing the geodesic pathway between two nodes (or images). Then, the procedure of warping all images to their population center turns to the dynamic shrinking of the graph nodes along their graph edges until all graph nodes become close to each other. Thus, the topology of image distribution on the image manifold is always preserved during the groupwise registration. More importantly, by modeling the distribution of all images via a graph, we can potentially reduce registration error since every time each image is warped only according to its nearby images with similar structures in the graph. We have evaluated our proposed groupwise registration method on both infant and adult data sets, by also comparing with the conventional group-mean based registration and the ABSORB methods. All experimental results show that our proposed method can achieve better performance in terms of registration accuracy and robustness.

Original languageEnglish
Pages (from-to)626-638
Number of pages13
JournalNeuroImage
Volume84
DOIs
Publication statusPublished - 2014 Jan 1
Externally publishedYes

Fingerprint

Datasets
Brain
Research
Population
Clinical Studies

Keywords

  • Diffeomorphism
  • Graph shrinking
  • Image manifold
  • Unbiased groupwise registration

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

Hierarchical unbiased graph shrinkage (HUGS) : A novel groupwise registration for large data set. / Ying, Shihui; Wu, Guorong; Wang, Qian; Shen, Dinggang.

In: NeuroImage, Vol. 84, 01.01.2014, p. 626-638.

Research output: Contribution to journalArticle

@article{a665790d33f94f03bf0dcd02b75bb53c,
title = "Hierarchical unbiased graph shrinkage (HUGS): A novel groupwise registration for large data set",
abstract = "Normalizing all images in a large data set into a common space is a key step in many clinical and research studies, e.g., for brain development, maturation, and aging. Recently, groupwise registration has been developed for simultaneous alignment of all images without selecting a particular image as template, thus potentially avoiding bias in the registration. However, most conventional groupwise registration methods do not explore the data distribution during the image registration. Thus, their performance could be affected by large inter-subject variations in the data set under registration. To solve this potential issue, we propose to use a graph to model the distribution of all image data sitting on the image manifold, with each node representing an image and each edge representing the geodesic pathway between two nodes (or images). Then, the procedure of warping all images to their population center turns to the dynamic shrinking of the graph nodes along their graph edges until all graph nodes become close to each other. Thus, the topology of image distribution on the image manifold is always preserved during the groupwise registration. More importantly, by modeling the distribution of all images via a graph, we can potentially reduce registration error since every time each image is warped only according to its nearby images with similar structures in the graph. We have evaluated our proposed groupwise registration method on both infant and adult data sets, by also comparing with the conventional group-mean based registration and the ABSORB methods. All experimental results show that our proposed method can achieve better performance in terms of registration accuracy and robustness.",
keywords = "Diffeomorphism, Graph shrinking, Image manifold, Unbiased groupwise registration",
author = "Shihui Ying and Guorong Wu and Qian Wang and Dinggang Shen",
year = "2014",
month = "1",
day = "1",
doi = "10.1016/j.neuroimage.2013.09.023",
language = "English",
volume = "84",
pages = "626--638",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Hierarchical unbiased graph shrinkage (HUGS)

T2 - A novel groupwise registration for large data set

AU - Ying, Shihui

AU - Wu, Guorong

AU - Wang, Qian

AU - Shen, Dinggang

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Normalizing all images in a large data set into a common space is a key step in many clinical and research studies, e.g., for brain development, maturation, and aging. Recently, groupwise registration has been developed for simultaneous alignment of all images without selecting a particular image as template, thus potentially avoiding bias in the registration. However, most conventional groupwise registration methods do not explore the data distribution during the image registration. Thus, their performance could be affected by large inter-subject variations in the data set under registration. To solve this potential issue, we propose to use a graph to model the distribution of all image data sitting on the image manifold, with each node representing an image and each edge representing the geodesic pathway between two nodes (or images). Then, the procedure of warping all images to their population center turns to the dynamic shrinking of the graph nodes along their graph edges until all graph nodes become close to each other. Thus, the topology of image distribution on the image manifold is always preserved during the groupwise registration. More importantly, by modeling the distribution of all images via a graph, we can potentially reduce registration error since every time each image is warped only according to its nearby images with similar structures in the graph. We have evaluated our proposed groupwise registration method on both infant and adult data sets, by also comparing with the conventional group-mean based registration and the ABSORB methods. All experimental results show that our proposed method can achieve better performance in terms of registration accuracy and robustness.

AB - Normalizing all images in a large data set into a common space is a key step in many clinical and research studies, e.g., for brain development, maturation, and aging. Recently, groupwise registration has been developed for simultaneous alignment of all images without selecting a particular image as template, thus potentially avoiding bias in the registration. However, most conventional groupwise registration methods do not explore the data distribution during the image registration. Thus, their performance could be affected by large inter-subject variations in the data set under registration. To solve this potential issue, we propose to use a graph to model the distribution of all image data sitting on the image manifold, with each node representing an image and each edge representing the geodesic pathway between two nodes (or images). Then, the procedure of warping all images to their population center turns to the dynamic shrinking of the graph nodes along their graph edges until all graph nodes become close to each other. Thus, the topology of image distribution on the image manifold is always preserved during the groupwise registration. More importantly, by modeling the distribution of all images via a graph, we can potentially reduce registration error since every time each image is warped only according to its nearby images with similar structures in the graph. We have evaluated our proposed groupwise registration method on both infant and adult data sets, by also comparing with the conventional group-mean based registration and the ABSORB methods. All experimental results show that our proposed method can achieve better performance in terms of registration accuracy and robustness.

KW - Diffeomorphism

KW - Graph shrinking

KW - Image manifold

KW - Unbiased groupwise registration

UR - http://www.scopus.com/inward/record.url?scp=84885123535&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885123535&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2013.09.023

DO - 10.1016/j.neuroimage.2013.09.023

M3 - Article

C2 - 24055505

AN - SCOPUS:84885123535

VL - 84

SP - 626

EP - 638

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -