EHUGS: Enhanced hierarchical unbiased graph shrinkage for efficient groupwise registration

Guorong Wu, Xuewei Peng, Shihui Ying, Qian Wang, Pew Thian Yap, Dan Shen, Dinggang Shen

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Effective and efficient spatial normalization of a large population of brain images is critical for many clinical and research studies, but it is technically very challenging. A commonly used approach is to choose a certain image as the template and then align all other images in the population to this template by applying pairwise registration. To avoid the potential bias induced by the inappropriate template selection, groupwise registration methods have been proposed to simultaneously register all images to a latent common space. However, current groupwise registration methods do not make full use of image distribution information for more accurate registration. In this paper, we present a novel groupwise registration method that harnesses the image distribution information by capturing the image distribution manifold using a hierarchical graph with its nodes representing the individual images. More specifically, a low-level graph describes the image distribution in each subgroup, and a high-level graph encodes the relationship between representative images of subgroups. Given the graph representation, we can register all images to the common space by dynamically shrinking the graph on the image manifold. The topology of the entire image distribution is always maintained during graph shrinkage. Evaluations on two datasets, one for 80 elderly individuals and one for 285 infants, indicate that our method can yield promising results.

Original languageEnglish
Article numbere0146870
JournalPLoS One
Volume11
Issue number1
DOIs
Publication statusPublished - 2016 Jan 1

Fingerprint

shrinkage
Information Dissemination
Brain
Topology
harness
methodology
topology
Population
brain
Research

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

EHUGS : Enhanced hierarchical unbiased graph shrinkage for efficient groupwise registration. / Wu, Guorong; Peng, Xuewei; Ying, Shihui; Wang, Qian; Yap, Pew Thian; Shen, Dan; Shen, Dinggang.

In: PLoS One, Vol. 11, No. 1, e0146870, 01.01.2016.

Research output: Contribution to journalArticle

Wu, Guorong ; Peng, Xuewei ; Ying, Shihui ; Wang, Qian ; Yap, Pew Thian ; Shen, Dan ; Shen, Dinggang. / EHUGS : Enhanced hierarchical unbiased graph shrinkage for efficient groupwise registration. In: PLoS One. 2016 ; Vol. 11, No. 1.
@article{ea5e393dafc94f1d90fe2b2aab60e1ec,
title = "EHUGS: Enhanced hierarchical unbiased graph shrinkage for efficient groupwise registration",
abstract = "Effective and efficient spatial normalization of a large population of brain images is critical for many clinical and research studies, but it is technically very challenging. A commonly used approach is to choose a certain image as the template and then align all other images in the population to this template by applying pairwise registration. To avoid the potential bias induced by the inappropriate template selection, groupwise registration methods have been proposed to simultaneously register all images to a latent common space. However, current groupwise registration methods do not make full use of image distribution information for more accurate registration. In this paper, we present a novel groupwise registration method that harnesses the image distribution information by capturing the image distribution manifold using a hierarchical graph with its nodes representing the individual images. More specifically, a low-level graph describes the image distribution in each subgroup, and a high-level graph encodes the relationship between representative images of subgroups. Given the graph representation, we can register all images to the common space by dynamically shrinking the graph on the image manifold. The topology of the entire image distribution is always maintained during graph shrinkage. Evaluations on two datasets, one for 80 elderly individuals and one for 285 infants, indicate that our method can yield promising results.",
author = "Guorong Wu and Xuewei Peng and Shihui Ying and Qian Wang and Yap, {Pew Thian} and Dan Shen and Dinggang Shen",
year = "2016",
month = "1",
day = "1",
doi = "10.1371/journal.pone.0146870",
language = "English",
volume = "11",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "1",

}

TY - JOUR

T1 - EHUGS

T2 - Enhanced hierarchical unbiased graph shrinkage for efficient groupwise registration

AU - Wu, Guorong

AU - Peng, Xuewei

AU - Ying, Shihui

AU - Wang, Qian

AU - Yap, Pew Thian

AU - Shen, Dan

AU - Shen, Dinggang

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Effective and efficient spatial normalization of a large population of brain images is critical for many clinical and research studies, but it is technically very challenging. A commonly used approach is to choose a certain image as the template and then align all other images in the population to this template by applying pairwise registration. To avoid the potential bias induced by the inappropriate template selection, groupwise registration methods have been proposed to simultaneously register all images to a latent common space. However, current groupwise registration methods do not make full use of image distribution information for more accurate registration. In this paper, we present a novel groupwise registration method that harnesses the image distribution information by capturing the image distribution manifold using a hierarchical graph with its nodes representing the individual images. More specifically, a low-level graph describes the image distribution in each subgroup, and a high-level graph encodes the relationship between representative images of subgroups. Given the graph representation, we can register all images to the common space by dynamically shrinking the graph on the image manifold. The topology of the entire image distribution is always maintained during graph shrinkage. Evaluations on two datasets, one for 80 elderly individuals and one for 285 infants, indicate that our method can yield promising results.

AB - Effective and efficient spatial normalization of a large population of brain images is critical for many clinical and research studies, but it is technically very challenging. A commonly used approach is to choose a certain image as the template and then align all other images in the population to this template by applying pairwise registration. To avoid the potential bias induced by the inappropriate template selection, groupwise registration methods have been proposed to simultaneously register all images to a latent common space. However, current groupwise registration methods do not make full use of image distribution information for more accurate registration. In this paper, we present a novel groupwise registration method that harnesses the image distribution information by capturing the image distribution manifold using a hierarchical graph with its nodes representing the individual images. More specifically, a low-level graph describes the image distribution in each subgroup, and a high-level graph encodes the relationship between representative images of subgroups. Given the graph representation, we can register all images to the common space by dynamically shrinking the graph on the image manifold. The topology of the entire image distribution is always maintained during graph shrinkage. Evaluations on two datasets, one for 80 elderly individuals and one for 285 infants, indicate that our method can yield promising results.

UR - http://www.scopus.com/inward/record.url?scp=84958225748&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958225748&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0146870

DO - 10.1371/journal.pone.0146870

M3 - Article

C2 - 26800361

AN - SCOPUS:84958225748

VL - 11

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 1

M1 - e0146870

ER -