F-TIMER: Fast tensor image morphing for elastic registration

Pew Thian Yap, Guorong Wu, Hongtu Zhu, Weili Lin, Dinggang Shen

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

We propose a novel diffusion tensor imaging (DTI) registration algorithm, called fast tensor image morphing for elastic registration (F-TIMER). F-TIMER leverages multiscale tensor regional distributions and local boundaries for hierarchically driving deformable matching of tensor image volumes. Registration is achieved by utilizing a set of automatically determined structural landmarks, via solving a soft correspondence problem. Based on the estimated correspondences, thin-plate splines are employed to generate a smooth, topology preserving, and dense transformation, and to avoid arbitrary mapping of nonlandmark voxels. To mitigate the problem of local minima, which is common in the estimation of high dimensional transformations, we employ a hierarchical strategy where a small subset of voxels with more distinctive attribute vectors are first deployed as landmarks to estimate a relatively robust low-degrees-of-freedom transformation. As the registration progresses, an increasing number of voxels are permitted to participate in refining the correspondence matching. A scheme as such allows less conservative progression of the correspondence matching towards the optimal solution, and hence results in a faster matching speed. Compared with its predecessor TIMER, which has been shown to outperform state-of-the-art algorithms, experimental results indicate that F-TIMER is capable of achieving comparable accuracy at only a fraction of the computation cost.

Original languageEnglish
Article number5433042
Pages (from-to)1192-1203
Number of pages12
JournalIEEE Transactions on Medical Imaging
Volume29
Issue number5
DOIs
Publication statusPublished - 2010 May 1
Externally publishedYes

Fingerprint

Tensors
Diffusion Tensor Imaging
Costs and Cost Analysis
Diffusion tensor imaging
Splines
Refining
Topology
Costs

Keywords

  • Diffusion tensor imaging (DTI)
  • Elastic registration
  • Log-Euclidean manifold
  • Tensor boundaries
  • Tensor regional distributions

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Radiological and Ultrasound Technology
  • Software

Cite this

F-TIMER : Fast tensor image morphing for elastic registration. / Yap, Pew Thian; Wu, Guorong; Zhu, Hongtu; Lin, Weili; Shen, Dinggang.

In: IEEE Transactions on Medical Imaging, Vol. 29, No. 5, 5433042, 01.05.2010, p. 1192-1203.

Research output: Contribution to journalArticle

Yap, Pew Thian ; Wu, Guorong ; Zhu, Hongtu ; Lin, Weili ; Shen, Dinggang. / F-TIMER : Fast tensor image morphing for elastic registration. In: IEEE Transactions on Medical Imaging. 2010 ; Vol. 29, No. 5. pp. 1192-1203.
@article{ee018b7b89ba43ba8d2c4243a448c72f,
title = "F-TIMER: Fast tensor image morphing for elastic registration",
abstract = "We propose a novel diffusion tensor imaging (DTI) registration algorithm, called fast tensor image morphing for elastic registration (F-TIMER). F-TIMER leverages multiscale tensor regional distributions and local boundaries for hierarchically driving deformable matching of tensor image volumes. Registration is achieved by utilizing a set of automatically determined structural landmarks, via solving a soft correspondence problem. Based on the estimated correspondences, thin-plate splines are employed to generate a smooth, topology preserving, and dense transformation, and to avoid arbitrary mapping of nonlandmark voxels. To mitigate the problem of local minima, which is common in the estimation of high dimensional transformations, we employ a hierarchical strategy where a small subset of voxels with more distinctive attribute vectors are first deployed as landmarks to estimate a relatively robust low-degrees-of-freedom transformation. As the registration progresses, an increasing number of voxels are permitted to participate in refining the correspondence matching. A scheme as such allows less conservative progression of the correspondence matching towards the optimal solution, and hence results in a faster matching speed. Compared with its predecessor TIMER, which has been shown to outperform state-of-the-art algorithms, experimental results indicate that F-TIMER is capable of achieving comparable accuracy at only a fraction of the computation cost.",
keywords = "Diffusion tensor imaging (DTI), Elastic registration, Log-Euclidean manifold, Tensor boundaries, Tensor regional distributions",
author = "Yap, {Pew Thian} and Guorong Wu and Hongtu Zhu and Weili Lin and Dinggang Shen",
year = "2010",
month = "5",
day = "1",
doi = "10.1109/TMI.2010.2043680",
language = "English",
volume = "29",
pages = "1192--1203",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

TY - JOUR

T1 - F-TIMER

T2 - Fast tensor image morphing for elastic registration

AU - Yap, Pew Thian

AU - Wu, Guorong

AU - Zhu, Hongtu

AU - Lin, Weili

AU - Shen, Dinggang

PY - 2010/5/1

Y1 - 2010/5/1

N2 - We propose a novel diffusion tensor imaging (DTI) registration algorithm, called fast tensor image morphing for elastic registration (F-TIMER). F-TIMER leverages multiscale tensor regional distributions and local boundaries for hierarchically driving deformable matching of tensor image volumes. Registration is achieved by utilizing a set of automatically determined structural landmarks, via solving a soft correspondence problem. Based on the estimated correspondences, thin-plate splines are employed to generate a smooth, topology preserving, and dense transformation, and to avoid arbitrary mapping of nonlandmark voxels. To mitigate the problem of local minima, which is common in the estimation of high dimensional transformations, we employ a hierarchical strategy where a small subset of voxels with more distinctive attribute vectors are first deployed as landmarks to estimate a relatively robust low-degrees-of-freedom transformation. As the registration progresses, an increasing number of voxels are permitted to participate in refining the correspondence matching. A scheme as such allows less conservative progression of the correspondence matching towards the optimal solution, and hence results in a faster matching speed. Compared with its predecessor TIMER, which has been shown to outperform state-of-the-art algorithms, experimental results indicate that F-TIMER is capable of achieving comparable accuracy at only a fraction of the computation cost.

AB - We propose a novel diffusion tensor imaging (DTI) registration algorithm, called fast tensor image morphing for elastic registration (F-TIMER). F-TIMER leverages multiscale tensor regional distributions and local boundaries for hierarchically driving deformable matching of tensor image volumes. Registration is achieved by utilizing a set of automatically determined structural landmarks, via solving a soft correspondence problem. Based on the estimated correspondences, thin-plate splines are employed to generate a smooth, topology preserving, and dense transformation, and to avoid arbitrary mapping of nonlandmark voxels. To mitigate the problem of local minima, which is common in the estimation of high dimensional transformations, we employ a hierarchical strategy where a small subset of voxels with more distinctive attribute vectors are first deployed as landmarks to estimate a relatively robust low-degrees-of-freedom transformation. As the registration progresses, an increasing number of voxels are permitted to participate in refining the correspondence matching. A scheme as such allows less conservative progression of the correspondence matching towards the optimal solution, and hence results in a faster matching speed. Compared with its predecessor TIMER, which has been shown to outperform state-of-the-art algorithms, experimental results indicate that F-TIMER is capable of achieving comparable accuracy at only a fraction of the computation cost.

KW - Diffusion tensor imaging (DTI)

KW - Elastic registration

KW - Log-Euclidean manifold

KW - Tensor boundaries

KW - Tensor regional distributions

UR - http://www.scopus.com/inward/record.url?scp=77951818972&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951818972&partnerID=8YFLogxK

U2 - 10.1109/TMI.2010.2043680

DO - 10.1109/TMI.2010.2043680

M3 - Article

C2 - 20304728

AN - SCOPUS:77951818972

VL - 29

SP - 1192

EP - 1203

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 5

M1 - 5433042

ER -