Adaptive grid generation based non-rigid image registration using mutual information for breast MRI

Mei Yi Chu, Hua Mei Chen, Chih Yao Hsieh, Ting Hung Lin, Hsi Yue Hsiao, Guojun Liao, Qi Peng

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In this paper a new approach for non-rigid image registration using mutual information is introduced. A fast parametric method for non-rigid registration is developed by adjusting divergence and curl of an intermediate vector field from which the deformation field is computed using finite-central difference method. Mutual information is newly employed as the similarity measure in the gradient-based cost minimization (or mutual information maximization) of the existing registration framework. The huge amount of data associated with MRI is handled by a fully automated multi-resolution scheme. The adaptive grid system naturally distributes more grids to deprived areas. The positive monitor function disallows grid folding and provides a mean to control the ratio of the areas between the original and transformed domain. The flexibility of the adaptive grid allocation could dramatically reduce processing time with quality preserved. Mutual information facilitates robust registration between different image modalities. Different types of joint histogram estimation are compared and integrated with the system. This scheme is applied on dynamic contrast-enhanced breast MRI, which requires the registration algorithm to be non-rigid, contrast-enhanced features preserving. Preliminary experiments show promising results and great potential for future extension.

Original languageEnglish (US)
Pages (from-to)45-63
Number of pages19
JournalJournal of Signal Processing Systems
Volume54
Issue number1-3
DOIs
StatePublished - Jan 2009
Externally publishedYes

Fingerprint

Non-rigid Registration
Grid Generation
Adaptive Grid
Image registration
Image Registration
Mutual Information
Magnetic resonance imaging
Registration
Grid
Curl
Processing
Folding
Multiresolution
Similarity Measure
Modality
Histogram
Difference Method
Costs
Vector Field
Divergence

Keywords

  • Breast MRI
  • Gradient of Mutual Information
  • Multi-resolution
  • Mutual information
  • Non-rigid registration

ASJC Scopus subject areas

  • Hardware and Architecture
  • Information Systems
  • Signal Processing
  • Theoretical Computer Science
  • Control and Systems Engineering
  • Modeling and Simulation

Cite this

Adaptive grid generation based non-rigid image registration using mutual information for breast MRI. / Chu, Mei Yi; Chen, Hua Mei; Hsieh, Chih Yao; Lin, Ting Hung; Hsiao, Hsi Yue; Liao, Guojun; Peng, Qi.

In: Journal of Signal Processing Systems, Vol. 54, No. 1-3, 01.2009, p. 45-63.

Research output: Contribution to journalArticle

Chu, Mei Yi ; Chen, Hua Mei ; Hsieh, Chih Yao ; Lin, Ting Hung ; Hsiao, Hsi Yue ; Liao, Guojun ; Peng, Qi. / Adaptive grid generation based non-rigid image registration using mutual information for breast MRI. In: Journal of Signal Processing Systems. 2009 ; Vol. 54, No. 1-3. pp. 45-63.
@article{c8e986677b5c4d21a71665633192ac67,
title = "Adaptive grid generation based non-rigid image registration using mutual information for breast MRI",
abstract = "In this paper a new approach for non-rigid image registration using mutual information is introduced. A fast parametric method for non-rigid registration is developed by adjusting divergence and curl of an intermediate vector field from which the deformation field is computed using finite-central difference method. Mutual information is newly employed as the similarity measure in the gradient-based cost minimization (or mutual information maximization) of the existing registration framework. The huge amount of data associated with MRI is handled by a fully automated multi-resolution scheme. The adaptive grid system naturally distributes more grids to deprived areas. The positive monitor function disallows grid folding and provides a mean to control the ratio of the areas between the original and transformed domain. The flexibility of the adaptive grid allocation could dramatically reduce processing time with quality preserved. Mutual information facilitates robust registration between different image modalities. Different types of joint histogram estimation are compared and integrated with the system. This scheme is applied on dynamic contrast-enhanced breast MRI, which requires the registration algorithm to be non-rigid, contrast-enhanced features preserving. Preliminary experiments show promising results and great potential for future extension.",
keywords = "Breast MRI, Gradient of Mutual Information, Multi-resolution, Mutual information, Non-rigid registration",
author = "Chu, {Mei Yi} and Chen, {Hua Mei} and Hsieh, {Chih Yao} and Lin, {Ting Hung} and Hsiao, {Hsi Yue} and Guojun Liao and Qi Peng",
year = "2009",
month = "1",
doi = "10.1007/s11265-008-0193-7",
language = "English (US)",
volume = "54",
pages = "45--63",
journal = "Journal of Signal Processing Systems",
issn = "1939-8018",
publisher = "Springer New York",
number = "1-3",

}

TY - JOUR

T1 - Adaptive grid generation based non-rigid image registration using mutual information for breast MRI

AU - Chu, Mei Yi

AU - Chen, Hua Mei

AU - Hsieh, Chih Yao

AU - Lin, Ting Hung

AU - Hsiao, Hsi Yue

AU - Liao, Guojun

AU - Peng, Qi

PY - 2009/1

Y1 - 2009/1

N2 - In this paper a new approach for non-rigid image registration using mutual information is introduced. A fast parametric method for non-rigid registration is developed by adjusting divergence and curl of an intermediate vector field from which the deformation field is computed using finite-central difference method. Mutual information is newly employed as the similarity measure in the gradient-based cost minimization (or mutual information maximization) of the existing registration framework. The huge amount of data associated with MRI is handled by a fully automated multi-resolution scheme. The adaptive grid system naturally distributes more grids to deprived areas. The positive monitor function disallows grid folding and provides a mean to control the ratio of the areas between the original and transformed domain. The flexibility of the adaptive grid allocation could dramatically reduce processing time with quality preserved. Mutual information facilitates robust registration between different image modalities. Different types of joint histogram estimation are compared and integrated with the system. This scheme is applied on dynamic contrast-enhanced breast MRI, which requires the registration algorithm to be non-rigid, contrast-enhanced features preserving. Preliminary experiments show promising results and great potential for future extension.

AB - In this paper a new approach for non-rigid image registration using mutual information is introduced. A fast parametric method for non-rigid registration is developed by adjusting divergence and curl of an intermediate vector field from which the deformation field is computed using finite-central difference method. Mutual information is newly employed as the similarity measure in the gradient-based cost minimization (or mutual information maximization) of the existing registration framework. The huge amount of data associated with MRI is handled by a fully automated multi-resolution scheme. The adaptive grid system naturally distributes more grids to deprived areas. The positive monitor function disallows grid folding and provides a mean to control the ratio of the areas between the original and transformed domain. The flexibility of the adaptive grid allocation could dramatically reduce processing time with quality preserved. Mutual information facilitates robust registration between different image modalities. Different types of joint histogram estimation are compared and integrated with the system. This scheme is applied on dynamic contrast-enhanced breast MRI, which requires the registration algorithm to be non-rigid, contrast-enhanced features preserving. Preliminary experiments show promising results and great potential for future extension.

KW - Breast MRI

KW - Gradient of Mutual Information

KW - Multi-resolution

KW - Mutual information

KW - Non-rigid registration

UR - http://www.scopus.com/inward/record.url?scp=58149267717&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58149267717&partnerID=8YFLogxK

U2 - 10.1007/s11265-008-0193-7

DO - 10.1007/s11265-008-0193-7

M3 - Article

AN - SCOPUS:58149267717

VL - 54

SP - 45

EP - 63

JO - Journal of Signal Processing Systems

JF - Journal of Signal Processing Systems

SN - 1939-8018

IS - 1-3

ER -