Symmetric deformable image registration via optimization of information theoretic measures

Ali Gholipour, Nasser Kehtarnavaz, Siamak Yousefi, Kaundinya Gopinath, Richard Briggs

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

The use of information theoretic measures (ITMs) has been steadily growing in image processing, bioinformatics, and pattern classification. Although the ITMs have been extensively used in rigid and affine registration of multi-modal images, their computation and accuracy are critical issues in deformable image registration. Three important aspects of using ITMs in multi-modal deformable image registration are considered in this paper: computation, inverse consistency, and accuracy; a symmetric formulation of the deformable image registration problem through the computation of derivatives and resampling on both source and target images, and sufficient criteria for inverse consistency are presented for the purpose of achieving more accurate registration. The techniques of estimating ITMs are examined and analytical derivatives are derived for carrying out the optimization in a computationally efficient manner. ITMs based on Shannon's and Renyi's definitions are considered and compared. The obtained evaluation results via registration functions, and controlled deformable registration of multi-modal digital brain phantom and in vivo magnetic resonance brain images show the improved accuracy and efficiency of the developed formulation. The results also indicate that despite the recent favorable studies towards the use of ITMs based on Renyi's definitions, these measures are seen not to provide improvements in this type of deformable registration as compared to ITMs based on Shannon's definitions.

Original languageEnglish (US)
Pages (from-to)965-975
Number of pages11
JournalImage and Vision Computing
Volume28
Issue number6
DOIs
StatePublished - Jan 1 2010

Fingerprint

Image registration
Brain
Derivatives
Magnetic resonance
Bioinformatics
Pattern recognition
Image processing

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Symmetric deformable image registration via optimization of information theoretic measures. / Gholipour, Ali; Kehtarnavaz, Nasser; Yousefi, Siamak; Gopinath, Kaundinya; Briggs, Richard.

In: Image and Vision Computing, Vol. 28, No. 6, 01.01.2010, p. 965-975.

Research output: Contribution to journalArticle

Gholipour, Ali ; Kehtarnavaz, Nasser ; Yousefi, Siamak ; Gopinath, Kaundinya ; Briggs, Richard. / Symmetric deformable image registration via optimization of information theoretic measures. In: Image and Vision Computing. 2010 ; Vol. 28, No. 6. pp. 965-975.
@article{b9d42411f70d41309b4c842281356329,
title = "Symmetric deformable image registration via optimization of information theoretic measures",
abstract = "The use of information theoretic measures (ITMs) has been steadily growing in image processing, bioinformatics, and pattern classification. Although the ITMs have been extensively used in rigid and affine registration of multi-modal images, their computation and accuracy are critical issues in deformable image registration. Three important aspects of using ITMs in multi-modal deformable image registration are considered in this paper: computation, inverse consistency, and accuracy; a symmetric formulation of the deformable image registration problem through the computation of derivatives and resampling on both source and target images, and sufficient criteria for inverse consistency are presented for the purpose of achieving more accurate registration. The techniques of estimating ITMs are examined and analytical derivatives are derived for carrying out the optimization in a computationally efficient manner. ITMs based on Shannon's and Renyi's definitions are considered and compared. The obtained evaluation results via registration functions, and controlled deformable registration of multi-modal digital brain phantom and in vivo magnetic resonance brain images show the improved accuracy and efficiency of the developed formulation. The results also indicate that despite the recent favorable studies towards the use of ITMs based on Renyi's definitions, these measures are seen not to provide improvements in this type of deformable registration as compared to ITMs based on Shannon's definitions.",
author = "Ali Gholipour and Nasser Kehtarnavaz and Siamak Yousefi and Kaundinya Gopinath and Richard Briggs",
year = "2010",
month = "1",
day = "1",
doi = "10.1016/j.imavis.2009.11.012",
language = "English (US)",
volume = "28",
pages = "965--975",
journal = "Image and Vision Computing",
issn = "0262-8856",
publisher = "Elsevier Limited",
number = "6",

}

TY - JOUR

T1 - Symmetric deformable image registration via optimization of information theoretic measures

AU - Gholipour, Ali

AU - Kehtarnavaz, Nasser

AU - Yousefi, Siamak

AU - Gopinath, Kaundinya

AU - Briggs, Richard

PY - 2010/1/1

Y1 - 2010/1/1

N2 - The use of information theoretic measures (ITMs) has been steadily growing in image processing, bioinformatics, and pattern classification. Although the ITMs have been extensively used in rigid and affine registration of multi-modal images, their computation and accuracy are critical issues in deformable image registration. Three important aspects of using ITMs in multi-modal deformable image registration are considered in this paper: computation, inverse consistency, and accuracy; a symmetric formulation of the deformable image registration problem through the computation of derivatives and resampling on both source and target images, and sufficient criteria for inverse consistency are presented for the purpose of achieving more accurate registration. The techniques of estimating ITMs are examined and analytical derivatives are derived for carrying out the optimization in a computationally efficient manner. ITMs based on Shannon's and Renyi's definitions are considered and compared. The obtained evaluation results via registration functions, and controlled deformable registration of multi-modal digital brain phantom and in vivo magnetic resonance brain images show the improved accuracy and efficiency of the developed formulation. The results also indicate that despite the recent favorable studies towards the use of ITMs based on Renyi's definitions, these measures are seen not to provide improvements in this type of deformable registration as compared to ITMs based on Shannon's definitions.

AB - The use of information theoretic measures (ITMs) has been steadily growing in image processing, bioinformatics, and pattern classification. Although the ITMs have been extensively used in rigid and affine registration of multi-modal images, their computation and accuracy are critical issues in deformable image registration. Three important aspects of using ITMs in multi-modal deformable image registration are considered in this paper: computation, inverse consistency, and accuracy; a symmetric formulation of the deformable image registration problem through the computation of derivatives and resampling on both source and target images, and sufficient criteria for inverse consistency are presented for the purpose of achieving more accurate registration. The techniques of estimating ITMs are examined and analytical derivatives are derived for carrying out the optimization in a computationally efficient manner. ITMs based on Shannon's and Renyi's definitions are considered and compared. The obtained evaluation results via registration functions, and controlled deformable registration of multi-modal digital brain phantom and in vivo magnetic resonance brain images show the improved accuracy and efficiency of the developed formulation. The results also indicate that despite the recent favorable studies towards the use of ITMs based on Renyi's definitions, these measures are seen not to provide improvements in this type of deformable registration as compared to ITMs based on Shannon's definitions.

UR - http://www.scopus.com/inward/record.url?scp=77649337056&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77649337056&partnerID=8YFLogxK

U2 - 10.1016/j.imavis.2009.11.012

DO - 10.1016/j.imavis.2009.11.012

M3 - Article

VL - 28

SP - 965

EP - 975

JO - Image and Vision Computing

JF - Image and Vision Computing

SN - 0262-8856

IS - 6

ER -