Evaluation of search strategies and cost functions in optimizing voxel-based image registration

David R. Holmes III, Jon J. Camp, Richard A. Robb

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

A number of image registration algorithms are currently used to register both intra-modality and inter-modality image data sets. These algorithms, although tested, have not always been optimized or evaluated in relationship to other registration algorithms available. Analysis of registration algorithms is often difficult, due to the fact that the registration components are integrated with each other and cannot be easily isolated form the rest of the algorithm. This study outlines some important features of registration algorithms and describes a method by which these algorithms may be analyzed. This method was used to analyze (1) two cost functions, a normalized standard deviation function and a conditional entropy function, (2) two search strategies, Powell's method and a derivative method, and (3) a number of iterative relaxation/data reduction techniques. These registration components were tested with a number of intra- modal and inter-modal data sets. The cost function analyses suggest that segmentation is necessary for some inter-modal registration problems. Multi-resolution techniques are also discussed with regard to registration effectiveness. A Euclidean distance measure was used to conditional entropy combined with a derivative search strategy may be the most robust approach to image registration, whereas the normalized standard deviation with Powell's search strategy produces the worst results. Generalization and further work are indicate in the discussion.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Place of PublicationBellingham, WA, United States
PublisherSociety of Photo-Optical Instrumentation Engineers
Pages554-562
Number of pages9
Volume3031
ISBN (Print)0819424420
StatePublished - 1997
EventMedical Imaging 1997: Image Display - Newport Beach, CA, USA
Duration: Feb 23 1997Feb 25 1997

Other

OtherMedical Imaging 1997: Image Display
CityNewport Beach, CA, USA
Period2/23/972/25/97

Fingerprint

Image registration
Cost functions
costs
evaluation
standard deviation
Entropy
entropy
Derivatives
data reduction
registers
Data reduction

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Holmes III, D. R., Camp, J. J., & Robb, R. A. (1997). Evaluation of search strategies and cost functions in optimizing voxel-based image registration. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 3031, pp. 554-562). Bellingham, WA, United States: Society of Photo-Optical Instrumentation Engineers.

Evaluation of search strategies and cost functions in optimizing voxel-based image registration. / Holmes III, David R.; Camp, Jon J.; Robb, Richard A.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3031 Bellingham, WA, United States : Society of Photo-Optical Instrumentation Engineers, 1997. p. 554-562.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Holmes III, DR, Camp, JJ & Robb, RA 1997, Evaluation of search strategies and cost functions in optimizing voxel-based image registration. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 3031, Society of Photo-Optical Instrumentation Engineers, Bellingham, WA, United States, pp. 554-562, Medical Imaging 1997: Image Display, Newport Beach, CA, USA, 2/23/97.
Holmes III DR, Camp JJ, Robb RA. Evaluation of search strategies and cost functions in optimizing voxel-based image registration. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3031. Bellingham, WA, United States: Society of Photo-Optical Instrumentation Engineers. 1997. p. 554-562
Holmes III, David R. ; Camp, Jon J. ; Robb, Richard A. / Evaluation of search strategies and cost functions in optimizing voxel-based image registration. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 3031 Bellingham, WA, United States : Society of Photo-Optical Instrumentation Engineers, 1997. pp. 554-562
@inproceedings{c5a4a136297b448bb06794cbeca1bb0b,
title = "Evaluation of search strategies and cost functions in optimizing voxel-based image registration",
abstract = "A number of image registration algorithms are currently used to register both intra-modality and inter-modality image data sets. These algorithms, although tested, have not always been optimized or evaluated in relationship to other registration algorithms available. Analysis of registration algorithms is often difficult, due to the fact that the registration components are integrated with each other and cannot be easily isolated form the rest of the algorithm. This study outlines some important features of registration algorithms and describes a method by which these algorithms may be analyzed. This method was used to analyze (1) two cost functions, a normalized standard deviation function and a conditional entropy function, (2) two search strategies, Powell's method and a derivative method, and (3) a number of iterative relaxation/data reduction techniques. These registration components were tested with a number of intra- modal and inter-modal data sets. The cost function analyses suggest that segmentation is necessary for some inter-modal registration problems. Multi-resolution techniques are also discussed with regard to registration effectiveness. A Euclidean distance measure was used to conditional entropy combined with a derivative search strategy may be the most robust approach to image registration, whereas the normalized standard deviation with Powell's search strategy produces the worst results. Generalization and further work are indicate in the discussion.",
author = "{Holmes III}, {David R.} and Camp, {Jon J.} and Robb, {Richard A.}",
year = "1997",
language = "English (US)",
isbn = "0819424420",
volume = "3031",
pages = "554--562",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "Society of Photo-Optical Instrumentation Engineers",

}

TY - GEN

T1 - Evaluation of search strategies and cost functions in optimizing voxel-based image registration

AU - Holmes III, David R.

AU - Camp, Jon J.

AU - Robb, Richard A.

PY - 1997

Y1 - 1997

N2 - A number of image registration algorithms are currently used to register both intra-modality and inter-modality image data sets. These algorithms, although tested, have not always been optimized or evaluated in relationship to other registration algorithms available. Analysis of registration algorithms is often difficult, due to the fact that the registration components are integrated with each other and cannot be easily isolated form the rest of the algorithm. This study outlines some important features of registration algorithms and describes a method by which these algorithms may be analyzed. This method was used to analyze (1) two cost functions, a normalized standard deviation function and a conditional entropy function, (2) two search strategies, Powell's method and a derivative method, and (3) a number of iterative relaxation/data reduction techniques. These registration components were tested with a number of intra- modal and inter-modal data sets. The cost function analyses suggest that segmentation is necessary for some inter-modal registration problems. Multi-resolution techniques are also discussed with regard to registration effectiveness. A Euclidean distance measure was used to conditional entropy combined with a derivative search strategy may be the most robust approach to image registration, whereas the normalized standard deviation with Powell's search strategy produces the worst results. Generalization and further work are indicate in the discussion.

AB - A number of image registration algorithms are currently used to register both intra-modality and inter-modality image data sets. These algorithms, although tested, have not always been optimized or evaluated in relationship to other registration algorithms available. Analysis of registration algorithms is often difficult, due to the fact that the registration components are integrated with each other and cannot be easily isolated form the rest of the algorithm. This study outlines some important features of registration algorithms and describes a method by which these algorithms may be analyzed. This method was used to analyze (1) two cost functions, a normalized standard deviation function and a conditional entropy function, (2) two search strategies, Powell's method and a derivative method, and (3) a number of iterative relaxation/data reduction techniques. These registration components were tested with a number of intra- modal and inter-modal data sets. The cost function analyses suggest that segmentation is necessary for some inter-modal registration problems. Multi-resolution techniques are also discussed with regard to registration effectiveness. A Euclidean distance measure was used to conditional entropy combined with a derivative search strategy may be the most robust approach to image registration, whereas the normalized standard deviation with Powell's search strategy produces the worst results. Generalization and further work are indicate in the discussion.

UR - http://www.scopus.com/inward/record.url?scp=0031365015&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031365015&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0031365015

SN - 0819424420

VL - 3031

SP - 554

EP - 562

BT - Proceedings of SPIE - The International Society for Optical Engineering

PB - Society of Photo-Optical Instrumentation Engineers

CY - Bellingham, WA, United States

ER -