Similarity metrics based on nonadditive entropies for 2D-3D multimodal biomedical image registration

Mark P. Wachowiak; Renata Smolíková; Georgia D. Tourassi; Adel S. Elmaghraby

doi:10.1117/12.480867

Similarity metrics based on nonadditive entropies for 2D-3D multimodal biomedical image registration

Mark P. Wachowiak, Renata Smolíková, Georgia D. Tourassi, Adel S. Elmaghraby

Research output: Contribution to journal › Conference article › peer-review

40 Scopus citations

Abstract

Information theoretic similarity metrics, including mutual information, have been widely and successfully employed in multimodal biomedical image registration. These metrics are generally based on the Shannon-Boltzmann-Gibbs definition of entropy. However, other entropy definitions exist, including generalized entropies, which are parameterized by a real number. New similarity metrics can be derived by exploiting the additivity and pseudoadditivity properties of these entropies. In many cases, use of these measures results in an increased percentage of correct registrations. Results suggest that generalized information theoretic similarity metrics, used in conjunction with other measures, including Shannon entropy metrics, can improve registration performance.

Original language	English
Pages (from-to)	1090-1100
Number of pages	11
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	5032 II
DOIs	https://doi.org/10.1117/12.480867
State	Published - 2003
Externally published	Yes
Event	Medical Imaging 2003: Image Processing - San Diego, CA, United States Duration: Feb 17 2003 → Feb 20 2003

Keywords

Image registration
Mutual information
Renyi entropy
Similarity measures
Tsallis entropy

Access to Document

10.1117/12.480867

Cite this

@article{cac2b684e78944859e1c5cbba2ea1411,

title = "Similarity metrics based on nonadditive entropies for 2D-3D multimodal biomedical image registration",

abstract = "Information theoretic similarity metrics, including mutual information, have been widely and successfully employed in multimodal biomedical image registration. These metrics are generally based on the Shannon-Boltzmann-Gibbs definition of entropy. However, other entropy definitions exist, including generalized entropies, which are parameterized by a real number. New similarity metrics can be derived by exploiting the additivity and pseudoadditivity properties of these entropies. In many cases, use of these measures results in an increased percentage of correct registrations. Results suggest that generalized information theoretic similarity metrics, used in conjunction with other measures, including Shannon entropy metrics, can improve registration performance.",

keywords = "Image registration, Mutual information, Renyi entropy, Similarity measures, Tsallis entropy",

author = "Wachowiak, {Mark P.} and Renata Smol{\'i}kov{\'a} and Tourassi, {Georgia D.} and Elmaghraby, {Adel S.}",

year = "2003",

doi = "10.1117/12.480867",

language = "English",

volume = "5032 II",

pages = "1090--1100",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "Society of Photo-Optical Instrumentation Engineers",

note = "Medical Imaging 2003: Image Processing ; Conference date: 17-02-2003 Through 20-02-2003",

}

TY - JOUR

T1 - Similarity metrics based on nonadditive entropies for 2D-3D multimodal biomedical image registration

AU - Wachowiak, Mark P.

AU - Smolíková, Renata

AU - Tourassi, Georgia D.

AU - Elmaghraby, Adel S.

PY - 2003

Y1 - 2003

N2 - Information theoretic similarity metrics, including mutual information, have been widely and successfully employed in multimodal biomedical image registration. These metrics are generally based on the Shannon-Boltzmann-Gibbs definition of entropy. However, other entropy definitions exist, including generalized entropies, which are parameterized by a real number. New similarity metrics can be derived by exploiting the additivity and pseudoadditivity properties of these entropies. In many cases, use of these measures results in an increased percentage of correct registrations. Results suggest that generalized information theoretic similarity metrics, used in conjunction with other measures, including Shannon entropy metrics, can improve registration performance.

AB - Information theoretic similarity metrics, including mutual information, have been widely and successfully employed in multimodal biomedical image registration. These metrics are generally based on the Shannon-Boltzmann-Gibbs definition of entropy. However, other entropy definitions exist, including generalized entropies, which are parameterized by a real number. New similarity metrics can be derived by exploiting the additivity and pseudoadditivity properties of these entropies. In many cases, use of these measures results in an increased percentage of correct registrations. Results suggest that generalized information theoretic similarity metrics, used in conjunction with other measures, including Shannon entropy metrics, can improve registration performance.

KW - Image registration

KW - Mutual information

KW - Renyi entropy

KW - Similarity measures

KW - Tsallis entropy

UR - http://www.scopus.com/inward/record.url?scp=0041373862&partnerID=8YFLogxK

U2 - 10.1117/12.480867

DO - 10.1117/12.480867

M3 - Conference article

AN - SCOPUS:0041373862

SN - 0277-786X

VL - 5032 II

SP - 1090

EP - 1100

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

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

T2 - Medical Imaging 2003: Image Processing

Y2 - 17 February 2003 through 20 February 2003

ER -

Similarity metrics based on nonadditive entropies for 2D-3D multimodal biomedical image registration

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this