Evaluating similarity measures for brain image registration

Q. R. Razlighi, N. Kehtarnavaz, Siamak Yousefi

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Evaluation of similarity measures for image registration is a challenging problem due to its complex interaction with the underlying optimization, regularization, image type and modality. We propose a single performance metric, named robustness, as part of a new evaluation method which quantifies the effectiveness of similarity measures for brain image registration while eliminating the effects of the other parts of the registration process. We show empirically that similarity measures with higher robustness are more effective in registering degraded images and are also more successful in performing intermodal image registration. Further, we introduce a new similarity measure, called normalized spatial mutual information, for 3D brain image registration whose robustness is shown to be much higher than the existing ones. Consequently, it tolerates greater image degradation and provides more consistent outcomes for intermodal brain image registration.

Original languageEnglish (US)
Pages (from-to)977-987
Number of pages11
JournalJournal of Visual Communication and Image Representation
Volume24
Issue number7
DOIs
StatePublished - Jul 19 2013

Fingerprint

Image registration
Brain
Degradation

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Media Technology
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Evaluating similarity measures for brain image registration. / Razlighi, Q. R.; Kehtarnavaz, N.; Yousefi, Siamak.

In: Journal of Visual Communication and Image Representation, Vol. 24, No. 7, 19.07.2013, p. 977-987.

Research output: Contribution to journalArticle

@article{9a41b9070a484098a9a171c5cecf447d,
title = "Evaluating similarity measures for brain image registration",
abstract = "Evaluation of similarity measures for image registration is a challenging problem due to its complex interaction with the underlying optimization, regularization, image type and modality. We propose a single performance metric, named robustness, as part of a new evaluation method which quantifies the effectiveness of similarity measures for brain image registration while eliminating the effects of the other parts of the registration process. We show empirically that similarity measures with higher robustness are more effective in registering degraded images and are also more successful in performing intermodal image registration. Further, we introduce a new similarity measure, called normalized spatial mutual information, for 3D brain image registration whose robustness is shown to be much higher than the existing ones. Consequently, it tolerates greater image degradation and provides more consistent outcomes for intermodal brain image registration.",
author = "Razlighi, {Q. R.} and N. Kehtarnavaz and Siamak Yousefi",
year = "2013",
month = "7",
day = "19",
doi = "10.1016/j.jvcir.2013.06.010",
language = "English (US)",
volume = "24",
pages = "977--987",
journal = "Journal of Visual Communication and Image Representation",
issn = "1047-3203",
publisher = "Academic Press Inc.",
number = "7",

}

TY - JOUR

T1 - Evaluating similarity measures for brain image registration

AU - Razlighi, Q. R.

AU - Kehtarnavaz, N.

AU - Yousefi, Siamak

PY - 2013/7/19

Y1 - 2013/7/19

N2 - Evaluation of similarity measures for image registration is a challenging problem due to its complex interaction with the underlying optimization, regularization, image type and modality. We propose a single performance metric, named robustness, as part of a new evaluation method which quantifies the effectiveness of similarity measures for brain image registration while eliminating the effects of the other parts of the registration process. We show empirically that similarity measures with higher robustness are more effective in registering degraded images and are also more successful in performing intermodal image registration. Further, we introduce a new similarity measure, called normalized spatial mutual information, for 3D brain image registration whose robustness is shown to be much higher than the existing ones. Consequently, it tolerates greater image degradation and provides more consistent outcomes for intermodal brain image registration.

AB - Evaluation of similarity measures for image registration is a challenging problem due to its complex interaction with the underlying optimization, regularization, image type and modality. We propose a single performance metric, named robustness, as part of a new evaluation method which quantifies the effectiveness of similarity measures for brain image registration while eliminating the effects of the other parts of the registration process. We show empirically that similarity measures with higher robustness are more effective in registering degraded images and are also more successful in performing intermodal image registration. Further, we introduce a new similarity measure, called normalized spatial mutual information, for 3D brain image registration whose robustness is shown to be much higher than the existing ones. Consequently, it tolerates greater image degradation and provides more consistent outcomes for intermodal brain image registration.

UR - http://www.scopus.com/inward/record.url?scp=84880146669&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880146669&partnerID=8YFLogxK

U2 - 10.1016/j.jvcir.2013.06.010

DO - 10.1016/j.jvcir.2013.06.010

M3 - Article

AN - SCOPUS:84880146669

VL - 24

SP - 977

EP - 987

JO - Journal of Visual Communication and Image Representation

JF - Journal of Visual Communication and Image Representation

SN - 1047-3203

IS - 7

ER -