Techniques for mutual information-based brain image registration and their applications

Hua Mei Chen, Pramod Kumar Varshney

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Mutual information is a powerful similarity measure assuming no specific relationship between the intensities of corresponding points. It has been shown that for many applications, by maximizing the mutual information, two images can be aligned with high precision. To utilize mutual information as a similarity measure for image registration, the joint histogram of two images must be estimated. Under certain conditions, existing joint histogram estimation methods result in a phenomenon known as interpolation induced artifacts that hamper the subsequent optimization process and may deteriorate registration accuracy. In this chapter, we discuss this phenomenon in detail and review some plausible solutions to reduce this phenomenon. In addition, a robust global optimization scheme is introduced in this chapter to optimize the mutual information similarity measure between two images. The core of this scheme lies in a heuristic global optimum test algorithm to distinguish the global optimum of the mutual information registration function from the numerous local ones. Finally, the effectiveness of the techniques covered in this chapter is demonstrated by two clinical examples including 3D brain image registration using the data provided by Vanderbilt University and cryosection image registration using the Visible Human Project data sets from the National Library of Medicine.

Original languageEnglish (US)
Title of host publicationMedical Imaging Systems Technology: Analysis and Computational Methods
PublisherWorld Scientific Publishing Co.
Pages325-350
Number of pages26
ISBN (Print)9789812705785, 9812563644, 9789812569936
DOIs
StatePublished - Jan 1 2005

Fingerprint

Visible Human Projects
Joints
National Library of Medicine (U.S.)
Brain
Artifacts
Heuristics
Datasets

Keywords

  • Brain image registration
  • Cryosection image registration
  • Image registration
  • Interpolation induced artifacts
  • Mutual information
  • Visible human project data

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Chen, H. M., & Varshney, P. K. (2005). Techniques for mutual information-based brain image registration and their applications. In Medical Imaging Systems Technology: Analysis and Computational Methods (pp. 325-350). World Scientific Publishing Co.. https://doi.org/10.1142/9789812705785_0010

Techniques for mutual information-based brain image registration and their applications. / Chen, Hua Mei; Varshney, Pramod Kumar.

Medical Imaging Systems Technology: Analysis and Computational Methods. World Scientific Publishing Co., 2005. p. 325-350.

Research output: Chapter in Book/Report/Conference proceedingChapter

Chen, HM & Varshney, PK 2005, Techniques for mutual information-based brain image registration and their applications. in Medical Imaging Systems Technology: Analysis and Computational Methods. World Scientific Publishing Co., pp. 325-350. https://doi.org/10.1142/9789812705785_0010
Chen HM, Varshney PK. Techniques for mutual information-based brain image registration and their applications. In Medical Imaging Systems Technology: Analysis and Computational Methods. World Scientific Publishing Co. 2005. p. 325-350 https://doi.org/10.1142/9789812705785_0010
Chen, Hua Mei ; Varshney, Pramod Kumar. / Techniques for mutual information-based brain image registration and their applications. Medical Imaging Systems Technology: Analysis and Computational Methods. World Scientific Publishing Co., 2005. pp. 325-350
@inbook{52dddeb708a647baa9e357d97df7157f,
title = "Techniques for mutual information-based brain image registration and their applications",
abstract = "Mutual information is a powerful similarity measure assuming no specific relationship between the intensities of corresponding points. It has been shown that for many applications, by maximizing the mutual information, two images can be aligned with high precision. To utilize mutual information as a similarity measure for image registration, the joint histogram of two images must be estimated. Under certain conditions, existing joint histogram estimation methods result in a phenomenon known as interpolation induced artifacts that hamper the subsequent optimization process and may deteriorate registration accuracy. In this chapter, we discuss this phenomenon in detail and review some plausible solutions to reduce this phenomenon. In addition, a robust global optimization scheme is introduced in this chapter to optimize the mutual information similarity measure between two images. The core of this scheme lies in a heuristic global optimum test algorithm to distinguish the global optimum of the mutual information registration function from the numerous local ones. Finally, the effectiveness of the techniques covered in this chapter is demonstrated by two clinical examples including 3D brain image registration using the data provided by Vanderbilt University and cryosection image registration using the Visible Human Project data sets from the National Library of Medicine.",
keywords = "Brain image registration, Cryosection image registration, Image registration, Interpolation induced artifacts, Mutual information, Visible human project data",
author = "Chen, {Hua Mei} and Varshney, {Pramod Kumar}",
year = "2005",
month = "1",
day = "1",
doi = "10.1142/9789812705785_0010",
language = "English (US)",
isbn = "9789812705785",
pages = "325--350",
booktitle = "Medical Imaging Systems Technology: Analysis and Computational Methods",
publisher = "World Scientific Publishing Co.",

}

TY - CHAP

T1 - Techniques for mutual information-based brain image registration and their applications

AU - Chen, Hua Mei

AU - Varshney, Pramod Kumar

PY - 2005/1/1

Y1 - 2005/1/1

N2 - Mutual information is a powerful similarity measure assuming no specific relationship between the intensities of corresponding points. It has been shown that for many applications, by maximizing the mutual information, two images can be aligned with high precision. To utilize mutual information as a similarity measure for image registration, the joint histogram of two images must be estimated. Under certain conditions, existing joint histogram estimation methods result in a phenomenon known as interpolation induced artifacts that hamper the subsequent optimization process and may deteriorate registration accuracy. In this chapter, we discuss this phenomenon in detail and review some plausible solutions to reduce this phenomenon. In addition, a robust global optimization scheme is introduced in this chapter to optimize the mutual information similarity measure between two images. The core of this scheme lies in a heuristic global optimum test algorithm to distinguish the global optimum of the mutual information registration function from the numerous local ones. Finally, the effectiveness of the techniques covered in this chapter is demonstrated by two clinical examples including 3D brain image registration using the data provided by Vanderbilt University and cryosection image registration using the Visible Human Project data sets from the National Library of Medicine.

AB - Mutual information is a powerful similarity measure assuming no specific relationship between the intensities of corresponding points. It has been shown that for many applications, by maximizing the mutual information, two images can be aligned with high precision. To utilize mutual information as a similarity measure for image registration, the joint histogram of two images must be estimated. Under certain conditions, existing joint histogram estimation methods result in a phenomenon known as interpolation induced artifacts that hamper the subsequent optimization process and may deteriorate registration accuracy. In this chapter, we discuss this phenomenon in detail and review some plausible solutions to reduce this phenomenon. In addition, a robust global optimization scheme is introduced in this chapter to optimize the mutual information similarity measure between two images. The core of this scheme lies in a heuristic global optimum test algorithm to distinguish the global optimum of the mutual information registration function from the numerous local ones. Finally, the effectiveness of the techniques covered in this chapter is demonstrated by two clinical examples including 3D brain image registration using the data provided by Vanderbilt University and cryosection image registration using the Visible Human Project data sets from the National Library of Medicine.

KW - Brain image registration

KW - Cryosection image registration

KW - Image registration

KW - Interpolation induced artifacts

KW - Mutual information

KW - Visible human project data

UR - http://www.scopus.com/inward/record.url?scp=84967546574&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84967546574&partnerID=8YFLogxK

U2 - 10.1142/9789812705785_0010

DO - 10.1142/9789812705785_0010

M3 - Chapter

SN - 9789812705785

SN - 9812563644

SN - 9789812569936

SP - 325

EP - 350

BT - Medical Imaging Systems Technology: Analysis and Computational Methods

PB - World Scientific Publishing Co.

ER -