Image registration by local histogram matching

Research output: Contribution to journalArticle

97 Citations (Scopus)

Abstract

We previously presented an image registration method, referred to hierarchical attribute matching mechanism for elastic registration (HAMMER), which demonstrated relatively high accuracy in inter-subject registration of MR brain images. However, the HAMMER algorithm requires the pre-segmentation of brain tissues, since the attribute vectors used to hierarchically match the corresponding pairs of points are defined from the segmented image. In many applications, the segmentation of tissues might be difficult, unreliable or even impossible to complete, which potentially limits the use of the HAMMER algorithm in more generalized applications. To overcome this limitation, we have used local spatial intensity histograms to design a new type of attribute vector for each point in an intensity image. The histogram-based attribute vector is rotationally invariant, and importantly it also captures spatial information by integrating a number of local intensity histograms from multi-resolution images of original intensity image. The new attribute vectors are able to determine the corresponding points across individual images. Therefore, by hierarchically matching new attribute vectors, the proposed method can perform as successfully as the previous HAMMER algorithm did in registering MR brain images, while providing more generalized applications in registering images of various organs. Experimental results show good performance of the proposed method in registering MR brain images, DTI brain images, CT pelvis images, and MR mouse images.

Original languageEnglish
Pages (from-to)1161-1172
Number of pages12
JournalPattern Recognition
Volume40
Issue number4
DOIs
Publication statusPublished - 2007 Apr 1
Externally publishedYes

Fingerprint

Image registration
Brain
Tissue
Image resolution

Keywords

  • Atlas-based segmentation and labeling
  • Attribute vector
  • Brain atlas
  • Deformable registration
  • Image warping
  • Invariants
  • Non-rigid registration
  • Spatial histogram

ASJC Scopus subject areas

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

Cite this

Image registration by local histogram matching. / Shen, Dinggang.

In: Pattern Recognition, Vol. 40, No. 4, 01.04.2007, p. 1161-1172.

Research output: Contribution to journalArticle

@article{e99e68344ff949b78e89915aa61e492f,
title = "Image registration by local histogram matching",
abstract = "We previously presented an image registration method, referred to hierarchical attribute matching mechanism for elastic registration (HAMMER), which demonstrated relatively high accuracy in inter-subject registration of MR brain images. However, the HAMMER algorithm requires the pre-segmentation of brain tissues, since the attribute vectors used to hierarchically match the corresponding pairs of points are defined from the segmented image. In many applications, the segmentation of tissues might be difficult, unreliable or even impossible to complete, which potentially limits the use of the HAMMER algorithm in more generalized applications. To overcome this limitation, we have used local spatial intensity histograms to design a new type of attribute vector for each point in an intensity image. The histogram-based attribute vector is rotationally invariant, and importantly it also captures spatial information by integrating a number of local intensity histograms from multi-resolution images of original intensity image. The new attribute vectors are able to determine the corresponding points across individual images. Therefore, by hierarchically matching new attribute vectors, the proposed method can perform as successfully as the previous HAMMER algorithm did in registering MR brain images, while providing more generalized applications in registering images of various organs. Experimental results show good performance of the proposed method in registering MR brain images, DTI brain images, CT pelvis images, and MR mouse images.",
keywords = "Atlas-based segmentation and labeling, Attribute vector, Brain atlas, Deformable registration, Image warping, Invariants, Non-rigid registration, Spatial histogram",
author = "Dinggang Shen",
year = "2007",
month = "4",
day = "1",
doi = "10.1016/j.patcog.2006.08.012",
language = "English",
volume = "40",
pages = "1161--1172",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "4",

}

TY - JOUR

T1 - Image registration by local histogram matching

AU - Shen, Dinggang

PY - 2007/4/1

Y1 - 2007/4/1

N2 - We previously presented an image registration method, referred to hierarchical attribute matching mechanism for elastic registration (HAMMER), which demonstrated relatively high accuracy in inter-subject registration of MR brain images. However, the HAMMER algorithm requires the pre-segmentation of brain tissues, since the attribute vectors used to hierarchically match the corresponding pairs of points are defined from the segmented image. In many applications, the segmentation of tissues might be difficult, unreliable or even impossible to complete, which potentially limits the use of the HAMMER algorithm in more generalized applications. To overcome this limitation, we have used local spatial intensity histograms to design a new type of attribute vector for each point in an intensity image. The histogram-based attribute vector is rotationally invariant, and importantly it also captures spatial information by integrating a number of local intensity histograms from multi-resolution images of original intensity image. The new attribute vectors are able to determine the corresponding points across individual images. Therefore, by hierarchically matching new attribute vectors, the proposed method can perform as successfully as the previous HAMMER algorithm did in registering MR brain images, while providing more generalized applications in registering images of various organs. Experimental results show good performance of the proposed method in registering MR brain images, DTI brain images, CT pelvis images, and MR mouse images.

AB - We previously presented an image registration method, referred to hierarchical attribute matching mechanism for elastic registration (HAMMER), which demonstrated relatively high accuracy in inter-subject registration of MR brain images. However, the HAMMER algorithm requires the pre-segmentation of brain tissues, since the attribute vectors used to hierarchically match the corresponding pairs of points are defined from the segmented image. In many applications, the segmentation of tissues might be difficult, unreliable or even impossible to complete, which potentially limits the use of the HAMMER algorithm in more generalized applications. To overcome this limitation, we have used local spatial intensity histograms to design a new type of attribute vector for each point in an intensity image. The histogram-based attribute vector is rotationally invariant, and importantly it also captures spatial information by integrating a number of local intensity histograms from multi-resolution images of original intensity image. The new attribute vectors are able to determine the corresponding points across individual images. Therefore, by hierarchically matching new attribute vectors, the proposed method can perform as successfully as the previous HAMMER algorithm did in registering MR brain images, while providing more generalized applications in registering images of various organs. Experimental results show good performance of the proposed method in registering MR brain images, DTI brain images, CT pelvis images, and MR mouse images.

KW - Atlas-based segmentation and labeling

KW - Attribute vector

KW - Brain atlas

KW - Deformable registration

KW - Image warping

KW - Invariants

KW - Non-rigid registration

KW - Spatial histogram

UR - http://www.scopus.com/inward/record.url?scp=33845418366&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845418366&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2006.08.012

DO - 10.1016/j.patcog.2006.08.012

M3 - Article

AN - SCOPUS:33845418366

VL - 40

SP - 1161

EP - 1172

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 4

ER -