Image registration by hierarchical matching of local spatial intensity histograms

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

10 Citations (Scopus)

Abstract

We previously presented a HAMMER image registration algorithm that demonstrated high accuracy in superposition of images from different individual brains. However, the HAMMER registration algorithm requires presegmentation of brain tissues, since the attribute vectors used to hierarchically match the corresponding pairs of points are defined from the segmented images. 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 use 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 more importantly it captures spatial information by integrating a number of local histograms that are calculated from multi-resolution images. The new attribute vectors are able to determine corresponding points across individual images. Therefore, by hierarchically matching new attribute vectors, the proposed registration method performs as successfully as the previous HAMMER algorithm did in registering MR brain images, while providing more general applications in registering images of other organs. Experimental results show good performance of the proposed method in registering MR brain images and CT pelvis images.

Original languageEnglish
Title of host publicationLecture Notes in Computer Science
EditorsC. Barillot, D.R. Haynor, P. Hellier
Pages582-590
Number of pages9
Volume3216
EditionPART 1
Publication statusPublished - 2004
Externally publishedYes
EventMedical Image Computing and Computer-Assisted Intervention, MICCAI 2004 - 7th International Conference, Proceedings - Saint-Malo, France
Duration: 2004 Sep 262004 Sep 29

Other

OtherMedical Image Computing and Computer-Assisted Intervention, MICCAI 2004 - 7th International Conference, Proceedings
CountryFrance
CitySaint-Malo
Period04/9/2604/9/29

Fingerprint

Image registration
Brain
Tissue
Image resolution

ASJC Scopus subject areas

  • Computer Science (miscellaneous)

Cite this

Shen, D. (2004). Image registration by hierarchical matching of local spatial intensity histograms. In C. Barillot, D. R. Haynor, & P. Hellier (Eds.), Lecture Notes in Computer Science (PART 1 ed., Vol. 3216, pp. 582-590)

Image registration by hierarchical matching of local spatial intensity histograms. / Shen, Dinggang.

Lecture Notes in Computer Science. ed. / C. Barillot; D.R. Haynor; P. Hellier. Vol. 3216 PART 1. ed. 2004. p. 582-590.

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

Shen, D 2004, Image registration by hierarchical matching of local spatial intensity histograms. in C Barillot, DR Haynor & P Hellier (eds), Lecture Notes in Computer Science. PART 1 edn, vol. 3216, pp. 582-590, Medical Image Computing and Computer-Assisted Intervention, MICCAI 2004 - 7th International Conference, Proceedings, Saint-Malo, France, 04/9/26.
Shen D. Image registration by hierarchical matching of local spatial intensity histograms. In Barillot C, Haynor DR, Hellier P, editors, Lecture Notes in Computer Science. PART 1 ed. Vol. 3216. 2004. p. 582-590
Shen, Dinggang. / Image registration by hierarchical matching of local spatial intensity histograms. Lecture Notes in Computer Science. editor / C. Barillot ; D.R. Haynor ; P. Hellier. Vol. 3216 PART 1. ed. 2004. pp. 582-590
@inproceedings{b7e3042a8f064868bb61c4296f1592fa,
title = "Image registration by hierarchical matching of local spatial intensity histograms",
abstract = "We previously presented a HAMMER image registration algorithm that demonstrated high accuracy in superposition of images from different individual brains. However, the HAMMER registration algorithm requires presegmentation of brain tissues, since the attribute vectors used to hierarchically match the corresponding pairs of points are defined from the segmented images. 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 use 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 more importantly it captures spatial information by integrating a number of local histograms that are calculated from multi-resolution images. The new attribute vectors are able to determine corresponding points across individual images. Therefore, by hierarchically matching new attribute vectors, the proposed registration method performs as successfully as the previous HAMMER algorithm did in registering MR brain images, while providing more general applications in registering images of other organs. Experimental results show good performance of the proposed method in registering MR brain images and CT pelvis images.",
author = "Dinggang Shen",
year = "2004",
language = "English",
volume = "3216",
pages = "582--590",
editor = "C. Barillot and D.R. Haynor and P. Hellier",
booktitle = "Lecture Notes in Computer Science",
edition = "PART 1",

}

TY - GEN

T1 - Image registration by hierarchical matching of local spatial intensity histograms

AU - Shen, Dinggang

PY - 2004

Y1 - 2004

N2 - We previously presented a HAMMER image registration algorithm that demonstrated high accuracy in superposition of images from different individual brains. However, the HAMMER registration algorithm requires presegmentation of brain tissues, since the attribute vectors used to hierarchically match the corresponding pairs of points are defined from the segmented images. 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 use 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 more importantly it captures spatial information by integrating a number of local histograms that are calculated from multi-resolution images. The new attribute vectors are able to determine corresponding points across individual images. Therefore, by hierarchically matching new attribute vectors, the proposed registration method performs as successfully as the previous HAMMER algorithm did in registering MR brain images, while providing more general applications in registering images of other organs. Experimental results show good performance of the proposed method in registering MR brain images and CT pelvis images.

AB - We previously presented a HAMMER image registration algorithm that demonstrated high accuracy in superposition of images from different individual brains. However, the HAMMER registration algorithm requires presegmentation of brain tissues, since the attribute vectors used to hierarchically match the corresponding pairs of points are defined from the segmented images. 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 use 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 more importantly it captures spatial information by integrating a number of local histograms that are calculated from multi-resolution images. The new attribute vectors are able to determine corresponding points across individual images. Therefore, by hierarchically matching new attribute vectors, the proposed registration method performs as successfully as the previous HAMMER algorithm did in registering MR brain images, while providing more general applications in registering images of other organs. Experimental results show good performance of the proposed method in registering MR brain images and CT pelvis images.

UR - http://www.scopus.com/inward/record.url?scp=20344401788&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=20344401788&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:20344401788

VL - 3216

SP - 582

EP - 590

BT - Lecture Notes in Computer Science

A2 - Barillot, C.

A2 - Haynor, D.R.

A2 - Hellier, P.

ER -