HAMMER: Hierarchical attribute matching mechanism for elastic registration

Dinggang Shen, Christos Davatzikos

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

18 Citations (Scopus)

Abstract

A new approach is presented for elastic registration of medical images, and is applied to magnetic resonance images of the brain. Experimental results demonstrate remarkably high accuracy in superposition of images from different subjects, thus enabling very precise localization of morphological characteristics in population studies. There are two major novelties in the proposed algorithm. First, it uses an attribute vector, i.e. a set of geometric moment invariants that is defined on each voxel in an image, to reflect the underlying anatomy at different scales. The attribute vector, if rich enough, can distinguish between different parts of an image, which helps establish anatomical correspondences in the deformation procedure. This is a fundamental deviation of our method, referred to as HAMMER, from other volumetric deformation methods, which are typically based on maximizing image similarity. Second, in order to avoid being trapped by local minima, i.e. suboptimal poor matches, HAMMER uses a successive approximation of the energy function being optimized by lower dimensional energy functions, which are constructed to have significantly fewer local minima. This is achieved by hierarchically selecting features that have distinct attribute vectors, thus drastically reducing ambiguity in finding correspondence. A number of experiments in this paper have demonstrated excellent performance.

Original languageEnglish
Title of host publicationProceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis
EditorsL. Staib
Pages29-36
Number of pages8
Publication statusPublished - 2001 Dec 1
Externally publishedYes
EventWorkshop on Mathematical Methods in Biomedical Image Analysis MMBIA 2001 - Kauai, HI, United States
Duration: 2001 Dec 92001 Dec 10

Other

OtherWorkshop on Mathematical Methods in Biomedical Image Analysis MMBIA 2001
CountryUnited States
CityKauai, HI
Period01/12/901/12/10

Fingerprint

Registration
Attribute
Energy Function
Local Minima
Correspondence
Moment Invariants
Geometric Invariants
Magnetic Resonance Image
Successive Approximation
Voxel
Anatomy
Medical Image
Superposition
High Accuracy
Deviation
Distinct
Experimental Results
Demonstrate
Experiment

ASJC Scopus subject areas

  • Analysis

Cite this

Shen, D., & Davatzikos, C. (2001). HAMMER: Hierarchical attribute matching mechanism for elastic registration. In L. Staib (Ed.), Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis (pp. 29-36)

HAMMER : Hierarchical attribute matching mechanism for elastic registration. / Shen, Dinggang; Davatzikos, Christos.

Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis. ed. / L. Staib. 2001. p. 29-36.

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

Shen, D & Davatzikos, C 2001, HAMMER: Hierarchical attribute matching mechanism for elastic registration. in L Staib (ed.), Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis. pp. 29-36, Workshop on Mathematical Methods in Biomedical Image Analysis MMBIA 2001, Kauai, HI, United States, 01/12/9.
Shen D, Davatzikos C. HAMMER: Hierarchical attribute matching mechanism for elastic registration. In Staib L, editor, Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis. 2001. p. 29-36
Shen, Dinggang ; Davatzikos, Christos. / HAMMER : Hierarchical attribute matching mechanism for elastic registration. Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis. editor / L. Staib. 2001. pp. 29-36
@inproceedings{0855fc3806484ce0a87df43451573112,
title = "HAMMER: Hierarchical attribute matching mechanism for elastic registration",
abstract = "A new approach is presented for elastic registration of medical images, and is applied to magnetic resonance images of the brain. Experimental results demonstrate remarkably high accuracy in superposition of images from different subjects, thus enabling very precise localization of morphological characteristics in population studies. There are two major novelties in the proposed algorithm. First, it uses an attribute vector, i.e. a set of geometric moment invariants that is defined on each voxel in an image, to reflect the underlying anatomy at different scales. The attribute vector, if rich enough, can distinguish between different parts of an image, which helps establish anatomical correspondences in the deformation procedure. This is a fundamental deviation of our method, referred to as HAMMER, from other volumetric deformation methods, which are typically based on maximizing image similarity. Second, in order to avoid being trapped by local minima, i.e. suboptimal poor matches, HAMMER uses a successive approximation of the energy function being optimized by lower dimensional energy functions, which are constructed to have significantly fewer local minima. This is achieved by hierarchically selecting features that have distinct attribute vectors, thus drastically reducing ambiguity in finding correspondence. A number of experiments in this paper have demonstrated excellent performance.",
author = "Dinggang Shen and Christos Davatzikos",
year = "2001",
month = "12",
day = "1",
language = "English",
pages = "29--36",
editor = "L. Staib",
booktitle = "Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis",

}

TY - GEN

T1 - HAMMER

T2 - Hierarchical attribute matching mechanism for elastic registration

AU - Shen, Dinggang

AU - Davatzikos, Christos

PY - 2001/12/1

Y1 - 2001/12/1

N2 - A new approach is presented for elastic registration of medical images, and is applied to magnetic resonance images of the brain. Experimental results demonstrate remarkably high accuracy in superposition of images from different subjects, thus enabling very precise localization of morphological characteristics in population studies. There are two major novelties in the proposed algorithm. First, it uses an attribute vector, i.e. a set of geometric moment invariants that is defined on each voxel in an image, to reflect the underlying anatomy at different scales. The attribute vector, if rich enough, can distinguish between different parts of an image, which helps establish anatomical correspondences in the deformation procedure. This is a fundamental deviation of our method, referred to as HAMMER, from other volumetric deformation methods, which are typically based on maximizing image similarity. Second, in order to avoid being trapped by local minima, i.e. suboptimal poor matches, HAMMER uses a successive approximation of the energy function being optimized by lower dimensional energy functions, which are constructed to have significantly fewer local minima. This is achieved by hierarchically selecting features that have distinct attribute vectors, thus drastically reducing ambiguity in finding correspondence. A number of experiments in this paper have demonstrated excellent performance.

AB - A new approach is presented for elastic registration of medical images, and is applied to magnetic resonance images of the brain. Experimental results demonstrate remarkably high accuracy in superposition of images from different subjects, thus enabling very precise localization of morphological characteristics in population studies. There are two major novelties in the proposed algorithm. First, it uses an attribute vector, i.e. a set of geometric moment invariants that is defined on each voxel in an image, to reflect the underlying anatomy at different scales. The attribute vector, if rich enough, can distinguish between different parts of an image, which helps establish anatomical correspondences in the deformation procedure. This is a fundamental deviation of our method, referred to as HAMMER, from other volumetric deformation methods, which are typically based on maximizing image similarity. Second, in order to avoid being trapped by local minima, i.e. suboptimal poor matches, HAMMER uses a successive approximation of the energy function being optimized by lower dimensional energy functions, which are constructed to have significantly fewer local minima. This is achieved by hierarchically selecting features that have distinct attribute vectors, thus drastically reducing ambiguity in finding correspondence. A number of experiments in this paper have demonstrated excellent performance.

UR - http://www.scopus.com/inward/record.url?scp=0035700327&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035700327&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0035700327

SP - 29

EP - 36

BT - Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis

A2 - Staib, L.

ER -