DRAMMS: Deformable registration via attribute matching and mutual-saliency weighting.
Yangming Ou
(1)
,
Aristeidis Sotiras
(2)
,
Nikos Paragios
(2, 3, 4, 5, 6, 7)
,
Christos Davatzikos
(1)
1
SBIA -
Section for Biomedical Image Analysis
2 GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
3 MAS - Mathématiques Appliquées aux Systèmes - EA 4037
4 imagine [Marne-la-Vallée]
5 LIGM - Laboratoire d'Informatique Gaspard-Monge
6 UPEM - Université Paris-Est Marne-la-Vallée
7 ENPC - École des Ponts ParisTech
2 GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
3 MAS - Mathématiques Appliquées aux Systèmes - EA 4037
4 imagine [Marne-la-Vallée]
5 LIGM - Laboratoire d'Informatique Gaspard-Monge
6 UPEM - Université Paris-Est Marne-la-Vallée
7 ENPC - École des Ponts ParisTech
Résumé
A general-purpose deformable registration algorithm referred to as "DRAMMS" is presented in this paper. DRAMMS bridges the gap between the traditional voxel-wise methods and landmark/feature-based methods with primarily two contributions. First, DRAMMS renders each voxel relatively distinctively identifiable by a rich set of attributes, therefore largely reducing matching ambiguities. In particular, a set of multi-scale and multi-orientation Gabor attributes are extracted and the optimal components are selected, so that they form a highly distinctive morphological signature reflecting the anatomical and geometric context around each voxel. Moreover, the way in which the optimal Gabor attributes are constructed is independent of the underlying image modalities or contents, which renders DRAMMS generally applicable to diverse registration tasks. A second contribution of DRAMMS is that it modulates the registration by assigning higher weights to those voxels having higher ability to establish unique (hence reliable) correspondences across images, therefore reducing the negative impact of those regions that are less capable of finding correspondences (such as outlier regions). A continuously-valued weighting function named "mutual-saliency" is developed to reflect the matching uniqueness between a pair of voxels implied by the tentative transformation. As a result, voxels do not contribute equally as in most voxel-wise methods, nor in isolation as in landmark/feature-based methods. Instead, they contribute according to the continuously-valued mutual-saliency map, which dynamically evolves during the registration process. Experiments in simulated images, inter-subject images, single-/multi-modality images, from brain, heart, and prostate have demonstrated the general applicability and the accuracy of DRAMMS.
Format du dépôt | Notice |
---|---|
Type de dépôt | Article dans une revue |
Titre |
en
DRAMMS: Deformable registration via attribute matching and mutual-saliency weighting.
|
Résumé |
en
A general-purpose deformable registration algorithm referred to as "DRAMMS" is presented in this paper. DRAMMS bridges the gap between the traditional voxel-wise methods and landmark/feature-based methods with primarily two contributions. First, DRAMMS renders each voxel relatively distinctively identifiable by a rich set of attributes, therefore largely reducing matching ambiguities. In particular, a set of multi-scale and multi-orientation Gabor attributes are extracted and the optimal components are selected, so that they form a highly distinctive morphological signature reflecting the anatomical and geometric context around each voxel. Moreover, the way in which the optimal Gabor attributes are constructed is independent of the underlying image modalities or contents, which renders DRAMMS generally applicable to diverse registration tasks. A second contribution of DRAMMS is that it modulates the registration by assigning higher weights to those voxels having higher ability to establish unique (hence reliable) correspondences across images, therefore reducing the negative impact of those regions that are less capable of finding correspondences (such as outlier regions). A continuously-valued weighting function named "mutual-saliency" is developed to reflect the matching uniqueness between a pair of voxels implied by the tentative transformation. As a result, voxels do not contribute equally as in most voxel-wise methods, nor in isolation as in landmark/feature-based methods. Instead, they contribute according to the continuously-valued mutual-saliency map, which dynamically evolves during the registration process. Experiments in simulated images, inter-subject images, single-/multi-modality images, from brain, heart, and prostate have demonstrated the general applicability and the accuracy of DRAMMS.
|
Auteur(s) |
Yangming Ou
1
, Aristeidis Sotiras
2
, Nikos Paragios
2, 3, 4, 5, 6, 7
, Christos Davatzikos
1
1
SBIA -
Section for Biomedical Image Analysis
( 98124 )
- 3600 Market St. Suite 380 Philadelphia, PA 19104
- États-Unis
2
GALEN -
Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
( 56046 )
- Laboratoire MAS Ecole Centrale de Paris Grande Voie des Vignes 92295 Chatenay-Malabry Cedex
- France
3
MAS -
Mathématiques Appliquées aux Systèmes - EA 4037
( 3207 )
- Grande Voie des Vignes 92295 Châtenay-Malabry
- France
4
imagine [Marne-la-Vallée]
( 91769 )
- 6 avenue Blaise Pascal - Cité Descartes, Champs-sur-Marne 77455 Marne-la-Vallée cedex 2
- France
5
LIGM -
Laboratoire d'Informatique Gaspard-Monge
( 3210 )
- Université de Paris-Est Marne-la-Vallée, Cité Descartes, Bâtiment Copernic, 5 bd Descartes, 77454 Marne-la-Vallée Cedex 2
- France
6
UPEM -
Université Paris-Est Marne-la-Vallée
( 301243 )
- 5 boulevard Descartes - Champs-sur-Marne - 77454 Marne-la-Vallée Cedex 2
- France
7
ENPC -
École des Ponts ParisTech
( 301545 )
- École des Ponts ParisTech 6-8 avenue Blaise-Pascal Cité Descartes 77455 Champs-sur-Marne Marne-la-Vallée cedex 2
- France
|
Comité de lecture |
Oui
|
Vulgarisation |
Non
|
Langue du document |
Anglais
|
Nom de la revue |
|
Audience |
Internationale
|
Date de publication |
2011-08
|
Volume |
15
|
Numéro |
4
|
Page/Identifiant |
622-639
|
URL éditeur |
http://www.sciencedirect.com/science/article/pii/S1361841510000940#
|
Domaine(s) |
|
DOI | 10.1016/j.media.2010.07.002 |
Pubmed Id | 20688559 |
PubMed Central | PMC3012150 |
Loading...