An airway tree-shape model for geodesic airway branch labeling

Aasa Feragen; Pechin Chien Pau Lo; Vladlena Gorbunova; Mads Nielsen; Asger Dirksen; Joseph M. Reinhardt; Francois Bernard Lauze; Marleen de Bruijne

An airway tree-shape model for geodesic airway branch labeling

Aasa Feragen, Pechin Chien Pau Lo, Vladlena Gorbunova, Mads Nielsen, Asger Dirksen, Joseph M. Reinhardt, Francois Bernard Lauze, Marleen de Bruijne

Department of Computer Science

Abstract

We present a mathematical airway tree-shape framework
where airway trees are compared using geodesic distances. The framework
consists of a rigorously dened shape space for treelike shapes,
endowed with a metric such that the shape space is a geodesic metric
space. This means that the distance between two tree-shapes can be realized
as the length of the geodesic, or shortest deformation, connecting
the two shapes. By computing geodesics between airway trees, as well as
the corresponding airway deformation, we generate airway branch correspondences.
Correspondences between an unlabeled airway tree and a set
of labeled airway trees are combined with a voting scheme to perform
automatic branch labeling of segmented airways from the challenging
EXACT'09 test set. In spite of the varying quality of the data, we obtain
robust labeling results.

Original language	English
Title of host publication	MFCA 2011 : 3rd MICCAI Workshop on Mathematical Foundations of Computational Anatomy
Editors	Xavier Pennec, Sarang Joshi, Mads Nielsen
Number of pages	12
Publication date	2011
Pages	123-134
Publication status	Published - 2011
Event	3rd MICCAI Workshop on Mathematical Foundations of Computational Anatomy - Westin Harbour Castle, Toronto, Canada Duration: 22 Sept 2011 → 22 Sept 2011 Conference number: 3

Conference

Conference	3rd MICCAI Workshop on Mathematical Foundations of Computational Anatomy
Number	3
Location	Westin Harbour Castle
Country/Territory	Canada
City	Toronto
Period	22/09/2011 → 22/09/2011

Access to Document

https://www-sop.inria.fr/asclepios/events/MFCA11/Proceedings/MFCA11_Proceedings.pdf

Cite this

Feragen, A., Lo, P. C. P., Gorbunova, V., Nielsen, M., Dirksen, A., Reinhardt, J. M., Lauze, F. B., & de Bruijne, M. (2011). An airway tree-shape model for geodesic airway branch labeling. In X. Pennec, S. Joshi, & M. Nielsen (Eds.), MFCA 2011: 3rd MICCAI Workshop on Mathematical Foundations of Computational Anatomy (pp. 123-134) https://www-sop.inria.fr/asclepios/events/MFCA11/Proceedings/MFCA11_Proceedings.pdf

An airway tree-shape model for geodesic airway branch labeling. / Feragen, Aasa; Lo, Pechin Chien Pau; Gorbunova, Vladlena et al.

MFCA 2011: 3rd MICCAI Workshop on Mathematical Foundations of Computational Anatomy. ed. / Xavier Pennec; Sarang Joshi; Mads Nielsen. 2011. p. 123-134.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Feragen, A, Lo, PCP, Gorbunova, V, Nielsen, M, Dirksen, A, Reinhardt, JM, Lauze, FB & de Bruijne, M 2011, An airway tree-shape model for geodesic airway branch labeling. in X Pennec, S Joshi & M Nielsen (eds), MFCA 2011: 3rd MICCAI Workshop on Mathematical Foundations of Computational Anatomy. pp. 123-134, 3rd MICCAI Workshop on Mathematical Foundations of Computational Anatomy, Toronto, Canada, 22/09/2011. <https://www-sop.inria.fr/asclepios/events/MFCA11/Proceedings/MFCA11_Proceedings.pdf>

@inproceedings{659432b9d1ac47158e5f78096cbe56f6,

title = "An airway tree-shape model for geodesic airway branch labeling",

abstract = "We present a mathematical airway tree-shape framework where airway trees are compared using geodesic distances. The framework consists of a rigorously dened shape space for treelike shapes, endowed with a metric such that the shape space is a geodesic metric space. This means that the distance between two tree-shapes can be realized as the length of the geodesic, or shortest deformation, connecting the two shapes. By computing geodesics between airway trees, as well as the corresponding airway deformation, we generate airway branch correspondences. Correspondences between an unlabeled airway tree and a set of labeled airway trees are combined with a voting scheme to perform automatic branch labeling of segmented airways from the challenging EXACT'09 test set. In spite of the varying quality of the data, we obtain robust labeling results.",

author = "Aasa Feragen and Lo, {Pechin Chien Pau} and Vladlena Gorbunova and Mads Nielsen and Asger Dirksen and Reinhardt, {Joseph M.} and Lauze, {Francois Bernard} and {de Bruijne}, Marleen",

year = "2011",

language = "English",

pages = "123--134",

editor = "{ Pennec}, {Xavier } and { Joshi}, Sarang and Mads Nielsen",

booktitle = "MFCA 2011",

note = "3rd MICCAI Workshop on Mathematical Foundations of Computational Anatomy, MFCA 2011 ; Conference date: 22-09-2011 Through 22-09-2011",

}

TY - GEN

T1 - An airway tree-shape model for geodesic airway branch labeling

AU - Feragen, Aasa

AU - Lo, Pechin Chien Pau

AU - Gorbunova, Vladlena

AU - Nielsen, Mads

AU - Dirksen, Asger

AU - Reinhardt, Joseph M.

AU - Lauze, Francois Bernard

AU - de Bruijne, Marleen

N1 - Conference code: 3

PY - 2011

Y1 - 2011

N2 - We present a mathematical airway tree-shape framework where airway trees are compared using geodesic distances. The framework consists of a rigorously dened shape space for treelike shapes, endowed with a metric such that the shape space is a geodesic metric space. This means that the distance between two tree-shapes can be realized as the length of the geodesic, or shortest deformation, connecting the two shapes. By computing geodesics between airway trees, as well as the corresponding airway deformation, we generate airway branch correspondences. Correspondences between an unlabeled airway tree and a set of labeled airway trees are combined with a voting scheme to perform automatic branch labeling of segmented airways from the challenging EXACT'09 test set. In spite of the varying quality of the data, we obtain robust labeling results.

AB - We present a mathematical airway tree-shape framework where airway trees are compared using geodesic distances. The framework consists of a rigorously dened shape space for treelike shapes, endowed with a metric such that the shape space is a geodesic metric space. This means that the distance between two tree-shapes can be realized as the length of the geodesic, or shortest deformation, connecting the two shapes. By computing geodesics between airway trees, as well as the corresponding airway deformation, we generate airway branch correspondences. Correspondences between an unlabeled airway tree and a set of labeled airway trees are combined with a voting scheme to perform automatic branch labeling of segmented airways from the challenging EXACT'09 test set. In spite of the varying quality of the data, we obtain robust labeling results.

M3 - Article in proceedings

SP - 123

EP - 134

BT - MFCA 2011

A2 - Pennec, Xavier

A2 - Joshi, Sarang

A2 - Nielsen, Mads

T2 - 3rd MICCAI Workshop on Mathematical Foundations of Computational Anatomy

Y2 - 22 September 2011 through 22 September 2011

ER -