A hierarchical scheme for geodesic anatomical labeling of airway trees

Aasa Feragen; Jens Petersen; Megan Owen; Pechin Chien Pau Lo; Laura Thomsen; Mathilde M. W. Wille; Asger Dirksen; Marleen de Bruijne

doi:10.1007/978-3-642-33454-2_19

A hierarchical scheme for geodesic anatomical labeling of airway trees

Aasa Feragen, Jens Petersen, Megan Owen, Pechin Chien Pau Lo, Laura Thomsen, Mathilde M. W. Wille, Asger Dirksen, Marleen de Bruijne

Datalogisk Institut

20 Citationer (Scopus)

1848 Downloads (Pure)

Abstract

We present a fast and robust supervised algorithm for label-
ing anatomical airway trees, based on geodesic distances in a geometric
tree-space. Possible branch label configurations for a given unlabeled air-
way tree are evaluated based on the distances to a training set of labeled
airway trees. In tree-space, the airway tree topology and geometry change
continuously, giving a natural way to automatically handle anatomical
differences and noise. The algorithm is made efficient using a hierarchical
approach, in which labels are assigned from the top down. We only use
features of the airway centerline tree, which is relatively unaffected by
pathology.

A thorough leave-one-patient-out evaluation of the algorithm is made on
40 segmented airway trees from 20 subjects labeled by 2 medical experts.
We evaluate accuracy, reproducibility and robustness in patients with
Chronic Obstructive Pulmonary Disease (COPD). Performance is statis-
tically similar to the inter- and intra-expert agreement, and we found no
significant correlation between COPD stage and labeling accuracy.

Originalsprog	Engelsk
Titel	Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012 : 15th International Conference, Nice, France, October 1-5, 2012, Proceedings, Part III
Redaktører	Nicholas Ayache , Hervé Delingette , Polina Golland, Kensaku Mori
Antal sider	9
Forlag	Springer
Publikationsdato	2012
Sider	147-155
ISBN (Trykt)	978-3-642-33453-5
ISBN (Elektronisk)	978-3-642-33454-2
DOI	https://doi.org/10.1007/978-3-642-33454-2_19
Status	Udgivet - 2012
Begivenhed	15th International Conference on Medical Image Computing and Computer-Assisted Intervention - Nice, Frankrig Varighed: 1 okt. 2012 → 5 okt. 2012 Konferencens nummer: 15

Konference

Konference	15th International Conference on Medical Image Computing and Computer-Assisted Intervention
Nummer	15
Land/Område	Frankrig
By	Nice
Periode	01/10/2012 → 05/10/2012

Navn	Lecture notes in computer science
Vol/bind	7512
ISSN	0302-9743

Adgang til dokumentet

10.1007/978-3-642-33454-2_19

feragen_miccai_2012Accepteret manuskript, 693 KB
10.1007%2F978-3-642-33454-2_19.pdfForlagets udgivne version, 569 KB

Citationsformater

Feragen, A., Petersen, J., Owen, M., Lo, P. C. P., Thomsen, L., Wille, M. M. W., Dirksen, A., & de Bruijne, M. (2012). A hierarchical scheme for geodesic anatomical labeling of airway trees. I N. Ayache , H. Delingette , P. Golland, & K. Mori (red.), Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012: 15th International Conference, Nice, France, October 1-5, 2012, Proceedings, Part III (s. 147-155). Springer. https://doi.org/10.1007/978-3-642-33454-2_19

A hierarchical scheme for geodesic anatomical labeling of airway trees. / Feragen, Aasa; Petersen, Jens; Owen, Megan et al.
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012: 15th International Conference, Nice, France, October 1-5, 2012, Proceedings, Part III. red. / Nicholas Ayache ; Hervé Delingette ; Polina Golland; Kensaku Mori . Springer, 2012. s. 147-155 (Lecture notes in computer science, Bind 7512).

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

Feragen, A, Petersen, J, Owen, M, Lo, PCP, Thomsen, L, Wille, MMW, Dirksen, A & de Bruijne, M 2012, A hierarchical scheme for geodesic anatomical labeling of airway trees. i N Ayache , H Delingette , P Golland & K Mori (red), Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012: 15th International Conference, Nice, France, October 1-5, 2012, Proceedings, Part III. Springer, Lecture notes in computer science, bind 7512, s. 147-155, 15th International Conference on Medical Image Computing and Computer-Assisted Intervention, Nice, Frankrig, 01/10/2012. https://doi.org/10.1007/978-3-642-33454-2_19

Feragen A, Petersen J, Owen M, Lo PCP, Thomsen L, Wille MMW et al. A hierarchical scheme for geodesic anatomical labeling of airway trees. I Ayache N, Delingette H, Golland P, Mori K, red., Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012: 15th International Conference, Nice, France, October 1-5, 2012, Proceedings, Part III. Springer. 2012. s. 147-155. (Lecture notes in computer science, Bind 7512). doi: 10.1007/978-3-642-33454-2_19

Feragen, Aasa ; Petersen, Jens ; Owen, Megan et al. / A hierarchical scheme for geodesic anatomical labeling of airway trees. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012: 15th International Conference, Nice, France, October 1-5, 2012, Proceedings, Part III. red. / Nicholas Ayache ; Hervé Delingette ; Polina Golland ; Kensaku Mori . Springer, 2012. s. 147-155 (Lecture notes in computer science, Bind 7512).

@inproceedings{7afc1510bdb64b3f8a2e37beb9a574ba,

title = "A hierarchical scheme for geodesic anatomical labeling of airway trees",

abstract = "We present a fast and robust supervised algorithm for labeling anatomical airway trees, based on geodesic distances in a geometric tree-space. Possible branch label configurations for a given tree are evaluated based on distances to a training set of labeled trees. In tree-space, the tree topology and geometry change continuously, giving a natural way to automatically handle anatomical differences and noise. The algorithm is made efficient using a hierarchical approach, in which labels are assigned from the top down. We only use features of the airway centerline tree, which are relatively unaffected by pathology. A thorough leave-one-patient-out evaluation of the algorithm is made on 40 segmented airway trees from 20 subjects labeled by 2 medical experts. We evaluate accuracy, reproducibility and robustness in patients with Chronic Obstructive Pulmonary Disease (COPD). Performance is statistically similar to the inter- and intra-expert agreement, and we found no significant correlation between COPD stage and labeling accuracy.",

author = "Aasa Feragen and Jens Petersen and Megan Owen and Lo, {Pechin Chien Pau} and Laura Thomsen and Wille, {Mathilde M. W.} and Asger Dirksen and {de Bruijne}, Marleen",

year = "2012",

doi = "10.1007/978-3-642-33454-2_19",

language = "English",

isbn = "978-3-642-33453-5",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "147--155",

editor = "{Ayache }, {Nicholas } and {Delingette }, {Herv{\'e} } and Golland, {Polina } and {Mori }, {Kensaku }",

booktitle = "Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012",

note = "15th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2012 ; Conference date: 01-10-2012 Through 05-10-2012",

}

TY - GEN

T1 - A hierarchical scheme for geodesic anatomical labeling of airway trees

AU - Feragen, Aasa

AU - Petersen, Jens

AU - Owen, Megan

AU - Lo, Pechin Chien Pau

AU - Thomsen, Laura

AU - Wille, Mathilde M. W.

AU - Dirksen, Asger

AU - de Bruijne, Marleen

N1 - Conference code: 15

PY - 2012

Y1 - 2012

N2 - We present a fast and robust supervised algorithm for labeling anatomical airway trees, based on geodesic distances in a geometric tree-space. Possible branch label configurations for a given tree are evaluated based on distances to a training set of labeled trees. In tree-space, the tree topology and geometry change continuously, giving a natural way to automatically handle anatomical differences and noise. The algorithm is made efficient using a hierarchical approach, in which labels are assigned from the top down. We only use features of the airway centerline tree, which are relatively unaffected by pathology. A thorough leave-one-patient-out evaluation of the algorithm is made on 40 segmented airway trees from 20 subjects labeled by 2 medical experts. We evaluate accuracy, reproducibility and robustness in patients with Chronic Obstructive Pulmonary Disease (COPD). Performance is statistically similar to the inter- and intra-expert agreement, and we found no significant correlation between COPD stage and labeling accuracy.

AB - We present a fast and robust supervised algorithm for labeling anatomical airway trees, based on geodesic distances in a geometric tree-space. Possible branch label configurations for a given tree are evaluated based on distances to a training set of labeled trees. In tree-space, the tree topology and geometry change continuously, giving a natural way to automatically handle anatomical differences and noise. The algorithm is made efficient using a hierarchical approach, in which labels are assigned from the top down. We only use features of the airway centerline tree, which are relatively unaffected by pathology. A thorough leave-one-patient-out evaluation of the algorithm is made on 40 segmented airway trees from 20 subjects labeled by 2 medical experts. We evaluate accuracy, reproducibility and robustness in patients with Chronic Obstructive Pulmonary Disease (COPD). Performance is statistically similar to the inter- and intra-expert agreement, and we found no significant correlation between COPD stage and labeling accuracy.

U2 - 10.1007/978-3-642-33454-2_19

DO - 10.1007/978-3-642-33454-2_19

M3 - Article in proceedings

SN - 978-3-642-33453-5

T3 - Lecture notes in computer science

SP - 147

EP - 155

BT - Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012

A2 - Ayache , Nicholas

A2 - Delingette , Hervé

A2 - Golland, Polina

A2 - Mori , Kensaku

PB - Springer

T2 - 15th International Conference on Medical Image Computing and Computer-Assisted Intervention

Y2 - 1 October 2012 through 5 October 2012

ER -

A hierarchical scheme for geodesic anatomical labeling of airway trees

Abstract

Konference

Adgang til dokumentet

Fingeraftryk

Citationsformater