A bottom-up approach for labeling of human airway trees

Pechin Lo; Eva M. van Rikxoort; Jonathan Goldin; Fereidoun Abtin; Marleen de Bruijne; Matthew Brown

A bottom-up approach for labeling of human airway trees

Pechin Lo, Eva M. van Rikxoort, Jonathan Goldin, Fereidoun Abtin, Marleen de Bruijne, Matthew Brown

Department of Computer Science

Abstract

In this paper, an airway labeling algorithm that allows for
gaps between the labeled branches is introduced. A bottom-up approach
for arriving to an optimal set of branches and their associated labels
is used in the proposed method. A K nearest neighbor based appearance
model is used to differentiate the different anatomical branches.
The proposed method was applied on 33 computed tomography scans
of different subjects, where an average of 24 anatomical branches were
correctly detected out of a total of 29 anatomical branches. Additionally
the proposed method was also evaluated on trees with simulated errors,
such as missing branches and having falsely detected branches, where we
showed that such errors have little or no effect on the proposed method.

Original language	English
Title of host publication	The Fourth International Workshop on Pulmonary Image Analysis
Editors	Reinhard Beichel, Marleen de Bruijne, Sven Kabus, Atilla Kiraly, Jan-Martin Kuhnigk, Jamie McClelland, Kensaku Mori, Eva van Rikxoort, Simon Rit
Number of pages	12
Publisher	CreateSpace
Publication date	2011
Pages	23-34
ISBN (Print)	978-1466200166
Publication status	Published - 2011
Event	4th International Workshop on Pulmonary Image Analysis - Toronto, Canada Duration: 18 Sept 2011 → 18 Sept 2011 Conference number: 4

Conference

Conference	4th International Workshop on Pulmonary Image Analysis
Number	4
Country/Territory	Canada
City	Toronto
Period	18/09/2011 → 18/09/2011

Access to Document

http://www.lungworkshop.org/2011/resources/A-Bottom-up-Approach-for-Labeling-of-Human-Airway-Trees.pdf

Cite this

Lo, P., van Rikxoort, E. M., Goldin, J., Abtin, F., de Bruijne, M., & Brown, M. (2011). A bottom-up approach for labeling of human airway trees. In R. Beichel, M. de Bruijne, S. Kabus, A. Kiraly, J-M. Kuhnigk, J. McClelland, K. Mori, E. van Rikxoort, & S. Rit (Eds.), The Fourth International Workshop on Pulmonary Image Analysis (pp. 23-34). CreateSpace. http://www.lungworkshop.org/2011/resources/A-Bottom-up-Approach-for-Labeling-of-Human-Airway-Trees.pdf

A bottom-up approach for labeling of human airway trees. / Lo, Pechin; van Rikxoort, Eva M.; Goldin, Jonathan et al.

The Fourth International Workshop on Pulmonary Image Analysis . ed. / Reinhard Beichel; Marleen de Bruijne; Sven Kabus; Atilla Kiraly; Jan-Martin Kuhnigk; Jamie McClelland; Kensaku Mori; Eva van Rikxoort; Simon Rit. CreateSpace, 2011. p. 23-34.

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

Lo, P, van Rikxoort, EM, Goldin, J, Abtin, F, de Bruijne, M & Brown, M 2011, A bottom-up approach for labeling of human airway trees. in R Beichel, M de Bruijne, S Kabus, A Kiraly, J-M Kuhnigk, J McClelland, K Mori, E van Rikxoort & S Rit (eds), The Fourth International Workshop on Pulmonary Image Analysis . CreateSpace, pp. 23-34, 4th International Workshop on Pulmonary Image Analysis, Toronto, Canada, 18/09/2011. <http://www.lungworkshop.org/2011/resources/A-Bottom-up-Approach-for-Labeling-of-Human-Airway-Trees.pdf>

Lo, Pechin ; van Rikxoort, Eva M. ; Goldin, Jonathan et al. / A bottom-up approach for labeling of human airway trees. The Fourth International Workshop on Pulmonary Image Analysis . editor / Reinhard Beichel ; Marleen de Bruijne ; Sven Kabus ; Atilla Kiraly ; Jan-Martin Kuhnigk ; Jamie McClelland ; Kensaku Mori ; Eva van Rikxoort ; Simon Rit. CreateSpace, 2011. pp. 23-34

@inproceedings{a250a1088bf14372967a10c0f361436e,

title = "A bottom-up approach for labeling of human airway trees",

abstract = "In this paper, an airway labeling algorithm that allows for gaps between the labeled branches is introduced. A bottom-up approach for arriving to an optimal set of branches and their associated labels is used in the proposed method. A K nearest neighbor based appearance model is used to differentiate the different anatomical branches. The proposed method was applied on 33 computed tomography scans of different subjects, where an average of 24 anatomical branches were correctly detected out of a total of 29 anatomical branches. Additionally the proposed method was also evaluated on trees with simulated errors, such as missing branches and having falsely detected branches, where we showed that such errors have little or no effect on the proposed method.",

author = "Pechin Lo and {van Rikxoort}, {Eva M.} and Jonathan Goldin and Fereidoun Abtin and {de Bruijne}, Marleen and Matthew Brown",

year = "2011",

language = "English",

isbn = "978-1466200166 ",

pages = "23--34",

editor = "Reinhard Beichel and {de Bruijne}, {Marleen } and Sven Kabus and Atilla Kiraly and Jan-Martin Kuhnigk and Jamie McClelland and Kensaku Mori and {van Rikxoort}, Eva and Simon Rit",

booktitle = "The Fourth International Workshop on Pulmonary Image Analysis",

publisher = "CreateSpace",

note = "4th International Workshop on Pulmonary Image Analysis ; Conference date: 18-09-2011 Through 18-09-2011",

}

TY - GEN

T1 - A bottom-up approach for labeling of human airway trees

AU - Lo, Pechin

AU - van Rikxoort, Eva M.

AU - Goldin, Jonathan

AU - Abtin, Fereidoun

AU - de Bruijne, Marleen

AU - Brown, Matthew

N1 - Conference code: 4

PY - 2011

Y1 - 2011

N2 - In this paper, an airway labeling algorithm that allows for gaps between the labeled branches is introduced. A bottom-up approach for arriving to an optimal set of branches and their associated labels is used in the proposed method. A K nearest neighbor based appearance model is used to differentiate the different anatomical branches. The proposed method was applied on 33 computed tomography scans of different subjects, where an average of 24 anatomical branches were correctly detected out of a total of 29 anatomical branches. Additionally the proposed method was also evaluated on trees with simulated errors, such as missing branches and having falsely detected branches, where we showed that such errors have little or no effect on the proposed method.

AB - In this paper, an airway labeling algorithm that allows for gaps between the labeled branches is introduced. A bottom-up approach for arriving to an optimal set of branches and their associated labels is used in the proposed method. A K nearest neighbor based appearance model is used to differentiate the different anatomical branches. The proposed method was applied on 33 computed tomography scans of different subjects, where an average of 24 anatomical branches were correctly detected out of a total of 29 anatomical branches. Additionally the proposed method was also evaluated on trees with simulated errors, such as missing branches and having falsely detected branches, where we showed that such errors have little or no effect on the proposed method.

M3 - Article in proceedings

SN - 978-1466200166

SP - 23

EP - 34

BT - The Fourth International Workshop on Pulmonary Image Analysis

A2 - Beichel, Reinhard

A2 - de Bruijne, Marleen

A2 - Kabus, Sven

A2 - Kiraly, Atilla

A2 - Kuhnigk, Jan-Martin

A2 - McClelland, Jamie

A2 - Mori, Kensaku

A2 - van Rikxoort, Eva

A2 - Rit, Simon

PB - CreateSpace

T2 - 4th International Workshop on Pulmonary Image Analysis

Y2 - 18 September 2011 through 18 September 2011

ER -

A bottom-up approach for labeling of human airway trees

Abstract

Conference

Access to Document

Fingerprint

Cite this