Vessel-guided airway segmentation based on voxel classification

Pechin Chien Pau Lo; Jon Sporring; Haseem Ashraf; Jesper Johannes Holst Pedersen; Marleen de Bruijne

Vessel-guided airway segmentation based on voxel classification

Pechin Chien Pau Lo, Jon Sporring, Haseem Ashraf, Jesper Johannes Holst Pedersen, Marleen de Bruijne

Abstract

This paper presents a method for improving airway tree segmentation using vessel orientation information. We use the fact that an airway branch is always accompanied by an artery, with both structures having similar orientations. This work is based on a voxel classification airway segmentation method proposed previously. The probability of a voxel belonging to the airway, from the voxel classification method, is augmented with an orientation similarity measure as a criterion for region growing. The orientation similarity measure of a voxel indicates how similar is the orientation of the surroundings of a voxel, estimated based on a tube model, is to that of a neighboring vessel. The proposed method is tested on 20 CT images from different subjects selected randomly from a lung cancer screening study. Length of the airway branches from the results of the proposed method are significantly longer (p = 0.0125) as compared to only using probability from the voxel classification method.

Original language	English
Title of host publication	The first International Workshop on Pulmonary Image Analysis : New York, September 6, 2008
Editors	Matthew Brown, Marleen de Bruijne, Bram van Ginneken, Atilla Kiraly, Jan-Martin Kuhnigk, Cristian Lorenz, Kensaku Mori, Joseph Reinhardt
Publisher	Lulu.com
Publication date	2008
Pages	113-122
ISBN (Print)	978-1-4357-5952-7
Publication status	Published - 2008
Event	International Workshop on Pulmonary Image Analysis: - New York, United States Duration: 6 Sept 2008 → 6 Sept 2008 Conference number: 1

Conference

Conference	International Workshop on Pulmonary Image Analysis:
Number	1
Country/Territory	United States
City	New York
Period	06/09/2008 → 06/09/2008

Access to Document

http://www.lulu.com/content/3507981

Cite this

Lo, P. C. P., Sporring, J., Ashraf, H., Holst Pedersen, J. J., & de Bruijne, M. (2008). Vessel-guided airway segmentation based on voxel classification. In M. Brown, M. de Bruijne, B. van Ginneken, A. Kiraly, J-M. Kuhnigk, C. Lorenz, K. Mori, & J. Reinhardt (Eds.), The first International Workshop on Pulmonary Image Analysis: New York, September 6, 2008 (pp. 113-122). Lulu.com. http://www.lulu.com/content/3507981

Vessel-guided airway segmentation based on voxel classification. / Lo, Pechin Chien Pau; Sporring, Jon; Ashraf, Haseem et al.

The first International Workshop on Pulmonary Image Analysis: New York, September 6, 2008. ed. / Matthew Brown; Marleen de Bruijne; Bram van Ginneken; Atilla Kiraly; Jan-Martin Kuhnigk; Cristian Lorenz; Kensaku Mori; Joseph Reinhardt. Lulu.com, 2008. p. 113-122.

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

Lo, PCP, Sporring, J, Ashraf, H, Holst Pedersen, JJ & de Bruijne, M 2008, Vessel-guided airway segmentation based on voxel classification. in M Brown, M de Bruijne, B van Ginneken, A Kiraly, J-M Kuhnigk, C Lorenz, K Mori & J Reinhardt (eds), The first International Workshop on Pulmonary Image Analysis: New York, September 6, 2008. Lulu.com, pp. 113-122, International Workshop on Pulmonary Image Analysis:, New York, United States, 06/09/2008. <http://www.lulu.com/content/3507981>

Lo, Pechin Chien Pau ; Sporring, Jon ; Ashraf, Haseem et al. / Vessel-guided airway segmentation based on voxel classification. The first International Workshop on Pulmonary Image Analysis: New York, September 6, 2008. editor / Matthew Brown ; Marleen de Bruijne ; Bram van Ginneken ; Atilla Kiraly ; Jan-Martin Kuhnigk ; Cristian Lorenz ; Kensaku Mori ; Joseph Reinhardt. Lulu.com, 2008. pp. 113-122

@inproceedings{c53cce90cc6611dd9473000ea68e967b,

title = "Vessel-guided airway segmentation based on voxel classification",

abstract = "This paper presents a method for improving airway tree segmentation using vessel orientation information. We use the fact that an airway branch is always accompanied by an artery, with both structures having similar orientations. This work is based on a voxel classification airway segmentation method proposed previously. The probability of a voxel belonging to the airway, from the voxel classification method, is augmented with an orientation similarity measure as a criterion for region growing. The orientation similarity measure of a voxel indicates how similar is the orientation of the surroundings of a voxel, estimated based on a tube model, is to that of a neighboring vessel. The proposed method is tested on 20 CT images from different subjects selected randomly from a lung cancer screening study. Length of the airway branches from the results of the proposed method are significantly longer (p = 0.0125) as compared to only using probability from the voxel classification method.",

author = "Lo, {Pechin Chien Pau} and Jon Sporring and Haseem Ashraf and {Holst Pedersen}, {Jesper Johannes} and {de Bruijne}, Marleen",

year = "2008",

language = "English",

isbn = "978-1-4357-5952-7",

pages = "113--122",

editor = "Matthew Brown and {de Bruijne}, Marleen and {van Ginneken}, Bram and Atilla Kiraly and Jan-Martin Kuhnigk and Cristian Lorenz and Kensaku Mori and Joseph Reinhardt",

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

publisher = "Lulu.com",

note = "International Workshop on Pulmonary Image Analysis: ; Conference date: 06-09-2008 Through 06-09-2008",

}

TY - GEN

T1 - Vessel-guided airway segmentation based on voxel classification

AU - Lo, Pechin Chien Pau

AU - Sporring, Jon

AU - Ashraf, Haseem

AU - Holst Pedersen, Jesper Johannes

AU - de Bruijne, Marleen

N1 - Conference code: 1

PY - 2008

Y1 - 2008

N2 - This paper presents a method for improving airway tree segmentation using vessel orientation information. We use the fact that an airway branch is always accompanied by an artery, with both structures having similar orientations. This work is based on a voxel classification airway segmentation method proposed previously. The probability of a voxel belonging to the airway, from the voxel classification method, is augmented with an orientation similarity measure as a criterion for region growing. The orientation similarity measure of a voxel indicates how similar is the orientation of the surroundings of a voxel, estimated based on a tube model, is to that of a neighboring vessel. The proposed method is tested on 20 CT images from different subjects selected randomly from a lung cancer screening study. Length of the airway branches from the results of the proposed method are significantly longer (p = 0.0125) as compared to only using probability from the voxel classification method.

AB - This paper presents a method for improving airway tree segmentation using vessel orientation information. We use the fact that an airway branch is always accompanied by an artery, with both structures having similar orientations. This work is based on a voxel classification airway segmentation method proposed previously. The probability of a voxel belonging to the airway, from the voxel classification method, is augmented with an orientation similarity measure as a criterion for region growing. The orientation similarity measure of a voxel indicates how similar is the orientation of the surroundings of a voxel, estimated based on a tube model, is to that of a neighboring vessel. The proposed method is tested on 20 CT images from different subjects selected randomly from a lung cancer screening study. Length of the airway branches from the results of the proposed method are significantly longer (p = 0.0125) as compared to only using probability from the voxel classification method.

M3 - Article in proceedings

SN - 978-1-4357-5952-7

SP - 113

EP - 122

BT - The first International Workshop on Pulmonary Image Analysis

A2 - Brown, Matthew

A2 - de Bruijne, Marleen

A2 - van Ginneken, Bram

A2 - Kiraly, Atilla

A2 - Kuhnigk, Jan-Martin

A2 - Lorenz, Cristian

A2 - Mori, Kensaku

A2 - Reinhardt, Joseph

PB - Lulu.com

T2 - International Workshop on Pulmonary Image Analysis:

Y2 - 6 September 2008 through 6 September 2008

ER -