Pulmonary airways tree segmentation from CT examinations using adaptive volume of interest

Sang Cheol Park, Won Pil Kim, Bin Zheng, Joseph K. Leader, Jiantao Pu, Jun Tan, David Gur

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Airways tree segmentation is an important step in quantitatively assessing the severity of and changes in several lung diseases such as chronic obstructive pulmonary disease (COPD), asthma, and cystic fibrosis. It can also be used in guiding bronchoscopy. The purpose of this study is to develop an automated scheme for segmenting the airways tree structure depicted on chest CT examinations. After lung volume segmentation, the scheme defines the first cylinder-like volume of interest (VOI) using a series of images depicting the trachea. The scheme then iteratively defines and adds subsequent VOIs using a region growing algorithm combined with adaptively determined thresholds in order to trace possible sections of airways located inside the combined VOI in question. The airway tree segmentation process is automatically terminated after the scheme assesses all defined VOIs in the iteratively assembled VOI list. In this preliminary study, ten CT examinations with 1.25mm section thickness and two different CT image reconstruction kernels ("bone" and "standard") were selected and used to test the proposed airways tree segmentation scheme. The experiment results showed that (1) adopting this approach affectively prevented the scheme from infiltrating into the parenchyma, (2) the proposed method reasonably accurately segmented the airways trees with lower false positive identification rate as compared with other previously reported schemes that are based on 2-D image segmentation and data analyses, and (3) the proposed adaptive, iterative threshold selection method for the region growing step in each identified VOI enables the scheme to segment the airways trees reliably to the 4th generation in this limited dataset with successful segmentation up to the 5th generation in a fraction of the airways tree branches.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2009 - Image Processing
Volume7259
DOIs
StatePublished - Dec 15 2009
EventMedical Imaging 2009 - Image Processing - Lake Buena Vista, FL, United States
Duration: Feb 8 2009Feb 10 2009

Other

OtherMedical Imaging 2009 - Image Processing
CountryUnited States
CityLake Buena Vista, FL
Period2/8/092/10/09

Fingerprint

examination
Lung
Pulmonary diseases
lungs
cystic fibrosis
asthma
trachea
Computer-Assisted Image Processing
Bronchoscopy
Trachea
thresholds
chest
Cystic Fibrosis
Chronic Obstructive Pulmonary Disease
Lung Diseases
image reconstruction
lists
Thorax
bones
Asthma

Keywords

  • 3-D region growing
  • Computed tomography
  • Pulmonary airways tree segmentation
  • Threshold selection
  • Volume of interest

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Park, S. C., Kim, W. P., Zheng, B., Leader, J. K., Pu, J., Tan, J., & Gur, D. (2009). Pulmonary airways tree segmentation from CT examinations using adaptive volume of interest. In Medical Imaging 2009 - Image Processing (Vol. 7259). [72593U] https://doi.org/10.1117/12.810947

Pulmonary airways tree segmentation from CT examinations using adaptive volume of interest. / Park, Sang Cheol; Kim, Won Pil; Zheng, Bin; Leader, Joseph K.; Pu, Jiantao; Tan, Jun; Gur, David.

Medical Imaging 2009 - Image Processing. Vol. 7259 2009. 72593U.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Park, SC, Kim, WP, Zheng, B, Leader, JK, Pu, J, Tan, J & Gur, D 2009, Pulmonary airways tree segmentation from CT examinations using adaptive volume of interest. in Medical Imaging 2009 - Image Processing. vol. 7259, 72593U, Medical Imaging 2009 - Image Processing, Lake Buena Vista, FL, United States, 2/8/09. https://doi.org/10.1117/12.810947
Park SC, Kim WP, Zheng B, Leader JK, Pu J, Tan J et al. Pulmonary airways tree segmentation from CT examinations using adaptive volume of interest. In Medical Imaging 2009 - Image Processing. Vol. 7259. 2009. 72593U https://doi.org/10.1117/12.810947
Park, Sang Cheol ; Kim, Won Pil ; Zheng, Bin ; Leader, Joseph K. ; Pu, Jiantao ; Tan, Jun ; Gur, David. / Pulmonary airways tree segmentation from CT examinations using adaptive volume of interest. Medical Imaging 2009 - Image Processing. Vol. 7259 2009.
@inproceedings{8ec30e3c7c2340aa8cd36000fbe2720c,
title = "Pulmonary airways tree segmentation from CT examinations using adaptive volume of interest",
abstract = "Airways tree segmentation is an important step in quantitatively assessing the severity of and changes in several lung diseases such as chronic obstructive pulmonary disease (COPD), asthma, and cystic fibrosis. It can also be used in guiding bronchoscopy. The purpose of this study is to develop an automated scheme for segmenting the airways tree structure depicted on chest CT examinations. After lung volume segmentation, the scheme defines the first cylinder-like volume of interest (VOI) using a series of images depicting the trachea. The scheme then iteratively defines and adds subsequent VOIs using a region growing algorithm combined with adaptively determined thresholds in order to trace possible sections of airways located inside the combined VOI in question. The airway tree segmentation process is automatically terminated after the scheme assesses all defined VOIs in the iteratively assembled VOI list. In this preliminary study, ten CT examinations with 1.25mm section thickness and two different CT image reconstruction kernels ({"}bone{"} and {"}standard{"}) were selected and used to test the proposed airways tree segmentation scheme. The experiment results showed that (1) adopting this approach affectively prevented the scheme from infiltrating into the parenchyma, (2) the proposed method reasonably accurately segmented the airways trees with lower false positive identification rate as compared with other previously reported schemes that are based on 2-D image segmentation and data analyses, and (3) the proposed adaptive, iterative threshold selection method for the region growing step in each identified VOI enables the scheme to segment the airways trees reliably to the 4th generation in this limited dataset with successful segmentation up to the 5th generation in a fraction of the airways tree branches.",
keywords = "3-D region growing, Computed tomography, Pulmonary airways tree segmentation, Threshold selection, Volume of interest",
author = "Park, {Sang Cheol} and Kim, {Won Pil} and Bin Zheng and Leader, {Joseph K.} and Jiantao Pu and Jun Tan and David Gur",
year = "2009",
month = "12",
day = "15",
doi = "10.1117/12.810947",
language = "English (US)",
isbn = "9780819475107",
volume = "7259",
booktitle = "Medical Imaging 2009 - Image Processing",

}

TY - GEN

T1 - Pulmonary airways tree segmentation from CT examinations using adaptive volume of interest

AU - Park, Sang Cheol

AU - Kim, Won Pil

AU - Zheng, Bin

AU - Leader, Joseph K.

AU - Pu, Jiantao

AU - Tan, Jun

AU - Gur, David

PY - 2009/12/15

Y1 - 2009/12/15

N2 - Airways tree segmentation is an important step in quantitatively assessing the severity of and changes in several lung diseases such as chronic obstructive pulmonary disease (COPD), asthma, and cystic fibrosis. It can also be used in guiding bronchoscopy. The purpose of this study is to develop an automated scheme for segmenting the airways tree structure depicted on chest CT examinations. After lung volume segmentation, the scheme defines the first cylinder-like volume of interest (VOI) using a series of images depicting the trachea. The scheme then iteratively defines and adds subsequent VOIs using a region growing algorithm combined with adaptively determined thresholds in order to trace possible sections of airways located inside the combined VOI in question. The airway tree segmentation process is automatically terminated after the scheme assesses all defined VOIs in the iteratively assembled VOI list. In this preliminary study, ten CT examinations with 1.25mm section thickness and two different CT image reconstruction kernels ("bone" and "standard") were selected and used to test the proposed airways tree segmentation scheme. The experiment results showed that (1) adopting this approach affectively prevented the scheme from infiltrating into the parenchyma, (2) the proposed method reasonably accurately segmented the airways trees with lower false positive identification rate as compared with other previously reported schemes that are based on 2-D image segmentation and data analyses, and (3) the proposed adaptive, iterative threshold selection method for the region growing step in each identified VOI enables the scheme to segment the airways trees reliably to the 4th generation in this limited dataset with successful segmentation up to the 5th generation in a fraction of the airways tree branches.

AB - Airways tree segmentation is an important step in quantitatively assessing the severity of and changes in several lung diseases such as chronic obstructive pulmonary disease (COPD), asthma, and cystic fibrosis. It can also be used in guiding bronchoscopy. The purpose of this study is to develop an automated scheme for segmenting the airways tree structure depicted on chest CT examinations. After lung volume segmentation, the scheme defines the first cylinder-like volume of interest (VOI) using a series of images depicting the trachea. The scheme then iteratively defines and adds subsequent VOIs using a region growing algorithm combined with adaptively determined thresholds in order to trace possible sections of airways located inside the combined VOI in question. The airway tree segmentation process is automatically terminated after the scheme assesses all defined VOIs in the iteratively assembled VOI list. In this preliminary study, ten CT examinations with 1.25mm section thickness and two different CT image reconstruction kernels ("bone" and "standard") were selected and used to test the proposed airways tree segmentation scheme. The experiment results showed that (1) adopting this approach affectively prevented the scheme from infiltrating into the parenchyma, (2) the proposed method reasonably accurately segmented the airways trees with lower false positive identification rate as compared with other previously reported schemes that are based on 2-D image segmentation and data analyses, and (3) the proposed adaptive, iterative threshold selection method for the region growing step in each identified VOI enables the scheme to segment the airways trees reliably to the 4th generation in this limited dataset with successful segmentation up to the 5th generation in a fraction of the airways tree branches.

KW - 3-D region growing

KW - Computed tomography

KW - Pulmonary airways tree segmentation

KW - Threshold selection

KW - Volume of interest

UR - http://www.scopus.com/inward/record.url?scp=71649098609&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=71649098609&partnerID=8YFLogxK

U2 - 10.1117/12.810947

DO - 10.1117/12.810947

M3 - Conference contribution

AN - SCOPUS:71649098609

SN - 9780819475107

VL - 7259

BT - Medical Imaging 2009 - Image Processing

ER -