Automated segmentation of the lungs From High resolution ct images for quantitative study of chronic obstructive pulmonary diseases

Ishita Garg, Ronald A. Karwoski, Jon J. Camp, Brian Jack Bartholmai, Richard A. Robb

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

Abstract

Chronic obstructive pulmonary diseases (COPD) are debilitating conditions of the lung and are the fourth leading cause of death in the United States. Early diagnosis is critical for timely intervention and effective treatment. The ability to quantify particular imaging features of specific pathology and accurately assess progression or response to treatment with current imaging tools is relatively poor. The goal of this project was to develop automated segmentation techniques that would be clinically useful as computer assisted diagnostic tools for COPD. The lungs were segmented using an optimized segmentation threshold and the trachea was segmented using a fixed threshold characteristic of air. The segmented images were smoothed by a morphological close operation using spherical elements of different sizes. The results were compared to other segmentation approaches using an optimized threshold to segment the trachea. Comparison of the segmentation results from 10 datasets showed that the method of trachea segmentation using a fixed air threshold followed by morphological closing with spherical element of size 23×23×5 yielded the best results. Inclusion of greater number of pulmonary vessels in the lung volume is important for the development of computer assisted diagnostic tools because the physiological changes of COPD can result in quantifiable anatomic changes in pulmonary vessels. Using a fixed threshold to segment the trachea removed airways from the lungs to a better extent as compared to using an optimized threshold. Preliminary measurements gathered from patient's CT scans suggest that segmented images can be used for accurate analysis of total lung volume and volumes of regional lung parenchyma. Additionally, reproducible segmentation allows for quantification of specific pathologic features, such as lower intensity pixels, which are characteristic of abnormal air spaces in diseases like emphysema.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
EditorsR.L. Galloway, Jr., K.R. Cleary
Pages5-12
Number of pages8
Volume5744
EditionI
DOIs
StatePublished - 2005
EventMedical Imaging 2005 - Visualization, Image-Guided Procedures, and Display - San Diego, CA, United States
Duration: Feb 13 2005Feb 15 2005

Other

OtherMedical Imaging 2005 - Visualization, Image-Guided Procedures, and Display
CountryUnited States
CitySan Diego, CA
Period2/13/052/15/05

Fingerprint

Pulmonary diseases
Image resolution
Air
Imaging techniques
Computerized tomography
Pathology
Pixels

Keywords

  • Chronic obstructive pulmonary diseases
  • Emphysema
  • High resolution CT
  • Lung segmentation

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Garg, I., Karwoski, R. A., Camp, J. J., Bartholmai, B. J., & Robb, R. A. (2005). Automated segmentation of the lungs From High resolution ct images for quantitative study of chronic obstructive pulmonary diseases. In R. L. Galloway, Jr., & K. R. Cleary (Eds.), Progress in Biomedical Optics and Imaging - Proceedings of SPIE (I ed., Vol. 5744, pp. 5-12). [02] https://doi.org/10.1117/12.595827

Automated segmentation of the lungs From High resolution ct images for quantitative study of chronic obstructive pulmonary diseases. / Garg, Ishita; Karwoski, Ronald A.; Camp, Jon J.; Bartholmai, Brian Jack; Robb, Richard A.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. ed. / R.L. Galloway, Jr.; K.R. Cleary. Vol. 5744 I. ed. 2005. p. 5-12 02.

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

Garg, I, Karwoski, RA, Camp, JJ, Bartholmai, BJ & Robb, RA 2005, Automated segmentation of the lungs From High resolution ct images for quantitative study of chronic obstructive pulmonary diseases. in RL Galloway, Jr. & KR Cleary (eds), Progress in Biomedical Optics and Imaging - Proceedings of SPIE. I edn, vol. 5744, 02, pp. 5-12, Medical Imaging 2005 - Visualization, Image-Guided Procedures, and Display, San Diego, CA, United States, 2/13/05. https://doi.org/10.1117/12.595827
Garg I, Karwoski RA, Camp JJ, Bartholmai BJ, Robb RA. Automated segmentation of the lungs From High resolution ct images for quantitative study of chronic obstructive pulmonary diseases. In Galloway, Jr. RL, Cleary KR, editors, Progress in Biomedical Optics and Imaging - Proceedings of SPIE. I ed. Vol. 5744. 2005. p. 5-12. 02 https://doi.org/10.1117/12.595827
Garg, Ishita ; Karwoski, Ronald A. ; Camp, Jon J. ; Bartholmai, Brian Jack ; Robb, Richard A. / Automated segmentation of the lungs From High resolution ct images for quantitative study of chronic obstructive pulmonary diseases. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. editor / R.L. Galloway, Jr. ; K.R. Cleary. Vol. 5744 I. ed. 2005. pp. 5-12
@inproceedings{ec6d0272caf1482fa68e7fcfa6b68f5b,
title = "Automated segmentation of the lungs From High resolution ct images for quantitative study of chronic obstructive pulmonary diseases",
abstract = "Chronic obstructive pulmonary diseases (COPD) are debilitating conditions of the lung and are the fourth leading cause of death in the United States. Early diagnosis is critical for timely intervention and effective treatment. The ability to quantify particular imaging features of specific pathology and accurately assess progression or response to treatment with current imaging tools is relatively poor. The goal of this project was to develop automated segmentation techniques that would be clinically useful as computer assisted diagnostic tools for COPD. The lungs were segmented using an optimized segmentation threshold and the trachea was segmented using a fixed threshold characteristic of air. The segmented images were smoothed by a morphological close operation using spherical elements of different sizes. The results were compared to other segmentation approaches using an optimized threshold to segment the trachea. Comparison of the segmentation results from 10 datasets showed that the method of trachea segmentation using a fixed air threshold followed by morphological closing with spherical element of size 23×23×5 yielded the best results. Inclusion of greater number of pulmonary vessels in the lung volume is important for the development of computer assisted diagnostic tools because the physiological changes of COPD can result in quantifiable anatomic changes in pulmonary vessels. Using a fixed threshold to segment the trachea removed airways from the lungs to a better extent as compared to using an optimized threshold. Preliminary measurements gathered from patient's CT scans suggest that segmented images can be used for accurate analysis of total lung volume and volumes of regional lung parenchyma. Additionally, reproducible segmentation allows for quantification of specific pathologic features, such as lower intensity pixels, which are characteristic of abnormal air spaces in diseases like emphysema.",
keywords = "Chronic obstructive pulmonary diseases, Emphysema, High resolution CT, Lung segmentation",
author = "Ishita Garg and Karwoski, {Ronald A.} and Camp, {Jon J.} and Bartholmai, {Brian Jack} and Robb, {Richard A.}",
year = "2005",
doi = "10.1117/12.595827",
language = "English (US)",
volume = "5744",
pages = "5--12",
editor = "{Galloway, Jr.}, R.L. and K.R. Cleary",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
edition = "I",

}

TY - GEN

T1 - Automated segmentation of the lungs From High resolution ct images for quantitative study of chronic obstructive pulmonary diseases

AU - Garg, Ishita

AU - Karwoski, Ronald A.

AU - Camp, Jon J.

AU - Bartholmai, Brian Jack

AU - Robb, Richard A.

PY - 2005

Y1 - 2005

N2 - Chronic obstructive pulmonary diseases (COPD) are debilitating conditions of the lung and are the fourth leading cause of death in the United States. Early diagnosis is critical for timely intervention and effective treatment. The ability to quantify particular imaging features of specific pathology and accurately assess progression or response to treatment with current imaging tools is relatively poor. The goal of this project was to develop automated segmentation techniques that would be clinically useful as computer assisted diagnostic tools for COPD. The lungs were segmented using an optimized segmentation threshold and the trachea was segmented using a fixed threshold characteristic of air. The segmented images were smoothed by a morphological close operation using spherical elements of different sizes. The results were compared to other segmentation approaches using an optimized threshold to segment the trachea. Comparison of the segmentation results from 10 datasets showed that the method of trachea segmentation using a fixed air threshold followed by morphological closing with spherical element of size 23×23×5 yielded the best results. Inclusion of greater number of pulmonary vessels in the lung volume is important for the development of computer assisted diagnostic tools because the physiological changes of COPD can result in quantifiable anatomic changes in pulmonary vessels. Using a fixed threshold to segment the trachea removed airways from the lungs to a better extent as compared to using an optimized threshold. Preliminary measurements gathered from patient's CT scans suggest that segmented images can be used for accurate analysis of total lung volume and volumes of regional lung parenchyma. Additionally, reproducible segmentation allows for quantification of specific pathologic features, such as lower intensity pixels, which are characteristic of abnormal air spaces in diseases like emphysema.

AB - Chronic obstructive pulmonary diseases (COPD) are debilitating conditions of the lung and are the fourth leading cause of death in the United States. Early diagnosis is critical for timely intervention and effective treatment. The ability to quantify particular imaging features of specific pathology and accurately assess progression or response to treatment with current imaging tools is relatively poor. The goal of this project was to develop automated segmentation techniques that would be clinically useful as computer assisted diagnostic tools for COPD. The lungs were segmented using an optimized segmentation threshold and the trachea was segmented using a fixed threshold characteristic of air. The segmented images were smoothed by a morphological close operation using spherical elements of different sizes. The results were compared to other segmentation approaches using an optimized threshold to segment the trachea. Comparison of the segmentation results from 10 datasets showed that the method of trachea segmentation using a fixed air threshold followed by morphological closing with spherical element of size 23×23×5 yielded the best results. Inclusion of greater number of pulmonary vessels in the lung volume is important for the development of computer assisted diagnostic tools because the physiological changes of COPD can result in quantifiable anatomic changes in pulmonary vessels. Using a fixed threshold to segment the trachea removed airways from the lungs to a better extent as compared to using an optimized threshold. Preliminary measurements gathered from patient's CT scans suggest that segmented images can be used for accurate analysis of total lung volume and volumes of regional lung parenchyma. Additionally, reproducible segmentation allows for quantification of specific pathologic features, such as lower intensity pixels, which are characteristic of abnormal air spaces in diseases like emphysema.

KW - Chronic obstructive pulmonary diseases

KW - Emphysema

KW - High resolution CT

KW - Lung segmentation

UR - http://www.scopus.com/inward/record.url?scp=23244460713&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=23244460713&partnerID=8YFLogxK

U2 - 10.1117/12.595827

DO - 10.1117/12.595827

M3 - Conference contribution

AN - SCOPUS:23244460713

VL - 5744

SP - 5

EP - 12

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

A2 - Galloway, Jr., R.L.

A2 - Cleary, K.R.

ER -