Texture-based quantification of pulmonary emphysema on high-resolution computed tomography: Comparison with density-based quantification and correlation with pulmonary function test

Yang Shin Park, Joon Beom Seo, Namkug Kim, Eun Jin Chae, Yeon Mok Oh, Sang Do Lee, Youngjoo Lee, Suk Ho Kang

Research output: Contribution to journalArticle

74 Citations (Scopus)

Abstract

PURPOSE: To develop a system for texture-based quantification of emphysema on high-resolution computed tomography (HRCT) and to compare it with density-based quantification in correlation with pulmonary function test (PFT). MATERIALS AND METHODS: Two hundred sixty-one circular regions of interest (ROI) with 16-pixel diameter [66 ROIs representing typical area of normal lung; 69 representing bronchiolitis obliterans (BO); 64, mild emphysema (ME); and 62, severe emphysema (SE)] were used to train the automated classification system based on the Support Vector Machine classifier and on variable texture and shape features. An automated quantification system was developed with a moving ROI in the lung area, which classified each pixel into 4 categories. To validate the system, the HRCT and standard-kernel-reconstructed volumetric CT data of 39 consecutive patients with emphysema were included. Using this system, the whole lung area was evaluated, and the area fractions of each class were calculated (normal lung%, BO%, ME%, SE%, respectively). The emphysema index (EI) of texture-based quantification was defined as follows: (0.3 × ME% + SE%) (TEI). EIs from density-based quantification with a threshold of -950 Hounsfield Units, were measured on both HRCT (DEI_HR_2D) and on volumetric CT (DEI_standard_3D). The agreement between TEI, DEI_HR_2D, and DEI_standard_3D was assessed using interclass correlation coefficients (ICC). Correlation of the results on the TEI with the PFT results was compared with the results of the DEI_standard_3D and the DEI_HR_2D with Spearman's correlation test. To evaluate the contribution of each texture-based quantification lesion (BO%, ME%, SE%) on PFT, multiple linear regression analysis was performed. RESULTS: The calculated TEI (19.71% ± 17.98%) was well correlated with the DEI_standard_3D (19.42% ± 14.30%) (ICC = 0.95), whereas the ICC with DEI_HR_2D (37.22% ± 9.42%) was 0.43. TEI showed better correlation with PFT than DEI_standard_3D or DEI_HR_2D did [R = 0.71 vs. 0.67 vs. 0.61 for forced expiratory volume in 1 second (FEV1)/forced vital capacity (FVC); 0.54 vs. 0.50 vs. 0.43 for diffusing capacity (DLco), respectively]. Multiple linear regression analysis revealed that the BO% and SE% areas were independent determinants of FEV1/FVC, whereas the ME% and the SE% were determinants of DLco. CONCLUSION: Texture-based quantification of emphysema using an automated system showed better correlation with the PFT results than density-based quantification. Separate quantification of the BO, ME, and SE areas showed a different contribution of each component to the FEV1/FVC and the DLco. The proposed system can be successfully used for detailed regional and global evaluation of lung lesions on HRCT scanning for emphysema.

Original languageEnglish
Pages (from-to)395-402
Number of pages8
JournalInvestigative Radiology
Volume43
Issue number6
DOIs
Publication statusPublished - 2008 Jun 1
Externally publishedYes

Fingerprint

Pulmonary Emphysema
Respiratory Function Tests
Emphysema
Tomography
Bronchiolitis Obliterans
Vital Capacity
Forced Expiratory Volume
Lung
Cone-Beam Computed Tomography
Linear Models
Regression Analysis

Keywords

  • Computed tomography
  • Emphysema
  • Quantitative
  • Texture

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Texture-based quantification of pulmonary emphysema on high-resolution computed tomography : Comparison with density-based quantification and correlation with pulmonary function test. / Park, Yang Shin; Seo, Joon Beom; Kim, Namkug; Chae, Eun Jin; Oh, Yeon Mok; Lee, Sang Do; Lee, Youngjoo; Kang, Suk Ho.

In: Investigative Radiology, Vol. 43, No. 6, 01.06.2008, p. 395-402.

Research output: Contribution to journalArticle

Park, Yang Shin ; Seo, Joon Beom ; Kim, Namkug ; Chae, Eun Jin ; Oh, Yeon Mok ; Lee, Sang Do ; Lee, Youngjoo ; Kang, Suk Ho. / Texture-based quantification of pulmonary emphysema on high-resolution computed tomography : Comparison with density-based quantification and correlation with pulmonary function test. In: Investigative Radiology. 2008 ; Vol. 43, No. 6. pp. 395-402.
@article{1577738e905844289eb9c1d98efdbfdd,
title = "Texture-based quantification of pulmonary emphysema on high-resolution computed tomography: Comparison with density-based quantification and correlation with pulmonary function test",
abstract = "PURPOSE: To develop a system for texture-based quantification of emphysema on high-resolution computed tomography (HRCT) and to compare it with density-based quantification in correlation with pulmonary function test (PFT). MATERIALS AND METHODS: Two hundred sixty-one circular regions of interest (ROI) with 16-pixel diameter [66 ROIs representing typical area of normal lung; 69 representing bronchiolitis obliterans (BO); 64, mild emphysema (ME); and 62, severe emphysema (SE)] were used to train the automated classification system based on the Support Vector Machine classifier and on variable texture and shape features. An automated quantification system was developed with a moving ROI in the lung area, which classified each pixel into 4 categories. To validate the system, the HRCT and standard-kernel-reconstructed volumetric CT data of 39 consecutive patients with emphysema were included. Using this system, the whole lung area was evaluated, and the area fractions of each class were calculated (normal lung{\%}, BO{\%}, ME{\%}, SE{\%}, respectively). The emphysema index (EI) of texture-based quantification was defined as follows: (0.3 × ME{\%} + SE{\%}) (TEI). EIs from density-based quantification with a threshold of -950 Hounsfield Units, were measured on both HRCT (DEI_HR_2D) and on volumetric CT (DEI_standard_3D). The agreement between TEI, DEI_HR_2D, and DEI_standard_3D was assessed using interclass correlation coefficients (ICC). Correlation of the results on the TEI with the PFT results was compared with the results of the DEI_standard_3D and the DEI_HR_2D with Spearman's correlation test. To evaluate the contribution of each texture-based quantification lesion (BO{\%}, ME{\%}, SE{\%}) on PFT, multiple linear regression analysis was performed. RESULTS: The calculated TEI (19.71{\%} ± 17.98{\%}) was well correlated with the DEI_standard_3D (19.42{\%} ± 14.30{\%}) (ICC = 0.95), whereas the ICC with DEI_HR_2D (37.22{\%} ± 9.42{\%}) was 0.43. TEI showed better correlation with PFT than DEI_standard_3D or DEI_HR_2D did [R = 0.71 vs. 0.67 vs. 0.61 for forced expiratory volume in 1 second (FEV1)/forced vital capacity (FVC); 0.54 vs. 0.50 vs. 0.43 for diffusing capacity (DLco), respectively]. Multiple linear regression analysis revealed that the BO{\%} and SE{\%} areas were independent determinants of FEV1/FVC, whereas the ME{\%} and the SE{\%} were determinants of DLco. CONCLUSION: Texture-based quantification of emphysema using an automated system showed better correlation with the PFT results than density-based quantification. Separate quantification of the BO, ME, and SE areas showed a different contribution of each component to the FEV1/FVC and the DLco. The proposed system can be successfully used for detailed regional and global evaluation of lung lesions on HRCT scanning for emphysema.",
keywords = "Computed tomography, Emphysema, Quantitative, Texture",
author = "Park, {Yang Shin} and Seo, {Joon Beom} and Namkug Kim and Chae, {Eun Jin} and Oh, {Yeon Mok} and Lee, {Sang Do} and Youngjoo Lee and Kang, {Suk Ho}",
year = "2008",
month = "6",
day = "1",
doi = "10.1097/RLI.0b013e31816901c7",
language = "English",
volume = "43",
pages = "395--402",
journal = "Investigative Radiology",
issn = "0020-9996",
publisher = "Lippincott Williams and Wilkins",
number = "6",

}

TY - JOUR

T1 - Texture-based quantification of pulmonary emphysema on high-resolution computed tomography

T2 - Comparison with density-based quantification and correlation with pulmonary function test

AU - Park, Yang Shin

AU - Seo, Joon Beom

AU - Kim, Namkug

AU - Chae, Eun Jin

AU - Oh, Yeon Mok

AU - Lee, Sang Do

AU - Lee, Youngjoo

AU - Kang, Suk Ho

PY - 2008/6/1

Y1 - 2008/6/1

N2 - PURPOSE: To develop a system for texture-based quantification of emphysema on high-resolution computed tomography (HRCT) and to compare it with density-based quantification in correlation with pulmonary function test (PFT). MATERIALS AND METHODS: Two hundred sixty-one circular regions of interest (ROI) with 16-pixel diameter [66 ROIs representing typical area of normal lung; 69 representing bronchiolitis obliterans (BO); 64, mild emphysema (ME); and 62, severe emphysema (SE)] were used to train the automated classification system based on the Support Vector Machine classifier and on variable texture and shape features. An automated quantification system was developed with a moving ROI in the lung area, which classified each pixel into 4 categories. To validate the system, the HRCT and standard-kernel-reconstructed volumetric CT data of 39 consecutive patients with emphysema were included. Using this system, the whole lung area was evaluated, and the area fractions of each class were calculated (normal lung%, BO%, ME%, SE%, respectively). The emphysema index (EI) of texture-based quantification was defined as follows: (0.3 × ME% + SE%) (TEI). EIs from density-based quantification with a threshold of -950 Hounsfield Units, were measured on both HRCT (DEI_HR_2D) and on volumetric CT (DEI_standard_3D). The agreement between TEI, DEI_HR_2D, and DEI_standard_3D was assessed using interclass correlation coefficients (ICC). Correlation of the results on the TEI with the PFT results was compared with the results of the DEI_standard_3D and the DEI_HR_2D with Spearman's correlation test. To evaluate the contribution of each texture-based quantification lesion (BO%, ME%, SE%) on PFT, multiple linear regression analysis was performed. RESULTS: The calculated TEI (19.71% ± 17.98%) was well correlated with the DEI_standard_3D (19.42% ± 14.30%) (ICC = 0.95), whereas the ICC with DEI_HR_2D (37.22% ± 9.42%) was 0.43. TEI showed better correlation with PFT than DEI_standard_3D or DEI_HR_2D did [R = 0.71 vs. 0.67 vs. 0.61 for forced expiratory volume in 1 second (FEV1)/forced vital capacity (FVC); 0.54 vs. 0.50 vs. 0.43 for diffusing capacity (DLco), respectively]. Multiple linear regression analysis revealed that the BO% and SE% areas were independent determinants of FEV1/FVC, whereas the ME% and the SE% were determinants of DLco. CONCLUSION: Texture-based quantification of emphysema using an automated system showed better correlation with the PFT results than density-based quantification. Separate quantification of the BO, ME, and SE areas showed a different contribution of each component to the FEV1/FVC and the DLco. The proposed system can be successfully used for detailed regional and global evaluation of lung lesions on HRCT scanning for emphysema.

AB - PURPOSE: To develop a system for texture-based quantification of emphysema on high-resolution computed tomography (HRCT) and to compare it with density-based quantification in correlation with pulmonary function test (PFT). MATERIALS AND METHODS: Two hundred sixty-one circular regions of interest (ROI) with 16-pixel diameter [66 ROIs representing typical area of normal lung; 69 representing bronchiolitis obliterans (BO); 64, mild emphysema (ME); and 62, severe emphysema (SE)] were used to train the automated classification system based on the Support Vector Machine classifier and on variable texture and shape features. An automated quantification system was developed with a moving ROI in the lung area, which classified each pixel into 4 categories. To validate the system, the HRCT and standard-kernel-reconstructed volumetric CT data of 39 consecutive patients with emphysema were included. Using this system, the whole lung area was evaluated, and the area fractions of each class were calculated (normal lung%, BO%, ME%, SE%, respectively). The emphysema index (EI) of texture-based quantification was defined as follows: (0.3 × ME% + SE%) (TEI). EIs from density-based quantification with a threshold of -950 Hounsfield Units, were measured on both HRCT (DEI_HR_2D) and on volumetric CT (DEI_standard_3D). The agreement between TEI, DEI_HR_2D, and DEI_standard_3D was assessed using interclass correlation coefficients (ICC). Correlation of the results on the TEI with the PFT results was compared with the results of the DEI_standard_3D and the DEI_HR_2D with Spearman's correlation test. To evaluate the contribution of each texture-based quantification lesion (BO%, ME%, SE%) on PFT, multiple linear regression analysis was performed. RESULTS: The calculated TEI (19.71% ± 17.98%) was well correlated with the DEI_standard_3D (19.42% ± 14.30%) (ICC = 0.95), whereas the ICC with DEI_HR_2D (37.22% ± 9.42%) was 0.43. TEI showed better correlation with PFT than DEI_standard_3D or DEI_HR_2D did [R = 0.71 vs. 0.67 vs. 0.61 for forced expiratory volume in 1 second (FEV1)/forced vital capacity (FVC); 0.54 vs. 0.50 vs. 0.43 for diffusing capacity (DLco), respectively]. Multiple linear regression analysis revealed that the BO% and SE% areas were independent determinants of FEV1/FVC, whereas the ME% and the SE% were determinants of DLco. CONCLUSION: Texture-based quantification of emphysema using an automated system showed better correlation with the PFT results than density-based quantification. Separate quantification of the BO, ME, and SE areas showed a different contribution of each component to the FEV1/FVC and the DLco. The proposed system can be successfully used for detailed regional and global evaluation of lung lesions on HRCT scanning for emphysema.

KW - Computed tomography

KW - Emphysema

KW - Quantitative

KW - Texture

UR - http://www.scopus.com/inward/record.url?scp=44449109945&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44449109945&partnerID=8YFLogxK

U2 - 10.1097/RLI.0b013e31816901c7

DO - 10.1097/RLI.0b013e31816901c7

M3 - Article

C2 - 18496044

AN - SCOPUS:44449109945

VL - 43

SP - 395

EP - 402

JO - Investigative Radiology

JF - Investigative Radiology

SN - 0020-9996

IS - 6

ER -