Combining 2D wavelet edge highlighting and 3D thresholding for lung segmentation in thin-slice CT

Panagiotis Korfiatis, S. Skiadopoulos, P. Sakellaropoulos, C. Kalogeropoulou, Lena Costaridou

Research output: Contribution to journalArticle

61 Citations (Scopus)

Abstract

The first step in lung analysis by CT is the identification of the lung border. To deal with the increased number of sections per scan in thin-slice multidetector CT, it has been crucial to develop accurate and automated lung segmentation algorithms. In this study, an automated method for lung segmentation of thin-slice CT data is presented. The method exploits the advantages of a two-dimensional wavelet edge-highlighting step in lung border delineation. Lung volume segmentation is achieved with three-dimensional (3D) grey level thresholding, using a minimum error technique. 3D thresholding, combined with the wavelet pre-processing step, successfully deals with lung border segmentation challenges, such as anterior or posterior junction lines and juxtapleural nodules. Finally, to deal with mediastinum border undersegmentation, 3D morphological closing with a spherical structural element is applied. The performance of the proposed method is quantitatively assessed on a dataset originating from the Lung Imaging Database Consortium (LIDC) by comparing automatically derived borders with the manually traced ones. Segmentation performance, averaged over left and right lung volumes, for lung volume overlap is 0.983 ± 0.008, whereas for shape differentiation in terms of mean distance it is 0.770 ± 0.251 mm (root mean square distance is 0.520 ± 0.008 mm; maximum distance is 3.327 ± 1.637 mm). The effect of the wavelet pre-processing step was assessed by comparing the proposed method with the 3D thresholding technique (applied on original volume data). This yielded statistically significant differences for all segmentation metrics (p<0.01). Results demonstrate an accurate method that could be used as a first step in computer lung analysis by CT.

Original languageEnglish (US)
Pages (from-to)996-1005
Number of pages10
JournalBritish Journal of Radiology
Volume80
Issue number960
DOIs
StatePublished - Dec 1 2007
Externally publishedYes

Fingerprint

Lung
Mediastinum
Databases

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Combining 2D wavelet edge highlighting and 3D thresholding for lung segmentation in thin-slice CT. / Korfiatis, Panagiotis; Skiadopoulos, S.; Sakellaropoulos, P.; Kalogeropoulou, C.; Costaridou, Lena.

In: British Journal of Radiology, Vol. 80, No. 960, 01.12.2007, p. 996-1005.

Research output: Contribution to journalArticle

Korfiatis, P, Skiadopoulos, S, Sakellaropoulos, P, Kalogeropoulou, C & Costaridou, L 2007, 'Combining 2D wavelet edge highlighting and 3D thresholding for lung segmentation in thin-slice CT', British Journal of Radiology, vol. 80, no. 960, pp. 996-1005. https://doi.org/10.1259/bjr/20861881
Korfiatis, Panagiotis ; Skiadopoulos, S. ; Sakellaropoulos, P. ; Kalogeropoulou, C. ; Costaridou, Lena. / Combining 2D wavelet edge highlighting and 3D thresholding for lung segmentation in thin-slice CT. In: British Journal of Radiology. 2007 ; Vol. 80, No. 960. pp. 996-1005.
@article{6e4f0bfc8744439eba859e02f0174f39,
title = "Combining 2D wavelet edge highlighting and 3D thresholding for lung segmentation in thin-slice CT",
abstract = "The first step in lung analysis by CT is the identification of the lung border. To deal with the increased number of sections per scan in thin-slice multidetector CT, it has been crucial to develop accurate and automated lung segmentation algorithms. In this study, an automated method for lung segmentation of thin-slice CT data is presented. The method exploits the advantages of a two-dimensional wavelet edge-highlighting step in lung border delineation. Lung volume segmentation is achieved with three-dimensional (3D) grey level thresholding, using a minimum error technique. 3D thresholding, combined with the wavelet pre-processing step, successfully deals with lung border segmentation challenges, such as anterior or posterior junction lines and juxtapleural nodules. Finally, to deal with mediastinum border undersegmentation, 3D morphological closing with a spherical structural element is applied. The performance of the proposed method is quantitatively assessed on a dataset originating from the Lung Imaging Database Consortium (LIDC) by comparing automatically derived borders with the manually traced ones. Segmentation performance, averaged over left and right lung volumes, for lung volume overlap is 0.983 ± 0.008, whereas for shape differentiation in terms of mean distance it is 0.770 ± 0.251 mm (root mean square distance is 0.520 ± 0.008 mm; maximum distance is 3.327 ± 1.637 mm). The effect of the wavelet pre-processing step was assessed by comparing the proposed method with the 3D thresholding technique (applied on original volume data). This yielded statistically significant differences for all segmentation metrics (p<0.01). Results demonstrate an accurate method that could be used as a first step in computer lung analysis by CT.",
author = "Panagiotis Korfiatis and S. Skiadopoulos and P. Sakellaropoulos and C. Kalogeropoulou and Lena Costaridou",
year = "2007",
month = "12",
day = "1",
doi = "10.1259/bjr/20861881",
language = "English (US)",
volume = "80",
pages = "996--1005",
journal = "British Journal of Radiology",
issn = "0007-1285",
publisher = "British Institute of Radiology",
number = "960",

}

TY - JOUR

T1 - Combining 2D wavelet edge highlighting and 3D thresholding for lung segmentation in thin-slice CT

AU - Korfiatis, Panagiotis

AU - Skiadopoulos, S.

AU - Sakellaropoulos, P.

AU - Kalogeropoulou, C.

AU - Costaridou, Lena

PY - 2007/12/1

Y1 - 2007/12/1

N2 - The first step in lung analysis by CT is the identification of the lung border. To deal with the increased number of sections per scan in thin-slice multidetector CT, it has been crucial to develop accurate and automated lung segmentation algorithms. In this study, an automated method for lung segmentation of thin-slice CT data is presented. The method exploits the advantages of a two-dimensional wavelet edge-highlighting step in lung border delineation. Lung volume segmentation is achieved with three-dimensional (3D) grey level thresholding, using a minimum error technique. 3D thresholding, combined with the wavelet pre-processing step, successfully deals with lung border segmentation challenges, such as anterior or posterior junction lines and juxtapleural nodules. Finally, to deal with mediastinum border undersegmentation, 3D morphological closing with a spherical structural element is applied. The performance of the proposed method is quantitatively assessed on a dataset originating from the Lung Imaging Database Consortium (LIDC) by comparing automatically derived borders with the manually traced ones. Segmentation performance, averaged over left and right lung volumes, for lung volume overlap is 0.983 ± 0.008, whereas for shape differentiation in terms of mean distance it is 0.770 ± 0.251 mm (root mean square distance is 0.520 ± 0.008 mm; maximum distance is 3.327 ± 1.637 mm). The effect of the wavelet pre-processing step was assessed by comparing the proposed method with the 3D thresholding technique (applied on original volume data). This yielded statistically significant differences for all segmentation metrics (p<0.01). Results demonstrate an accurate method that could be used as a first step in computer lung analysis by CT.

AB - The first step in lung analysis by CT is the identification of the lung border. To deal with the increased number of sections per scan in thin-slice multidetector CT, it has been crucial to develop accurate and automated lung segmentation algorithms. In this study, an automated method for lung segmentation of thin-slice CT data is presented. The method exploits the advantages of a two-dimensional wavelet edge-highlighting step in lung border delineation. Lung volume segmentation is achieved with three-dimensional (3D) grey level thresholding, using a minimum error technique. 3D thresholding, combined with the wavelet pre-processing step, successfully deals with lung border segmentation challenges, such as anterior or posterior junction lines and juxtapleural nodules. Finally, to deal with mediastinum border undersegmentation, 3D morphological closing with a spherical structural element is applied. The performance of the proposed method is quantitatively assessed on a dataset originating from the Lung Imaging Database Consortium (LIDC) by comparing automatically derived borders with the manually traced ones. Segmentation performance, averaged over left and right lung volumes, for lung volume overlap is 0.983 ± 0.008, whereas for shape differentiation in terms of mean distance it is 0.770 ± 0.251 mm (root mean square distance is 0.520 ± 0.008 mm; maximum distance is 3.327 ± 1.637 mm). The effect of the wavelet pre-processing step was assessed by comparing the proposed method with the 3D thresholding technique (applied on original volume data). This yielded statistically significant differences for all segmentation metrics (p<0.01). Results demonstrate an accurate method that could be used as a first step in computer lung analysis by CT.

UR - http://www.scopus.com/inward/record.url?scp=38349000626&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38349000626&partnerID=8YFLogxK

U2 - 10.1259/bjr/20861881

DO - 10.1259/bjr/20861881

M3 - Article

C2 - 18065645

AN - SCOPUS:38349000626

VL - 80

SP - 996

EP - 1005

JO - British Journal of Radiology

JF - British Journal of Radiology

SN - 0007-1285

IS - 960

ER -