schliessen

Filtern

 

Bibliotheken

A Fully Automatic Method for Lung Parenchyma Segmentation and Repairing

Considering that the traditional lung segmentation algorithms are not adaptive for the situations that most of the juxtapleural nodules, which are excluded as fat, and lung are not segmented perfectly. In this paper, several methods are comprehensively utilized including optimal iterative threshold,... Full description

Journal Title: Journal of Digital Imaging 2013, Vol.26(3), pp.483-495
Main Author: Wei, Ying
Other Authors: Shen, Guo , Li, Juan-juan
Format: Electronic Article Electronic Article
Language: English
Subjects:
ID: ISSN: 0897-1889 ; E-ISSN: 1618-727X ; DOI: 10.1007/s10278-012-9528-9
Link: http://dx.doi.org/10.1007/s10278-012-9528-9
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: springer_jour10.1007/s10278-012-9528-9
title: A Fully Automatic Method for Lung Parenchyma Segmentation and Repairing
format: Article
creator:
  • Wei, Ying
  • Shen, Guo
  • Li, Juan-juan
subjects:
  • Computer-aided diagnosis
  • Thoracic CT image
  • Lung parenchyma
  • Segmentation
  • Repairing
  • Improved chain code
  • Bresenham algorithms
ispartof: Journal of Digital Imaging, 2013, Vol.26(3), pp.483-495
description: Considering that the traditional lung segmentation algorithms are not adaptive for the situations that most of the juxtapleural nodules, which are excluded as fat, and lung are not segmented perfectly. In this paper, several methods are comprehensively utilized including optimal iterative threshold, three-dimensional connectivity labeling, three-dimensional region growing for the initial segmentation of the lung parenchyma, based on improved chain code, and Bresenham algorithms to repair the lung parenchyma. The paper thus proposes a fully automatic method for lung parenchyma segmentation and repairing. Ninety-seven lung nodule thoracic computed tomography scans and 25 juxtapleural nodule scans are used to test the proposed method and compare with the most-cited rolling-ball method. Experimental results show that the algorithm can segment lung parenchyma region automatically and accurately. The sensitivity of juxtapleural nodule inclusion is 100 %, the segmentation accuracy of juxtapleural nodule regions is 98.6 %, segmentation accuracy of lung parenchyma is more than 95.2 %, and the average segmentation time is 0.67 s/frame. The algorithm can achieve good results for lung parenchyma segmentation and repairing in various cases that nodules/tumors adhere to lung wall.
language: eng
source:
identifier: ISSN: 0897-1889 ; E-ISSN: 1618-727X ; DOI: 10.1007/s10278-012-9528-9
fulltext: fulltext
issn:
  • 1618-727X
  • 1618727X
  • 0897-1889
  • 08971889
url: Link


@attributes
ID651212404
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordid10.1007/s10278-012-9528-9
sourceidspringer_jour
recordidTN_springer_jour10.1007/s10278-012-9528-9
sourcesystemPC
pqid1372612870
galeid329851775
display
typearticle
titleA Fully Automatic Method for Lung Parenchyma Segmentation and Repairing
creatorWei, Ying ; Shen, Guo ; Li, Juan-juan
ispartofJournal of Digital Imaging, 2013, Vol.26(3), pp.483-495
identifier
subjectComputer-aided diagnosis ; Thoracic CT image ; Lung parenchyma ; Segmentation ; Repairing ; Improved chain code ; Bresenham algorithms
descriptionConsidering that the traditional lung segmentation algorithms are not adaptive for the situations that most of the juxtapleural nodules, which are excluded as fat, and lung are not segmented perfectly. In this paper, several methods are comprehensively utilized including optimal iterative threshold, three-dimensional connectivity labeling, three-dimensional region growing for the initial segmentation of the lung parenchyma, based on improved chain code, and Bresenham algorithms to repair the lung parenchyma. The paper thus proposes a fully automatic method for lung parenchyma segmentation and repairing. Ninety-seven lung nodule thoracic computed tomography scans and 25 juxtapleural nodule scans are used to test the proposed method and compare with the most-cited rolling-ball method. Experimental results show that the algorithm can segment lung parenchyma region automatically and accurately. The sensitivity of juxtapleural nodule inclusion is 100 %, the segmentation accuracy of juxtapleural nodule regions is 98.6 %, segmentation accuracy of lung parenchyma is more than 95.2 %, and the average segmentation time is 0.67 s/frame. The algorithm can achieve good results for lung parenchyma segmentation and repairing in various cases that nodules/tumors adhere to lung wall.
languageeng
source
version8
lds50peer_reviewed
links
openurl$$Topenurl_article
openurlfulltext$$Topenurlfull_article
backlink$$Uhttp://dx.doi.org/10.1007/s10278-012-9528-9$$EView_full_text_in_Springer_(Subscribers_only)
search
creatorcontrib
0Wei, Ying
1Shen, Guo
2Li, Juan-juan
titleA Fully Automatic Method for Lung Parenchyma Segmentation and Repairing
descriptionConsidering that the traditional lung segmentation algorithms are not adaptive for the situations that most of the juxtapleural nodules, which are excluded as fat, and lung are not segmented perfectly. In this paper, several methods are comprehensively utilized including optimal iterative threshold, three-dimensional connectivity labeling, three-dimensional region growing for the initial segmentation of the lung parenchyma, based on improved chain code, and Bresenham algorithms to repair the lung parenchyma. The paper thus proposes a fully automatic method for lung parenchyma segmentation and repairing. Ninety-seven lung nodule thoracic computed tomography scans and 25 juxtapleural nodule scans are used to test the proposed method and compare with the most-cited rolling-ball method. Experimental results show that the algorithm can segment lung parenchyma region automatically and accurately. The sensitivity of juxtapleural nodule inclusion is 100 %, the segmentation accuracy of juxtapleural nodule regions is 98.6 %, segmentation accuracy of lung parenchyma is more than 95.2 %, and the average segmentation time is 0.67 s/frame. The algorithm can achieve good results for lung parenchyma segmentation and repairing in various cases that nodules/tumors adhere to lung wall.
subject
0Computer-aided diagnosis
1Thoracic CT image
2Lung parenchyma
3Segmentation
4Repairing
5Improved chain code
6Bresenham algorithms
general
010.1007/s10278-012-9528-9
1English
2Springer Science & Business Media B.V.
3SpringerLink
sourceidspringer_jour
recordidspringer_jour10.1007/s10278-012-9528-9
issn
01618-727X
11618727X
20897-1889
308971889
rsrctypearticle
creationdate2013
addtitle
0Journal of Digital Imaging
1The Journal of the Society for Computer Applications in Radiology
2J Digit Imaging
searchscopespringer_journals_complete
scopespringer_journals_complete
lsr30VSR-Enriched:[pages, pqid, galeid]
sort
titleA Fully Automatic Method for Lung Parenchyma Segmentation and Repairing
authorWei, Ying ; Shen, Guo ; Li, Juan-juan
creationdate20130600
facets
frbrgroupid9133453372650006734
frbrtype5
languageeng
creationdate2013
topic
0Computer-Aided Diagnosis
1Thoracic Ct Image
2Lung Parenchyma
3Segmentation
4Repairing
5Improved Chain Code
6Bresenham Algorithms
collectionSpringerLink
prefilterarticles
rsrctypearticles
creatorcontrib
0Wei, Ying
1Shen, Guo
2Li, Juan-juan
jtitleJournal Of Digital Imaging
toplevelpeer_reviewed
delivery
delcategoryRemote Search Resource
fulltextfulltext
addata
aulast
0Wei
1Shen
2Li
aufirst
0Ying
1Guo
2Juan-juan
au
0Wei, Ying
1Shen, Guo
2Li, Juan-juan
atitleA Fully Automatic Method for Lung Parenchyma Segmentation and Repairing
jtitleJournal of Digital Imaging
stitleJ Digit Imaging
addtitleThe Journal of the Society for Computer Applications in Radiology
risdate201306
volume26
issue3
spage483
epage495
issn0897-1889
eissn1618-727X
genrearticle
ristypeJOUR
abstractConsidering that the traditional lung segmentation algorithms are not adaptive for the situations that most of the juxtapleural nodules, which are excluded as fat, and lung are not segmented perfectly. In this paper, several methods are comprehensively utilized including optimal iterative threshold, three-dimensional connectivity labeling, three-dimensional region growing for the initial segmentation of the lung parenchyma, based on improved chain code, and Bresenham algorithms to repair the lung parenchyma. The paper thus proposes a fully automatic method for lung parenchyma segmentation and repairing. Ninety-seven lung nodule thoracic computed tomography scans and 25 juxtapleural nodule scans are used to test the proposed method and compare with the most-cited rolling-ball method. Experimental results show that the algorithm can segment lung parenchyma region automatically and accurately. The sensitivity of juxtapleural nodule inclusion is 100 %, the segmentation accuracy of juxtapleural nodule regions is 98.6 %, segmentation accuracy of lung parenchyma is more than 95.2 %, and the average segmentation time is 0.67 s/frame. The algorithm can achieve good results for lung parenchyma segmentation and repairing in various cases that nodules/tumors adhere to lung wall.
copNew York
pubSpringer-Verlag
doi10.1007/s10278-012-9528-9
pages483-495
date2013-06