Forskning ved Københavns Universitet - Københavns Universitet

Forside

Segmentation of anatomical structures in chest radiographs using supervised methods: A comparative study on a public database

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningfagfællebedømt

Standard

Segmentation of anatomical structures in chest radiographs using supervised methods: A comparative study on a public database. / van Ginneken, Bram; Stegmann, Mikkel B.; Loog, Marco.

I: Medical Image Analysis, Bind 10, Nr. 1, 2006, s. 19-40.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningfagfællebedømt

Harvard

van Ginneken, B, Stegmann, MB & Loog, M 2006, 'Segmentation of anatomical structures in chest radiographs using supervised methods: A comparative study on a public database', Medical Image Analysis, bind 10, nr. 1, s. 19-40. https://doi.org/10.1016/j.media.2005.02.002

APA

van Ginneken, B., Stegmann, M. B., & Loog, M. (2006). Segmentation of anatomical structures in chest radiographs using supervised methods: A comparative study on a public database. Medical Image Analysis, 10(1), 19-40. https://doi.org/10.1016/j.media.2005.02.002

Vancouver

van Ginneken B, Stegmann MB, Loog M. Segmentation of anatomical structures in chest radiographs using supervised methods: A comparative study on a public database. Medical Image Analysis. 2006;10(1):19-40. https://doi.org/10.1016/j.media.2005.02.002

Author

van Ginneken, Bram ; Stegmann, Mikkel B. ; Loog, Marco. / Segmentation of anatomical structures in chest radiographs using supervised methods: A comparative study on a public database. I: Medical Image Analysis. 2006 ; Bind 10, Nr. 1. s. 19-40.

Bibtex

@article{42a71fa0474411ddb7b4000ea68e967b,
title = "Segmentation of anatomical structures in chest radiographs using supervised methods: A comparative study on a public database",
abstract = "The task of segmenting the lung fields, the heart, and the clavicles in standard posterior–anterior chest radiographs is considered. Three supervised segmentation methods are compared: active shape models, active appearance models and a multi-resolution pixel classification method that employs a multi-scale filter bank of Gaussian derivatives and a k-nearest-neighbors classifier. The methods have been tested on a publicly available database of 247 chest radiographs, in which all objects have been manually segmented by two human observers.A parameter optimization for active shape models is presented, and it is shown that this optimization improves performance significantly. It is demonstrated that the standard active appearance model scheme performs poorly, but large improvements can be obtained by including areas outside the objects into the model.For lung field segmentation, all methods perform well, with pixel classification giving the best results: a paired t-test showed no significant performance difference between pixel classification and an independent human observer. For heart segmentation, all methods perform comparably, but significantly worse than a human observer. Clavicle segmentation is a hard problem for all methods; best results are obtained with active shape models, but human performance is substantially better.In addition, several hybrid systems are investigated. For heart segmentation, where the separate systems perform comparably, significantly better performance can be obtained by combining the results with majority voting.As an application, the cardio-thoracic ratio is computed automatically from the segmentation results. Bland and Altman plots indicate that all methods perform well when compared to the gold standard, with confidence intervals from pixel classification and active appearance modeling very close to those of a human observer.All results, including the manual segmentations, have been made publicly available to facilitate future comparative studies.",
author = "{van Ginneken}, Bram and Stegmann, {Mikkel B.} and Marco Loog",
note = "Paper id:: 10.1016/j.media.2005.02.002",
year = "2006",
doi = "10.1016/j.media.2005.02.002",
language = "English",
volume = "10",
pages = "19--40",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",
number = "1",

}

RIS

TY - JOUR

T1 - Segmentation of anatomical structures in chest radiographs using supervised methods: A comparative study on a public database

AU - van Ginneken, Bram

AU - Stegmann, Mikkel B.

AU - Loog, Marco

N1 - Paper id:: 10.1016/j.media.2005.02.002

PY - 2006

Y1 - 2006

N2 - The task of segmenting the lung fields, the heart, and the clavicles in standard posterior–anterior chest radiographs is considered. Three supervised segmentation methods are compared: active shape models, active appearance models and a multi-resolution pixel classification method that employs a multi-scale filter bank of Gaussian derivatives and a k-nearest-neighbors classifier. The methods have been tested on a publicly available database of 247 chest radiographs, in which all objects have been manually segmented by two human observers.A parameter optimization for active shape models is presented, and it is shown that this optimization improves performance significantly. It is demonstrated that the standard active appearance model scheme performs poorly, but large improvements can be obtained by including areas outside the objects into the model.For lung field segmentation, all methods perform well, with pixel classification giving the best results: a paired t-test showed no significant performance difference between pixel classification and an independent human observer. For heart segmentation, all methods perform comparably, but significantly worse than a human observer. Clavicle segmentation is a hard problem for all methods; best results are obtained with active shape models, but human performance is substantially better.In addition, several hybrid systems are investigated. For heart segmentation, where the separate systems perform comparably, significantly better performance can be obtained by combining the results with majority voting.As an application, the cardio-thoracic ratio is computed automatically from the segmentation results. Bland and Altman plots indicate that all methods perform well when compared to the gold standard, with confidence intervals from pixel classification and active appearance modeling very close to those of a human observer.All results, including the manual segmentations, have been made publicly available to facilitate future comparative studies.

AB - The task of segmenting the lung fields, the heart, and the clavicles in standard posterior–anterior chest radiographs is considered. Three supervised segmentation methods are compared: active shape models, active appearance models and a multi-resolution pixel classification method that employs a multi-scale filter bank of Gaussian derivatives and a k-nearest-neighbors classifier. The methods have been tested on a publicly available database of 247 chest radiographs, in which all objects have been manually segmented by two human observers.A parameter optimization for active shape models is presented, and it is shown that this optimization improves performance significantly. It is demonstrated that the standard active appearance model scheme performs poorly, but large improvements can be obtained by including areas outside the objects into the model.For lung field segmentation, all methods perform well, with pixel classification giving the best results: a paired t-test showed no significant performance difference between pixel classification and an independent human observer. For heart segmentation, all methods perform comparably, but significantly worse than a human observer. Clavicle segmentation is a hard problem for all methods; best results are obtained with active shape models, but human performance is substantially better.In addition, several hybrid systems are investigated. For heart segmentation, where the separate systems perform comparably, significantly better performance can be obtained by combining the results with majority voting.As an application, the cardio-thoracic ratio is computed automatically from the segmentation results. Bland and Altman plots indicate that all methods perform well when compared to the gold standard, with confidence intervals from pixel classification and active appearance modeling very close to those of a human observer.All results, including the manual segmentations, have been made publicly available to facilitate future comparative studies.

U2 - 10.1016/j.media.2005.02.002

DO - 10.1016/j.media.2005.02.002

M3 - Journal article

C2 - 15919232

VL - 10

SP - 19

EP - 40

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

IS - 1

ER -

ID: 4850591