An improved algorithm for computerized detection and quantification of pulmonary emphysema at high resolution computed tomography (HRCT)

Ulf Tylen, O. Friman, M. Borga, J. E. Angelhed

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

6 Citations (Scopus)

Abstract

Emphysema is characterized by destruction of lung tissue with development of small or large holes within the lung. These areas will have Hounsfield values (HU) approaching -1000. It is possible to detect and quantificate such areas using simple density mask technique. The edge enhancement reconstruction algorithm, gravity and motion of the heart and vessels during scanning causes artefacts, however. The purpose of our work was to construct an algorithm that detects such image artefacts and corrects them. The first step is to apply inverse filtering to the image removing much of the effect of the edge enhancement reconstruction algorithm. The next step implies computation of the antero-posterior density gradient caused by gravity and correction for that. Motion artefacts are in a third step corrected for by use of normalized averaging, thresholding and region growing. Twenty healthy volunteers were investigated, 10 with slight emphysema and 10 without. Using simple density mask technique it was not possible to separate persons with disease from those without. Our algorithm improved separation of the two groups considerably. Our algorithm needs further refinement, but may form a basis for further development of methods for computerized diagnosis and quantification of emphysema by HRCT.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsC. Chen, A.V. Clough
Pages254-262
Number of pages9
Volume4321
DOIs
StatePublished - 2001
Externally publishedYes
EventMedical Imaging 2001: Physiology and Function from Multidimensional Images - Sandiego, CA, United States
Duration: Feb 18 2001Feb 20 2001

Other

OtherMedical Imaging 2001: Physiology and Function from Multidimensional Images
CountryUnited States
CitySandiego, CA
Period2/18/012/20/01

Fingerprint

emphysema
Tomography
tomography
high resolution
artifacts
lungs
Masks
Gravitation
masks
gravitation
augmentation
destruction
vessels
Tissue
Scanning
gradients
scanning
causes

Keywords

  • Algorithms
  • Computed tomography
  • Computer assisted image processing
  • Pulmonary emphysema
  • Quantification

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Tylen, U., Friman, O., Borga, M., & Angelhed, J. E. (2001). An improved algorithm for computerized detection and quantification of pulmonary emphysema at high resolution computed tomography (HRCT). In C. Chen, & A. V. Clough (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 4321, pp. 254-262) https://doi.org/10.1117/12.428144

An improved algorithm for computerized detection and quantification of pulmonary emphysema at high resolution computed tomography (HRCT). / Tylen, Ulf; Friman, O.; Borga, M.; Angelhed, J. E.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / C. Chen; A.V. Clough. Vol. 4321 2001. p. 254-262.

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

Tylen, U, Friman, O, Borga, M & Angelhed, JE 2001, An improved algorithm for computerized detection and quantification of pulmonary emphysema at high resolution computed tomography (HRCT). in C Chen & AV Clough (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 4321, pp. 254-262, Medical Imaging 2001: Physiology and Function from Multidimensional Images, Sandiego, CA, United States, 2/18/01. https://doi.org/10.1117/12.428144
Tylen U, Friman O, Borga M, Angelhed JE. An improved algorithm for computerized detection and quantification of pulmonary emphysema at high resolution computed tomography (HRCT). In Chen C, Clough AV, editors, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 4321. 2001. p. 254-262 https://doi.org/10.1117/12.428144
Tylen, Ulf ; Friman, O. ; Borga, M. ; Angelhed, J. E. / An improved algorithm for computerized detection and quantification of pulmonary emphysema at high resolution computed tomography (HRCT). Proceedings of SPIE - The International Society for Optical Engineering. editor / C. Chen ; A.V. Clough. Vol. 4321 2001. pp. 254-262
@inproceedings{b4d4c4d91562417bbb0fe9202567f245,
title = "An improved algorithm for computerized detection and quantification of pulmonary emphysema at high resolution computed tomography (HRCT)",
abstract = "Emphysema is characterized by destruction of lung tissue with development of small or large holes within the lung. These areas will have Hounsfield values (HU) approaching -1000. It is possible to detect and quantificate such areas using simple density mask technique. The edge enhancement reconstruction algorithm, gravity and motion of the heart and vessels during scanning causes artefacts, however. The purpose of our work was to construct an algorithm that detects such image artefacts and corrects them. The first step is to apply inverse filtering to the image removing much of the effect of the edge enhancement reconstruction algorithm. The next step implies computation of the antero-posterior density gradient caused by gravity and correction for that. Motion artefacts are in a third step corrected for by use of normalized averaging, thresholding and region growing. Twenty healthy volunteers were investigated, 10 with slight emphysema and 10 without. Using simple density mask technique it was not possible to separate persons with disease from those without. Our algorithm improved separation of the two groups considerably. Our algorithm needs further refinement, but may form a basis for further development of methods for computerized diagnosis and quantification of emphysema by HRCT.",
keywords = "Algorithms, Computed tomography, Computer assisted image processing, Pulmonary emphysema, Quantification",
author = "Ulf Tylen and O. Friman and M. Borga and Angelhed, {J. E.}",
year = "2001",
doi = "10.1117/12.428144",
language = "English (US)",
volume = "4321",
pages = "254--262",
editor = "C. Chen and A.V. Clough",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - An improved algorithm for computerized detection and quantification of pulmonary emphysema at high resolution computed tomography (HRCT)

AU - Tylen, Ulf

AU - Friman, O.

AU - Borga, M.

AU - Angelhed, J. E.

PY - 2001

Y1 - 2001

N2 - Emphysema is characterized by destruction of lung tissue with development of small or large holes within the lung. These areas will have Hounsfield values (HU) approaching -1000. It is possible to detect and quantificate such areas using simple density mask technique. The edge enhancement reconstruction algorithm, gravity and motion of the heart and vessels during scanning causes artefacts, however. The purpose of our work was to construct an algorithm that detects such image artefacts and corrects them. The first step is to apply inverse filtering to the image removing much of the effect of the edge enhancement reconstruction algorithm. The next step implies computation of the antero-posterior density gradient caused by gravity and correction for that. Motion artefacts are in a third step corrected for by use of normalized averaging, thresholding and region growing. Twenty healthy volunteers were investigated, 10 with slight emphysema and 10 without. Using simple density mask technique it was not possible to separate persons with disease from those without. Our algorithm improved separation of the two groups considerably. Our algorithm needs further refinement, but may form a basis for further development of methods for computerized diagnosis and quantification of emphysema by HRCT.

AB - Emphysema is characterized by destruction of lung tissue with development of small or large holes within the lung. These areas will have Hounsfield values (HU) approaching -1000. It is possible to detect and quantificate such areas using simple density mask technique. The edge enhancement reconstruction algorithm, gravity and motion of the heart and vessels during scanning causes artefacts, however. The purpose of our work was to construct an algorithm that detects such image artefacts and corrects them. The first step is to apply inverse filtering to the image removing much of the effect of the edge enhancement reconstruction algorithm. The next step implies computation of the antero-posterior density gradient caused by gravity and correction for that. Motion artefacts are in a third step corrected for by use of normalized averaging, thresholding and region growing. Twenty healthy volunteers were investigated, 10 with slight emphysema and 10 without. Using simple density mask technique it was not possible to separate persons with disease from those without. Our algorithm improved separation of the two groups considerably. Our algorithm needs further refinement, but may form a basis for further development of methods for computerized diagnosis and quantification of emphysema by HRCT.

KW - Algorithms

KW - Computed tomography

KW - Computer assisted image processing

KW - Pulmonary emphysema

KW - Quantification

UR - http://www.scopus.com/inward/record.url?scp=0034874241&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034874241&partnerID=8YFLogxK

U2 - 10.1117/12.428144

DO - 10.1117/12.428144

M3 - Conference contribution

VL - 4321

SP - 254

EP - 262

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Chen, C.

A2 - Clough, A.V.

ER -