Image dissimilarity-based quantification of lung disease from CT

Lauge Sørensen; Marco Loog; Pechin Chien Pau Lo; Haseem Ashraf; Asger Dirksen; Robert P. W. Duin; Marleen de Bruijne

doi:10.1007/978-3-642-15705-9_5

Image dissimilarity-based quantification of lung disease from CT

Lauge Sørensen, Marco Loog, Pechin Chien Pau Lo, Haseem Ashraf, Asger Dirksen, Robert P. W. Duin, Marleen de Bruijne

18 Citations (Scopus)

Abstract

In this paper, we propose to classify medical images using dissimilarities computed between collections of regions of interest. The images are mapped into a dissimilarity space using an image dissimilarity measure, and a standard vector space-based classifier is applied in this space. The classification output of this approach can be used in computer aided-diagnosis problems where the goal is to detect the presence of abnormal regions or to quantify the extent or severity of abnormalities in these regions. The proposed approach is applied to quantify chronic obstructive pulmonary disease in computed tomography (CT) images, achieving an area under the receiver operating characteristic curve of 0.817. This is significantly better compared to combining individual region classifications into an overall image classification, and compared to common computerized quantitative measures in pulmonary CT.

Original language	English
Title of host publication	Medical Image Computing and Computer-Assisted Intervention - MICCAI 2010 : 13th International Conference, Beijing, China, September 20-24, 2010, Proceedings, Part I
Editors	Tianzi Jiang, Nassir Navab, Josien P. W. Pluim, Max A. Viergever
Number of pages	8
Volume	Part I
Publisher	Springer
Publication date	2010
Pages	37-44
ISBN (Print)	978-3-642-15704-2
ISBN (Electronic)	978-3-642-15705-9
DOIs	https://doi.org/10.1007/978-3-642-15705-9_5
Publication status	Published - 2010
Event	13th International Conference on Medical Image Computing and Computer Assisted Intervention - Beijing, China Duration: 20 Sept 2010 → 24 Sept 2010 Conference number: 13

Conference

Conference	13th International Conference on Medical Image Computing and Computer Assisted Intervention
Number	13
Country/Territory	China
City	Beijing
Period	20/09/2010 → 24/09/2010

Series	Lecture notes in computer science
Number	6361
ISSN	0302-9743

Access to Document

10.1007/978-3-642-15705-9_5

10.1007%2F978-3-642-15705-9_5.pdfFinal published version, 166 KB

Cite this

Sørensen, L., Loog, M., Lo, P. C. P., Ashraf, H., Dirksen, A., P. W. Duin, R., & de Bruijne, M. (2010). Image dissimilarity-based quantification of lung disease from CT. In T. Jiang, N. Navab, J. P. W. Pluim, & M. A. Viergever (Eds.), Medical Image Computing and Computer-Assisted Intervention - MICCAI 2010: 13th International Conference, Beijing, China, September 20-24, 2010, Proceedings, Part I (Vol. Part I, pp. 37-44). Springer. Lecture notes in computer science No. 6361 https://doi.org/10.1007/978-3-642-15705-9_5

Image dissimilarity-based quantification of lung disease from CT. / Sørensen, Lauge; Loog, Marco; Lo, Pechin Chien Pau et al.

Medical Image Computing and Computer-Assisted Intervention - MICCAI 2010: 13th International Conference, Beijing, China, September 20-24, 2010, Proceedings, Part I. ed. / Tianzi Jiang; Nassir Navab; Josien P. W. Pluim; Max A. Viergever. Vol. Part I Springer, 2010. p. 37-44 (Lecture notes in computer science; No. 6361).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Sørensen, L, Loog, M, Lo, PCP, Ashraf, H, Dirksen, A, P. W. Duin, R & de Bruijne, M 2010, Image dissimilarity-based quantification of lung disease from CT. in T Jiang, N Navab, JPW Pluim & MA Viergever (eds), Medical Image Computing and Computer-Assisted Intervention - MICCAI 2010: 13th International Conference, Beijing, China, September 20-24, 2010, Proceedings, Part I. vol. Part I, Springer, Lecture notes in computer science, no. 6361, pp. 37-44, 13th International Conference on Medical Image Computing and Computer Assisted Intervention, Beijing, China, 20/09/2010. https://doi.org/10.1007/978-3-642-15705-9_5

Sørensen L, Loog M, Lo PCP, Ashraf H, Dirksen A, P. W. Duin R et al. Image dissimilarity-based quantification of lung disease from CT. In Jiang T, Navab N, Pluim JPW, Viergever MA, editors, Medical Image Computing and Computer-Assisted Intervention - MICCAI 2010: 13th International Conference, Beijing, China, September 20-24, 2010, Proceedings, Part I. Vol. Part I. Springer. 2010. p. 37-44. (Lecture notes in computer science; No. 6361). doi: 10.1007/978-3-642-15705-9_5

Sørensen, Lauge ; Loog, Marco ; Lo, Pechin Chien Pau et al. / Image dissimilarity-based quantification of lung disease from CT. Medical Image Computing and Computer-Assisted Intervention - MICCAI 2010: 13th International Conference, Beijing, China, September 20-24, 2010, Proceedings, Part I. editor / Tianzi Jiang ; Nassir Navab ; Josien P. W. Pluim ; Max A. Viergever. Vol. Part I Springer, 2010. pp. 37-44 (Lecture notes in computer science; No. 6361).

@inproceedings{37bf2280635411df928f000ea68e967b,

title = "Image dissimilarity-based quantification of lung disease from CT",

abstract = "In this paper, we propose to classify medical images using dissimilarities computed between collections of regions of interest. The images are mapped into a dissimilarity space using an image dissimilarity measure, and a standard vector space-based classifier is applied in this space. The classification output of this approach can be used in computer aided-diagnosis problems where the goal is to detect the presence of abnormal regions or to quantify the extent or severity of abnormalities in these regions. The proposed approach is applied to quantify chronic obstructive pulmonary disease in computed tomography (CT) images, achieving an area under the receiver operating characteristic curve of 0.817. This is significantly better compared to combining individual region classifications into an overall image classification, and compared to common computerized quantitative measures in pulmonary CT.",

author = "Lauge S{\o}rensen and Marco Loog and Lo, {Pechin Chien Pau} and Haseem Ashraf and Asger Dirksen and {P. W. Duin}, Robert and {de Bruijne}, Marleen",

year = "2010",

doi = "10.1007/978-3-642-15705-9_5",

language = "English",

isbn = "978-3-642-15704-2",

volume = "Part I",

series = "Lecture notes in computer science",

publisher = "Springer",

number = "6361",

pages = "37--44",

editor = "Tianzi Jiang and Nassir Navab and Pluim, {Josien P. W.} and Viergever, {Max A.}",

booktitle = "Medical Image Computing and Computer-Assisted Intervention - MICCAI 2010",

note = "13th International Conference on Medical Image Computing and Computer Assisted Intervention ; Conference date: 20-09-2010 Through 24-09-2010",

}

TY - GEN

T1 - Image dissimilarity-based quantification of lung disease from CT

AU - Sørensen, Lauge

AU - Loog, Marco

AU - Lo, Pechin Chien Pau

AU - Ashraf, Haseem

AU - Dirksen, Asger

AU - P. W. Duin, Robert

AU - de Bruijne, Marleen

N1 - Conference code: 13

PY - 2010

Y1 - 2010

N2 - In this paper, we propose to classify medical images using dissimilarities computed between collections of regions of interest. The images are mapped into a dissimilarity space using an image dissimilarity measure, and a standard vector space-based classifier is applied in this space. The classification output of this approach can be used in computer aided-diagnosis problems where the goal is to detect the presence of abnormal regions or to quantify the extent or severity of abnormalities in these regions. The proposed approach is applied to quantify chronic obstructive pulmonary disease in computed tomography (CT) images, achieving an area under the receiver operating characteristic curve of 0.817. This is significantly better compared to combining individual region classifications into an overall image classification, and compared to common computerized quantitative measures in pulmonary CT.

AB - In this paper, we propose to classify medical images using dissimilarities computed between collections of regions of interest. The images are mapped into a dissimilarity space using an image dissimilarity measure, and a standard vector space-based classifier is applied in this space. The classification output of this approach can be used in computer aided-diagnosis problems where the goal is to detect the presence of abnormal regions or to quantify the extent or severity of abnormalities in these regions. The proposed approach is applied to quantify chronic obstructive pulmonary disease in computed tomography (CT) images, achieving an area under the receiver operating characteristic curve of 0.817. This is significantly better compared to combining individual region classifications into an overall image classification, and compared to common computerized quantitative measures in pulmonary CT.

U2 - 10.1007/978-3-642-15705-9_5

DO - 10.1007/978-3-642-15705-9_5

M3 - Article in proceedings

SN - 978-3-642-15704-2

VL - Part I

T3 - Lecture notes in computer science

SP - 37

EP - 44

BT - Medical Image Computing and Computer-Assisted Intervention - MICCAI 2010

A2 - Jiang, Tianzi

A2 - Navab, Nassir

A2 - Pluim, Josien P. W.

A2 - Viergever, Max A.

PB - Springer

T2 - 13th International Conference on Medical Image Computing and Computer Assisted Intervention

Y2 - 20 September 2010 through 24 September 2010

ER -

Image dissimilarity-based quantification of lung disease from CT

Abstract

Conference

Access to Document

Fingerprint

Cite this