Dissimilarity-based classification of anatomical tree structures

Lauge Sørensen; Pechin Chien Pau Lo; Asger Dirksen; Jens Petersen; Marleen de Bruijne

doi:10.1007/978-3-642-22092-0_39

Dissimilarity-based classification of anatomical tree structures

Lauge Sørensen, Pechin Chien Pau Lo, Asger Dirksen, Jens Petersen, Marleen de Bruijne

Department of Computer Science

5 Citations (Scopus)

Abstract

A novel method for classification of abnormality in anatomical
tree structures is presented. A tree is classified based on direct comparisons
with other trees in a dissimilarity-based classification scheme.
The pair-wise dissimilarity measure between two trees is based on a linear
assignment between the branch feature vectors representing those trees.
Hereby, localized information in the branches is collectively used in classification
and variations in feature values across the tree are taken into
account. An approximate anatomical correspondence between matched
branches can be achieved by including anatomical features in the branch
feature vectors. The proposed approach is applied to classify airway trees
in computed tomography images of subjects with and without chronic
obstructive pulmonary disease (COPD). Using the wall area percentage
(WA%), a common measure of airway abnormality in COPD, as well
as anatomical features to characterize each branch, an area under the
receiver operating characteristic curve of 0.912 is achieved. This is significantly
better than computing the average WA%.

Original language	English
Title of host publication	Information Processing in Medical Imaging : 22nd International Conference, IPMI 2011, Kloster Irsee, Germany, July 3-8, 2011. Proceedings
Editors	Gábor Székely, Horst K. Hahn
Number of pages	11
Publisher	Springer
Publication date	2011
Pages	475-485
ISBN (Print)	978-3-642-22091-3
ISBN (Electronic)	978-3-642-22092-0
DOIs	https://doi.org/10.1007/978-3-642-22092-0_39
Publication status	Published - 2011
Event	22nd International Conference on Information Processing in Medical Imaging - Kloster Irsee, Germany Duration: 3 Jul 2011 → 8 Jul 2011 Conference number: 22

Conference

Conference	22nd International Conference on Information Processing in Medical Imaging
Number	22
Country/Territory	Germany
City	Kloster Irsee
Period	03/07/2011 → 08/07/2011

Series	Lecture notes in computer science
Volume	6801
ISSN	0302-9743

Access to Document

10.1007/978-3-642-22092-0_39

Cite this

Sørensen, L., Lo, P. C. P., Dirksen, A., Petersen, J., & de Bruijne, M. (2011). Dissimilarity-based classification of anatomical tree structures. In G. Székely, & H. K. Hahn (Eds.), Information Processing in Medical Imaging: 22nd International Conference, IPMI 2011, Kloster Irsee, Germany, July 3-8, 2011. Proceedings (pp. 475-485). Springer. Lecture notes in computer science Vol. 6801 https://doi.org/10.1007/978-3-642-22092-0_39

Dissimilarity-based classification of anatomical tree structures. / Sørensen, Lauge; Lo, Pechin Chien Pau; Dirksen, Asger et al.

Information Processing in Medical Imaging: 22nd International Conference, IPMI 2011, Kloster Irsee, Germany, July 3-8, 2011. Proceedings. ed. / Gábor Székely; Horst K. Hahn. Springer, 2011. p. 475-485 (Lecture notes in computer science, Vol. 6801).

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

Sørensen, L, Lo, PCP, Dirksen, A, Petersen, J & de Bruijne, M 2011, Dissimilarity-based classification of anatomical tree structures. in G Székely & HK Hahn (eds), Information Processing in Medical Imaging: 22nd International Conference, IPMI 2011, Kloster Irsee, Germany, July 3-8, 2011. Proceedings. Springer, Lecture notes in computer science, vol. 6801, pp. 475-485, 22nd International Conference on Information Processing in Medical Imaging, Kloster Irsee, Germany, 03/07/2011. https://doi.org/10.1007/978-3-642-22092-0_39

Sørensen L, Lo PCP, Dirksen A, Petersen J , de Bruijne M. Dissimilarity-based classification of anatomical tree structures. In Székely G, Hahn HK, editors, Information Processing in Medical Imaging: 22nd International Conference, IPMI 2011, Kloster Irsee, Germany, July 3-8, 2011. Proceedings. Springer. 2011. p. 475-485. (Lecture notes in computer science, Vol. 6801). doi: 10.1007/978-3-642-22092-0_39

Sørensen, Lauge ; Lo, Pechin Chien Pau ; Dirksen, Asger et al. / Dissimilarity-based classification of anatomical tree structures. Information Processing in Medical Imaging: 22nd International Conference, IPMI 2011, Kloster Irsee, Germany, July 3-8, 2011. Proceedings. editor / Gábor Székely ; Horst K. Hahn. Springer, 2011. pp. 475-485 (Lecture notes in computer science, Vol. 6801).

@inproceedings{48047d40714a4c77a8f6f5442029fc25,

title = "Dissimilarity-based classification of anatomical tree structures",

abstract = "A novel method for classification of abnormality in anatomical tree structures is presented. A tree is classified based on direct comparisons with other trees in a dissimilarity-based classification scheme. The pair-wise dissimilarity measure between two trees is based on a linear assignment between the branch feature vectors representing those trees. Hereby, localized information in the branches is collectively used in classification and variations in feature values across the tree are taken into account. An approximate anatomical correspondence between matched branches can be achieved by including anatomical features in the branch feature vectors. The proposed approach is applied to classify airway trees in computed tomography images of subjects with and without chronic obstructive pulmonary disease (COPD). Using the wall area percentage (WA%), a common measure of airway abnormality in COPD, as well as anatomical features to characterize each branch, an area under the receiver operating characteristic curve of 0.912 is achieved. This is significantly better than computing the average WA%.",

author = "Lauge S{\o}rensen and Lo, {Pechin Chien Pau} and Asger Dirksen and Jens Petersen and {de Bruijne}, Marleen",

year = "2011",

doi = "10.1007/978-3-642-22092-0_39",

language = "English",

isbn = "978-3-642-22091-3",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "475--485",

editor = "{ Sz{\'e}kely}, {G{\'a}bor } and { Hahn}, {Horst K.}",

booktitle = "Information Processing in Medical Imaging",

note = "22nd International Conference on Information Processing in Medical Imaging ; Conference date: 03-07-2011 Through 08-07-2011",

}

TY - GEN

T1 - Dissimilarity-based classification of anatomical tree structures

AU - Sørensen, Lauge

AU - Lo, Pechin Chien Pau

AU - Dirksen, Asger

AU - Petersen, Jens

AU - de Bruijne, Marleen

N1 - Conference code: 22

PY - 2011

Y1 - 2011

N2 - A novel method for classification of abnormality in anatomical tree structures is presented. A tree is classified based on direct comparisons with other trees in a dissimilarity-based classification scheme. The pair-wise dissimilarity measure between two trees is based on a linear assignment between the branch feature vectors representing those trees. Hereby, localized information in the branches is collectively used in classification and variations in feature values across the tree are taken into account. An approximate anatomical correspondence between matched branches can be achieved by including anatomical features in the branch feature vectors. The proposed approach is applied to classify airway trees in computed tomography images of subjects with and without chronic obstructive pulmonary disease (COPD). Using the wall area percentage (WA%), a common measure of airway abnormality in COPD, as well as anatomical features to characterize each branch, an area under the receiver operating characteristic curve of 0.912 is achieved. This is significantly better than computing the average WA%.

AB - A novel method for classification of abnormality in anatomical tree structures is presented. A tree is classified based on direct comparisons with other trees in a dissimilarity-based classification scheme. The pair-wise dissimilarity measure between two trees is based on a linear assignment between the branch feature vectors representing those trees. Hereby, localized information in the branches is collectively used in classification and variations in feature values across the tree are taken into account. An approximate anatomical correspondence between matched branches can be achieved by including anatomical features in the branch feature vectors. The proposed approach is applied to classify airway trees in computed tomography images of subjects with and without chronic obstructive pulmonary disease (COPD). Using the wall area percentage (WA%), a common measure of airway abnormality in COPD, as well as anatomical features to characterize each branch, an area under the receiver operating characteristic curve of 0.912 is achieved. This is significantly better than computing the average WA%.

U2 - 10.1007/978-3-642-22092-0_39

DO - 10.1007/978-3-642-22092-0_39

M3 - Article in proceedings

SN - 978-3-642-22091-3

T3 - Lecture notes in computer science

SP - 475

EP - 485

BT - Information Processing in Medical Imaging

A2 - Székely, Gábor

A2 - Hahn, Horst K.

PB - Springer

T2 - 22nd International Conference on Information Processing in Medical Imaging

Y2 - 3 July 2011 through 8 July 2011

ER -