Image dissimilarity-based quantification of lung disease from CT

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

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

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.

OriginalsprogEngelsk
TitelMedical Image Computing and Computer-Assisted Intervention - MICCAI 2010 : 13th International Conference, Beijing, China, September 20-24, 2010, Proceedings, Part I
RedaktørerTianzi Jiang, Nassir Navab, Josien P. W. Pluim, Max A. Viergever
Antal sider8
Vol/bindPart I
ForlagSpringer
Publikationsdato2010
Sider37-44
ISBN (Trykt)978-3-642-15704-2
ISBN (Elektronisk)978-3-642-15705-9
DOI
StatusUdgivet - 2010
Begivenhed13th International Conference on Medical Image Computing and Computer Assisted Intervention - Beijing, Kina
Varighed: 20 sep. 201024 sep. 2010
Konferencens nummer: 13

Konference

Konference13th International Conference on Medical Image Computing and Computer Assisted Intervention
Nummer13
LandKina
ByBeijing
Periode20/09/201024/09/2010
NavnLecture notes in computer science
Nummer6361
ISSN0302-9743

ID: 19823761