Towards exaggerated emphysema stereotypes

Chen Chen, Lauge Sørensen, Francois Bernard Lauze, Christian Igel, Marco Loog, Aasa Feragen, Marleen de Bruijne, Mads Nielsen

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningpeer review

1 Citationer (Scopus)

Abstract

We introduce the notion of an exaggerated image stereotype for some image class of interest, which emphasizes/exaggerates the characteristic patterns in an image class and visualizes what visual information the classication relies on. This is useful for gaining insight into the classi cation and serves for comparison with thebiological models of disease.
We build the exaggerated image stereotypes by optimizing an objective function which consists of a discriminativeterm based on the classi cation accuracy, and a generative term based on the class distribution. Agradient descent method is employed for optimization. We use this idea with Fisher's Linear Discriminant rule,and assume a multivariate normal distribution for samples within a class. The proposed framework is appliedto computed tomography (CT) images of lung tissue with emphysema. The synthesized stereotypes illustratethe exaggerated patterns of lung tissue with emphysema, which is underpinned by three di erent quantitativeevaluation methods.
OriginalsprogEngelsk
TitelMedical Imaging 2012 : Computer-Aided Diagnosis
RedaktørerBram van Ginneken, Carol L. Novak
Antal sider13
ForlagSPIE - International Society for Optical Engineering
Publikationsdato2012
Artikelnummer83150Q
ISBN (Trykt)9780819489647
DOI
StatusUdgivet - 2012
BegivenhedMedical Imaging 2012: Computer-Aided Diagnosis - San Diego, California, USA
Varighed: 4 feb. 20129 feb. 2012

Konference

KonferenceMedical Imaging 2012: Computer-Aided Diagnosis
Land/OmrådeUSA
BySan Diego, California
Periode04/02/201209/02/2012
NavnProceedings of S P I E - International Society for Optical Engineering
Vol/bind7964
ISSN0277-768X
NavnProgress in Biomedical Optics and Imaging
Nummer31
Vol/bind13
ISSN1605-7422

Citationsformater