Towards exaggerated emphysema stereotypes

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Standard

Towards exaggerated emphysema stereotypes. / Chen, Chen; Sørensen, Lauge; Lauze, Francois Bernard; Igel, Christian; Loog, Marco; Feragen, Aasa; de Bruijne, Marleen; Nielsen, Mads.

Medical Imaging 2012: Computer-Aided Diagnosis. red. / Bram van Ginneken; Carol L. Novak. SPIE - International Society for Optical Engineering, 2012. 83150Q (Proceedings of S P I E - International Society for Optical Engineering, Bind 7964). (Progress in Biomedical Optics and Imaging; Nr. 31, Bind 13).

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Harvard

Chen, C, Sørensen, L, Lauze, FB, Igel, C, Loog, M, Feragen, A, de Bruijne, M & Nielsen, M 2012, Towards exaggerated emphysema stereotypes. i B van Ginneken & CL Novak (red), Medical Imaging 2012: Computer-Aided Diagnosis., 83150Q, SPIE - International Society for Optical Engineering, Proceedings of S P I E - International Society for Optical Engineering, bind 7964, Progress in Biomedical Optics and Imaging, nr. 31, bind 13, Medical Imaging 2012: Computer-Aided Diagnosis, San Diego, California, USA, 04/02/2012. https://doi.org/10.1117/12.911398

APA

Chen, C., Sørensen, L., Lauze, F. B., Igel, C., Loog, M., Feragen, A., ... Nielsen, M. (2012). Towards exaggerated emphysema stereotypes. I B. van Ginneken, & C. L. Novak (red.), Medical Imaging 2012: Computer-Aided Diagnosis [83150Q] SPIE - International Society for Optical Engineering. Proceedings of S P I E - International Society for Optical Engineering, Bind. 7964, Progress in Biomedical Optics and Imaging, Nr. 31, Bind. 13 https://doi.org/10.1117/12.911398

Vancouver

Chen C, Sørensen L, Lauze FB, Igel C, Loog M, Feragen A o.a. Towards exaggerated emphysema stereotypes. I van Ginneken B, Novak CL, red., Medical Imaging 2012: Computer-Aided Diagnosis. SPIE - International Society for Optical Engineering. 2012. 83150Q. (Proceedings of S P I E - International Society for Optical Engineering, Bind 7964). (Progress in Biomedical Optics and Imaging; Nr. 31, Bind 13). https://doi.org/10.1117/12.911398

Author

Chen, Chen ; Sørensen, Lauge ; Lauze, Francois Bernard ; Igel, Christian ; Loog, Marco ; Feragen, Aasa ; de Bruijne, Marleen ; Nielsen, Mads. / Towards exaggerated emphysema stereotypes. Medical Imaging 2012: Computer-Aided Diagnosis. red. / Bram van Ginneken ; Carol L. Novak. SPIE - International Society for Optical Engineering, 2012. (Proceedings of S P I E - International Society for Optical Engineering, Bind 7964). (Progress in Biomedical Optics and Imaging; Nr. 31, Bind 13).

Bibtex

@inproceedings{4450830efd0746e7b548e23949db0e1e,
title = "Towards exaggerated emphysema stereotypes",
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.",
author = "Chen Chen and Lauge S{\o}rensen and Lauze, {Francois Bernard} and Christian Igel and Marco Loog and Aasa Feragen and {de Bruijne}, Marleen and Mads Nielsen",
year = "2012",
doi = "10.1117/12.911398",
language = "English",
isbn = "9780819489647",
series = "Proceedings of S P I E - International Society for Optical Engineering",
publisher = "SPIE - International Society for Optical Engineering",
editor = "{van Ginneken}, Bram and Novak, {Carol L.}",
booktitle = "Medical Imaging 2012",
note = "null ; Conference date: 04-02-2012 Through 09-02-2012",

}

RIS

TY - GEN

T1 - Towards exaggerated emphysema stereotypes

AU - Chen, Chen

AU - Sørensen, Lauge

AU - Lauze, Francois Bernard

AU - Igel, Christian

AU - Loog, Marco

AU - Feragen, Aasa

AU - de Bruijne, Marleen

AU - Nielsen, Mads

PY - 2012

Y1 - 2012

N2 - 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.

AB - 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.

U2 - 10.1117/12.911398

DO - 10.1117/12.911398

M3 - Article in proceedings

SN - 9780819489647

T3 - Proceedings of S P I E - International Society for Optical Engineering

BT - Medical Imaging 2012

A2 - van Ginneken, Bram

A2 - Novak, Carol L.

PB - SPIE - International Society for Optical Engineering

Y2 - 4 February 2012 through 9 February 2012

ER -

ID: 168457099