Aarhus University Seal / Aarhus Universitets segl

Torben Ellegaard Lund

Visualization of nonlinear classification models in neuroimaging: Signed sensitivity maps

Research output: Contribution to book/anthology/report/proceedingArticle in proceedingsResearchpeer-review

Standard

Visualization of nonlinear classification models in neuroimaging : Signed sensitivity maps. / Rasmussen, Peter Mondrup; Madsen, K.H.; Hansen, L.K.; Lund, T.E.; Schmah, T.; Yourganov, G.; Strother, S.C.

BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing. 2012. p. 254-263.

Research output: Contribution to book/anthology/report/proceedingArticle in proceedingsResearchpeer-review

Harvard

Rasmussen, PM, Madsen, KH, Hansen, LK, Lund, TE, Schmah, T, Yourganov, G & Strother, SC 2012, Visualization of nonlinear classification models in neuroimaging: Signed sensitivity maps. in BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing. pp. 254-263.

APA

Rasmussen, P. M., Madsen, K. H., Hansen, L. K., Lund, T. E., Schmah, T., Yourganov, G., & Strother, S. C. (2012). Visualization of nonlinear classification models in neuroimaging: Signed sensitivity maps. In BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing (pp. 254-263)

CBE

Rasmussen PM, Madsen KH, Hansen LK, Lund TE, Schmah T, Yourganov G, Strother SC. 2012. Visualization of nonlinear classification models in neuroimaging: Signed sensitivity maps. In BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing. pp. 254-263.

MLA

Rasmussen, Peter Mondrup et al. "Visualization of nonlinear classification models in neuroimaging: Signed sensitivity maps". BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing. 2012, 254-263.

Vancouver

Rasmussen PM, Madsen KH, Hansen LK, Lund TE, Schmah T, Yourganov G et al. Visualization of nonlinear classification models in neuroimaging: Signed sensitivity maps. In BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing. 2012. p. 254-263

Author

Rasmussen, Peter Mondrup ; Madsen, K.H. ; Hansen, L.K. ; Lund, T.E. ; Schmah, T. ; Yourganov, G. ; Strother, S.C. / Visualization of nonlinear classification models in neuroimaging : Signed sensitivity maps. BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing. 2012. pp. 254-263

Bibtex

@inproceedings{25e10c248600489ba5afaf4009e63247,
title = "Visualization of nonlinear classification models in neuroimaging: Signed sensitivity maps",
abstract = "Classification models are becoming increasing popular tools in the analysis of neuroimaging data sets. Besides obtaining good prediction accuracy, a competing goal is to interpret how the classifier works. From a neuroscientific perspective, we are interested in the brain pattern reflecting the underlying neural encoding of an experiment defining multiple brain states. In this relation there is a great desire for the researcher to generate brain maps, that highlight brain locations of importance to the classifiers decisions. Based on sensitivity analysis, we develop further procedures for model visualization. Specifically we focus on the generation of summary maps of a nonlinear classifier, that reveal how the classifier works in different parts of the input domain. Each of the maps includes sign information, unlike earlier related methods. The sign information allows the researcher to assess in which direction the individual locations influence the classification. We illustrate the visualization procedure on a real data from a simple functional magnetic resonance imaging experiment.",
author = "Rasmussen, {Peter Mondrup} and K.H. Madsen and L.K. Hansen and T.E. Lund and T. Schmah and G. Yourganov and S.C. Strother",
year = "2012",
month = jan,
day = "1",
language = "English",
pages = "254--263",
booktitle = "BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing",

}

RIS

TY - GEN

T1 - Visualization of nonlinear classification models in neuroimaging

T2 - Signed sensitivity maps

AU - Rasmussen, Peter Mondrup

AU - Madsen, K.H.

AU - Hansen, L.K.

AU - Lund, T.E.

AU - Schmah, T.

AU - Yourganov, G.

AU - Strother, S.C.

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Classification models are becoming increasing popular tools in the analysis of neuroimaging data sets. Besides obtaining good prediction accuracy, a competing goal is to interpret how the classifier works. From a neuroscientific perspective, we are interested in the brain pattern reflecting the underlying neural encoding of an experiment defining multiple brain states. In this relation there is a great desire for the researcher to generate brain maps, that highlight brain locations of importance to the classifiers decisions. Based on sensitivity analysis, we develop further procedures for model visualization. Specifically we focus on the generation of summary maps of a nonlinear classifier, that reveal how the classifier works in different parts of the input domain. Each of the maps includes sign information, unlike earlier related methods. The sign information allows the researcher to assess in which direction the individual locations influence the classification. We illustrate the visualization procedure on a real data from a simple functional magnetic resonance imaging experiment.

AB - Classification models are becoming increasing popular tools in the analysis of neuroimaging data sets. Besides obtaining good prediction accuracy, a competing goal is to interpret how the classifier works. From a neuroscientific perspective, we are interested in the brain pattern reflecting the underlying neural encoding of an experiment defining multiple brain states. In this relation there is a great desire for the researcher to generate brain maps, that highlight brain locations of importance to the classifiers decisions. Based on sensitivity analysis, we develop further procedures for model visualization. Specifically we focus on the generation of summary maps of a nonlinear classifier, that reveal how the classifier works in different parts of the input domain. Each of the maps includes sign information, unlike earlier related methods. The sign information allows the researcher to assess in which direction the individual locations influence the classification. We illustrate the visualization procedure on a real data from a simple functional magnetic resonance imaging experiment.

UR - http://www.scopus.com/inward/record.url?scp=84861974541&partnerID=8YFLogxK

M3 - Article in proceedings

AN - SCOPUS:84861974541

SP - 254

EP - 263

BT - BIOSIGNALS 2012 - Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing

ER -