Visualization of nonlinear kernel models in neuroimaging by sensitivity maps

Research output: Contribution to journalJournal article – Annual report year: 2011Researchpeer-review

Standard

Visualization of nonlinear kernel models in neuroimaging by sensitivity maps. / Rasmussen, Peter Mondrup; Madsen, Kristoffer Hougaard; Lund, Torben Ellegaard; Hansen, Lars Kai.

In: NeuroImage, Vol. 55, No. 3, 2011, p. 1120-1131.

Research output: Contribution to journalJournal article – Annual report year: 2011Researchpeer-review

Harvard

APA

CBE

MLA

Vancouver

Author

Bibtex

@article{6fa711b565ea48ecb62bef5afa8738e6,
title = "Visualization of nonlinear kernel models in neuroimaging by sensitivity maps",
abstract = "There is significant current interest in decoding mental states from neuroimages. In this context kernel methods, e.g., support vector machines (SVM) are frequently adopted to learn statistical relations between patterns of brain activation and experimental conditions. In this paper we focus on visualization of such nonlinear kernel models. Specifically, we investigate the sensitivity map as a technique for generation of global summary maps of kernel classification models. We illustrate the performance of the sensitivity map on functional magnetic resonance (fMRI) data based on visual stimuli. We show that the performance of linear models is reduced for certain scan labelings/categorizations in this data set, while the nonlinear models provide more flexibility. We show that the sensitivity map can be used to visualize nonlinear versions of kernel logistic regression, the kernel Fisher discriminant, and the SVM, and conclude that the sensitivity map is a versatile and computationally efficient tool for visualization of nonlinear kernel models in neuroimaging.",
keywords = "Model visualization, Nonlinear modeling, Support vector machine, Neuroimaging, Multivariate analysis, Sensitivity map, Kernel methods, Machine learning, Pattern analysis",
author = "Rasmussen, {Peter Mondrup} and Madsen, {Kristoffer Hougaard} and Lund, {Torben Ellegaard} and Hansen, {Lars Kai}",
year = "2011",
doi = "10.1016/j.neuroimage.2010.12.035",
language = "English",
volume = "55",
pages = "1120--1131",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Elsevier B.V.",
number = "3",

}

RIS

TY - JOUR

T1 - Visualization of nonlinear kernel models in neuroimaging by sensitivity maps

AU - Rasmussen, Peter Mondrup

AU - Madsen, Kristoffer Hougaard

AU - Lund, Torben Ellegaard

AU - Hansen, Lars Kai

PY - 2011

Y1 - 2011

N2 - There is significant current interest in decoding mental states from neuroimages. In this context kernel methods, e.g., support vector machines (SVM) are frequently adopted to learn statistical relations between patterns of brain activation and experimental conditions. In this paper we focus on visualization of such nonlinear kernel models. Specifically, we investigate the sensitivity map as a technique for generation of global summary maps of kernel classification models. We illustrate the performance of the sensitivity map on functional magnetic resonance (fMRI) data based on visual stimuli. We show that the performance of linear models is reduced for certain scan labelings/categorizations in this data set, while the nonlinear models provide more flexibility. We show that the sensitivity map can be used to visualize nonlinear versions of kernel logistic regression, the kernel Fisher discriminant, and the SVM, and conclude that the sensitivity map is a versatile and computationally efficient tool for visualization of nonlinear kernel models in neuroimaging.

AB - There is significant current interest in decoding mental states from neuroimages. In this context kernel methods, e.g., support vector machines (SVM) are frequently adopted to learn statistical relations between patterns of brain activation and experimental conditions. In this paper we focus on visualization of such nonlinear kernel models. Specifically, we investigate the sensitivity map as a technique for generation of global summary maps of kernel classification models. We illustrate the performance of the sensitivity map on functional magnetic resonance (fMRI) data based on visual stimuli. We show that the performance of linear models is reduced for certain scan labelings/categorizations in this data set, while the nonlinear models provide more flexibility. We show that the sensitivity map can be used to visualize nonlinear versions of kernel logistic regression, the kernel Fisher discriminant, and the SVM, and conclude that the sensitivity map is a versatile and computationally efficient tool for visualization of nonlinear kernel models in neuroimaging.

KW - Model visualization

KW - Nonlinear modeling

KW - Support vector machine

KW - Neuroimaging

KW - Multivariate analysis

KW - Sensitivity map

KW - Kernel methods

KW - Machine learning

KW - Pattern analysis

U2 - 10.1016/j.neuroimage.2010.12.035

DO - 10.1016/j.neuroimage.2010.12.035

M3 - Journal article

VL - 55

SP - 1120

EP - 1131

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 3

ER -