Nonlinear Denoising and Analysis of Neuroimages With Kernel Principal Component Analysis and Pre-Image Estimation

Publication: Research - peer-reviewJournal article – Annual report year: 2012

Standard

Harvard

APA

CBE

MLA

Vancouver

Author

Bibtex

@article{579e47d13e814dc1bec7742e03a59c42,
title = "Nonlinear Denoising and Analysis of Neuroimages With Kernel Principal Component Analysis and Pre-Image Estimation",
keywords = "Multivariate analysis, Classification, Decoding, Nonlinear modeling, Kernel PCA, Pre-image estimation, NPAIRS resampling",
publisher = "Academic Press",
author = "Rasmussen, {Peter Mondrup} and Abrahamsen, {Trine Julie} and Madsen, {Kristoffer Hougaard} and Hansen, {Lars Kai}",
year = "2012",
doi = "10.1016/j.neuroimage.2012.01.096",
volume = "60",
number = "3",
pages = "1807--1818",
journal = "NeuroImage",
issn = "1053-8119",

}

RIS

TY - JOUR

T1 - Nonlinear Denoising and Analysis of Neuroimages With Kernel Principal Component Analysis and Pre-Image Estimation

A1 - Rasmussen,Peter Mondrup

A1 - Abrahamsen,Trine Julie

A1 - Madsen,Kristoffer Hougaard

A1 - Hansen,Lars Kai

AU - Rasmussen,Peter Mondrup

AU - Abrahamsen,Trine Julie

AU - Madsen,Kristoffer Hougaard

AU - Hansen,Lars Kai

PB - Academic Press

PY - 2012

Y1 - 2012

N2 - We investigate the use of kernel principal component analysis (PCA) and the inverse problem known as pre-image estimation in neuroimaging: i) We explore kernel PCA and pre-image estimation as a means for image denoising as part of the image preprocessing pipeline. Evaluation of the denoising procedure is performed within a data-driven split-half evaluation framework. ii) We introduce manifold navigation for exploration of a nonlinear data manifold, and illustrate how pre-image estimation can be used to generate brain maps in the continuum between experimentally defined brain states/classes. We base these illustrations on two fMRI BOLD data sets — one from a simple finger tapping experiment and the other from an experiment on object recognition in the ventral temporal lobe.

AB - We investigate the use of kernel principal component analysis (PCA) and the inverse problem known as pre-image estimation in neuroimaging: i) We explore kernel PCA and pre-image estimation as a means for image denoising as part of the image preprocessing pipeline. Evaluation of the denoising procedure is performed within a data-driven split-half evaluation framework. ii) We introduce manifold navigation for exploration of a nonlinear data manifold, and illustrate how pre-image estimation can be used to generate brain maps in the continuum between experimentally defined brain states/classes. We base these illustrations on two fMRI BOLD data sets — one from a simple finger tapping experiment and the other from an experiment on object recognition in the ventral temporal lobe.

KW - Multivariate analysis

KW - Classification

KW - Decoding

KW - Nonlinear modeling

KW - Kernel PCA

KW - Pre-image estimation

KW - NPAIRS resampling

U2 - 10.1016/j.neuroimage.2012.01.096

DO - 10.1016/j.neuroimage.2012.01.096

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 3

VL - 60

SP - 1807

EP - 1818

ER -