Cargando…

Kernel regression for fMRI pattern prediction

This paper introduces two kernel-based regression schemes to decode or predict brain states from functional brain scans as part of the Pittsburgh Brain Activity Interpretation Competition (PBAIC) 2007, in which our team was awarded first place. Our procedure involved image realignment, spatial smoot...

Descripción completa

Detalles Bibliográficos
Autores principales: Chu, Carlton, Ni, Yizhao, Tan, Geoffrey, Saunders, Craig J., Ashburner, John
Formato: Texto
Lenguaje:English
Publicado: Academic Press 2011
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3084459/
https://www.ncbi.nlm.nih.gov/pubmed/20348000
http://dx.doi.org/10.1016/j.neuroimage.2010.03.058
_version_ 1782202505739894784
author Chu, Carlton
Ni, Yizhao
Tan, Geoffrey
Saunders, Craig J.
Ashburner, John
author_facet Chu, Carlton
Ni, Yizhao
Tan, Geoffrey
Saunders, Craig J.
Ashburner, John
author_sort Chu, Carlton
collection PubMed
description This paper introduces two kernel-based regression schemes to decode or predict brain states from functional brain scans as part of the Pittsburgh Brain Activity Interpretation Competition (PBAIC) 2007, in which our team was awarded first place. Our procedure involved image realignment, spatial smoothing, detrending of low-frequency drifts, and application of multivariate linear and non-linear kernel regression methods: namely kernel ridge regression (KRR) and relevance vector regression (RVR). RVR is based on a Bayesian framework, which automatically determines a sparse solution through maximization of marginal likelihood. KRR is the dual-form formulation of ridge regression, which solves regression problems with high dimensional data in a computationally efficient way. Feature selection based on prior knowledge about human brain function was also used. Post-processing by constrained deconvolution and re-convolution was used to furnish the prediction. This paper also contains a detailed description of how prior knowledge was used to fine tune predictions of specific “feature ratings,” which we believe is one of the key factors in our prediction accuracy. The impact of pre-processing was also evaluated, demonstrating that different pre-processing may lead to significantly different accuracies. Although the original work was aimed at the PBAIC, many techniques described in this paper can be generally applied to any fMRI decoding works to increase the prediction accuracy.
format Text
id pubmed-3084459
institution National Center for Biotechnology Information
language English
publishDate 2011
publisher Academic Press
record_format MEDLINE/PubMed
spelling pubmed-30844592011-06-28 Kernel regression for fMRI pattern prediction Chu, Carlton Ni, Yizhao Tan, Geoffrey Saunders, Craig J. Ashburner, John Neuroimage Article This paper introduces two kernel-based regression schemes to decode or predict brain states from functional brain scans as part of the Pittsburgh Brain Activity Interpretation Competition (PBAIC) 2007, in which our team was awarded first place. Our procedure involved image realignment, spatial smoothing, detrending of low-frequency drifts, and application of multivariate linear and non-linear kernel regression methods: namely kernel ridge regression (KRR) and relevance vector regression (RVR). RVR is based on a Bayesian framework, which automatically determines a sparse solution through maximization of marginal likelihood. KRR is the dual-form formulation of ridge regression, which solves regression problems with high dimensional data in a computationally efficient way. Feature selection based on prior knowledge about human brain function was also used. Post-processing by constrained deconvolution and re-convolution was used to furnish the prediction. This paper also contains a detailed description of how prior knowledge was used to fine tune predictions of specific “feature ratings,” which we believe is one of the key factors in our prediction accuracy. The impact of pre-processing was also evaluated, demonstrating that different pre-processing may lead to significantly different accuracies. Although the original work was aimed at the PBAIC, many techniques described in this paper can be generally applied to any fMRI decoding works to increase the prediction accuracy. Academic Press 2011-05-15 /pmc/articles/PMC3084459/ /pubmed/20348000 http://dx.doi.org/10.1016/j.neuroimage.2010.03.058 Text en https://creativecommons.org/licenses/by/3.0/ Open Access under CC BY 3.0 (https://creativecommons.org/licenses/by/3.0/) license
spellingShingle Article
Chu, Carlton
Ni, Yizhao
Tan, Geoffrey
Saunders, Craig J.
Ashburner, John
Kernel regression for fMRI pattern prediction
title Kernel regression for fMRI pattern prediction
title_full Kernel regression for fMRI pattern prediction
title_fullStr Kernel regression for fMRI pattern prediction
title_full_unstemmed Kernel regression for fMRI pattern prediction
title_short Kernel regression for fMRI pattern prediction
title_sort kernel regression for fmri pattern prediction
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3084459/
https://www.ncbi.nlm.nih.gov/pubmed/20348000
http://dx.doi.org/10.1016/j.neuroimage.2010.03.058
work_keys_str_mv AT chucarlton kernelregressionforfmripatternprediction
AT niyizhao kernelregressionforfmripatternprediction
AT tangeoffrey kernelregressionforfmripatternprediction
AT saunderscraigj kernelregressionforfmripatternprediction
AT ashburnerjohn kernelregressionforfmripatternprediction