Radial basis function-sparse partial least squares for application to brain imaging data

Hisako Yoshida, Atsushi Kawaguchi, Kazuhiko Tsuruya

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Magnetic resonance imaging (MRI) data is an invaluable tool in brain morphology research. Here, we propose a novel statistical method for investigating the relationship between clinical characteristics and brain morphology based on three-dimensional MRI data via radial basis function-sparse partial least squares (RBF-sPLS). Our data consisted of MRI image intensities for multimillion voxels in a 3D array along with 73 clinical variables. This dataset represents a suitable application of RBF-sPLS because of a potential correlation among voxels as well as among clinical characteristics. Additionally, this method can simultaneously select both effective brain regions and clinical characteristics based on sparse modeling. This is in contrast to existing methods, which consider prespecified brain regions because of the computational difficulties involved in processing high-dimensional data. RBF-sPLS employs dimensionality reduction in order to overcome this obstacle. We have applied RBF-sPLS to a real dataset composed of 102 chronic kidney disease patients, while a comparison study used a simulated dataset. RBF-sPLS identified two brain regions of interest from our patient data: the temporal lobe and the occipital lobe, which are associated with aging and anemia, respectively. Our simulation study suggested that such brain regions are extracted with excellent accuracy using our method.

Original languageEnglish
Article number591032
JournalComputational and Mathematical Methods in Medicine
Volume2013
DOIs
Publication statusPublished - Jun 11 2013

Fingerprint

Partial Least Squares
Least-Squares Analysis
Radial Functions
Neuroimaging
Basis Functions
Brain
Imaging
Imaging techniques
Magnetic Resonance Imaging
Magnetic resonance imaging
Voxel
Three-dimensional Imaging
Occipital Lobe
Kidney
Dimensionality Reduction
Temporal Lobe
High-dimensional Data
Region of Interest
Chronic Renal Insufficiency
Statistical method

All Science Journal Classification (ASJC) codes

  • Modelling and Simulation
  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)
  • Applied Mathematics

Cite this

Radial basis function-sparse partial least squares for application to brain imaging data. / Yoshida, Hisako; Kawaguchi, Atsushi; Tsuruya, Kazuhiko.

In: Computational and Mathematical Methods in Medicine, Vol. 2013, 591032, 11.06.2013.

Research output: Contribution to journalArticle

@article{e23df1b00a5b44c9a27d5e745aae7fcb,
title = "Radial basis function-sparse partial least squares for application to brain imaging data",
abstract = "Magnetic resonance imaging (MRI) data is an invaluable tool in brain morphology research. Here, we propose a novel statistical method for investigating the relationship between clinical characteristics and brain morphology based on three-dimensional MRI data via radial basis function-sparse partial least squares (RBF-sPLS). Our data consisted of MRI image intensities for multimillion voxels in a 3D array along with 73 clinical variables. This dataset represents a suitable application of RBF-sPLS because of a potential correlation among voxels as well as among clinical characteristics. Additionally, this method can simultaneously select both effective brain regions and clinical characteristics based on sparse modeling. This is in contrast to existing methods, which consider prespecified brain regions because of the computational difficulties involved in processing high-dimensional data. RBF-sPLS employs dimensionality reduction in order to overcome this obstacle. We have applied RBF-sPLS to a real dataset composed of 102 chronic kidney disease patients, while a comparison study used a simulated dataset. RBF-sPLS identified two brain regions of interest from our patient data: the temporal lobe and the occipital lobe, which are associated with aging and anemia, respectively. Our simulation study suggested that such brain regions are extracted with excellent accuracy using our method.",
author = "Hisako Yoshida and Atsushi Kawaguchi and Kazuhiko Tsuruya",
year = "2013",
month = "6",
day = "11",
doi = "10.1155/2013/591032",
language = "English",
volume = "2013",
journal = "Computational and Mathematical Methods in Medicine",
issn = "1748-670X",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Radial basis function-sparse partial least squares for application to brain imaging data

AU - Yoshida, Hisako

AU - Kawaguchi, Atsushi

AU - Tsuruya, Kazuhiko

PY - 2013/6/11

Y1 - 2013/6/11

N2 - Magnetic resonance imaging (MRI) data is an invaluable tool in brain morphology research. Here, we propose a novel statistical method for investigating the relationship between clinical characteristics and brain morphology based on three-dimensional MRI data via radial basis function-sparse partial least squares (RBF-sPLS). Our data consisted of MRI image intensities for multimillion voxels in a 3D array along with 73 clinical variables. This dataset represents a suitable application of RBF-sPLS because of a potential correlation among voxels as well as among clinical characteristics. Additionally, this method can simultaneously select both effective brain regions and clinical characteristics based on sparse modeling. This is in contrast to existing methods, which consider prespecified brain regions because of the computational difficulties involved in processing high-dimensional data. RBF-sPLS employs dimensionality reduction in order to overcome this obstacle. We have applied RBF-sPLS to a real dataset composed of 102 chronic kidney disease patients, while a comparison study used a simulated dataset. RBF-sPLS identified two brain regions of interest from our patient data: the temporal lobe and the occipital lobe, which are associated with aging and anemia, respectively. Our simulation study suggested that such brain regions are extracted with excellent accuracy using our method.

AB - Magnetic resonance imaging (MRI) data is an invaluable tool in brain morphology research. Here, we propose a novel statistical method for investigating the relationship between clinical characteristics and brain morphology based on three-dimensional MRI data via radial basis function-sparse partial least squares (RBF-sPLS). Our data consisted of MRI image intensities for multimillion voxels in a 3D array along with 73 clinical variables. This dataset represents a suitable application of RBF-sPLS because of a potential correlation among voxels as well as among clinical characteristics. Additionally, this method can simultaneously select both effective brain regions and clinical characteristics based on sparse modeling. This is in contrast to existing methods, which consider prespecified brain regions because of the computational difficulties involved in processing high-dimensional data. RBF-sPLS employs dimensionality reduction in order to overcome this obstacle. We have applied RBF-sPLS to a real dataset composed of 102 chronic kidney disease patients, while a comparison study used a simulated dataset. RBF-sPLS identified two brain regions of interest from our patient data: the temporal lobe and the occipital lobe, which are associated with aging and anemia, respectively. Our simulation study suggested that such brain regions are extracted with excellent accuracy using our method.

UR - http://www.scopus.com/inward/record.url?scp=84878663672&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878663672&partnerID=8YFLogxK

U2 - 10.1155/2013/591032

DO - 10.1155/2013/591032

M3 - Article

VL - 2013

JO - Computational and Mathematical Methods in Medicine

JF - Computational and Mathematical Methods in Medicine

SN - 1748-670X

M1 - 591032

ER -