High dimensional classification of structural MRI Alzheimer’s disease data based on large scale regularization

Ramon Casanova, Christopher T. Whitlow, Benjamin Wagner, Jeff Williamson, Sally A. Shumaker, Joseph A Maldjian, Mark A. Espeland

Research output: Contribution to journalArticle

44 Citations (Scopus)

Abstract

In this work we use a large scale regularization approach based on penalized logistic regression to automatically classify structural MRI images (sMRI) according to cognitive status. Its performance is illustrated using sMRI data from the Alzheimer Disease Neuroimaging Initiative (ADNI) clinical database. We downloaded sMRI data from 98 subjects (49 cognitive normal and 49 patients) matched by age and sex from the ADNI website. Images were segmented and normalized using SPM8 and ANTS software packages. Classification was performed using GLMNET library implementation of penalized logistic regression based on coordinate-wise descent optimization techniques. To avoid optimistic estimates classification accuracy, sensitivity, and specificity were determined based on a combination of three-way split of the data with nested 10-fold cross-validations. One of the main features of this approach is that classification is performed based on large scale regularization. The methodology presented here was highly accurate, sensitive, and specific when automatically classifying sMRI images of cognitive normal subjects and Alzheimer disease (AD) patients. Higher levels of accuracy, sensitivity, and specificity were achieved for gray matter (GM) volume maps (85.7, 82.9, and 90%, respectively) compared to white matter volume maps (81.1, 80.6, and 82.5%, respectively). We found that GM and white matter tissues carry useful information for discriminating patients from cognitive normal subjects using sMRI brain data. Although we have demonstrated the efficacy of this voxel-wise classification method in discriminating cognitive normal subjects from AD patients, in principle it could be applied to any clinical population.

Original languageEnglish (US)
Article number22
JournalFrontiers in Neuroinformatics
Volume5
DOIs
StatePublished - Oct 14 2011

Fingerprint

Magnetic resonance imaging
Alzheimer Disease
Neuroimaging
Logistic Models
Logistics
Sensitivity and Specificity
Libraries
Software
Software packages
Databases
Websites
Brain
Tissue
Population
White Matter
Gray Matter

Keywords

  • ADNI
  • Curse of dimensionality
  • Elastic net
  • GLMNET
  • High dimensional
  • Large scale regularization
  • Logistic regression

ASJC Scopus subject areas

  • Neuroscience (miscellaneous)
  • Biomedical Engineering
  • Computer Science Applications

Cite this

High dimensional classification of structural MRI Alzheimer’s disease data based on large scale regularization. / Casanova, Ramon; Whitlow, Christopher T.; Wagner, Benjamin; Williamson, Jeff; Shumaker, Sally A.; Maldjian, Joseph A; Espeland, Mark A.

In: Frontiers in Neuroinformatics, Vol. 5, 22, 14.10.2011.

Research output: Contribution to journalArticle

Casanova, Ramon ; Whitlow, Christopher T. ; Wagner, Benjamin ; Williamson, Jeff ; Shumaker, Sally A. ; Maldjian, Joseph A ; Espeland, Mark A. / High dimensional classification of structural MRI Alzheimer’s disease data based on large scale regularization. In: Frontiers in Neuroinformatics. 2011 ; Vol. 5.
@article{820e2acfef4b40ffae89f6a80b40e469,
title = "High dimensional classification of structural MRI Alzheimer’s disease data based on large scale regularization",
abstract = "In this work we use a large scale regularization approach based on penalized logistic regression to automatically classify structural MRI images (sMRI) according to cognitive status. Its performance is illustrated using sMRI data from the Alzheimer Disease Neuroimaging Initiative (ADNI) clinical database. We downloaded sMRI data from 98 subjects (49 cognitive normal and 49 patients) matched by age and sex from the ADNI website. Images were segmented and normalized using SPM8 and ANTS software packages. Classification was performed using GLMNET library implementation of penalized logistic regression based on coordinate-wise descent optimization techniques. To avoid optimistic estimates classification accuracy, sensitivity, and specificity were determined based on a combination of three-way split of the data with nested 10-fold cross-validations. One of the main features of this approach is that classification is performed based on large scale regularization. The methodology presented here was highly accurate, sensitive, and specific when automatically classifying sMRI images of cognitive normal subjects and Alzheimer disease (AD) patients. Higher levels of accuracy, sensitivity, and specificity were achieved for gray matter (GM) volume maps (85.7, 82.9, and 90{\%}, respectively) compared to white matter volume maps (81.1, 80.6, and 82.5{\%}, respectively). We found that GM and white matter tissues carry useful information for discriminating patients from cognitive normal subjects using sMRI brain data. Although we have demonstrated the efficacy of this voxel-wise classification method in discriminating cognitive normal subjects from AD patients, in principle it could be applied to any clinical population.",
keywords = "ADNI, Curse of dimensionality, Elastic net, GLMNET, High dimensional, Large scale regularization, Logistic regression",
author = "Ramon Casanova and Whitlow, {Christopher T.} and Benjamin Wagner and Jeff Williamson and Shumaker, {Sally A.} and Maldjian, {Joseph A} and Espeland, {Mark A.}",
year = "2011",
month = "10",
day = "14",
doi = "10.3389/fninf.2011.00022",
language = "English (US)",
volume = "5",
journal = "Frontiers in Neuroinformatics",
issn = "1662-5196",
publisher = "Frontiers Research Foundation",

}

TY - JOUR

T1 - High dimensional classification of structural MRI Alzheimer’s disease data based on large scale regularization

AU - Casanova, Ramon

AU - Whitlow, Christopher T.

AU - Wagner, Benjamin

AU - Williamson, Jeff

AU - Shumaker, Sally A.

AU - Maldjian, Joseph A

AU - Espeland, Mark A.

PY - 2011/10/14

Y1 - 2011/10/14

N2 - In this work we use a large scale regularization approach based on penalized logistic regression to automatically classify structural MRI images (sMRI) according to cognitive status. Its performance is illustrated using sMRI data from the Alzheimer Disease Neuroimaging Initiative (ADNI) clinical database. We downloaded sMRI data from 98 subjects (49 cognitive normal and 49 patients) matched by age and sex from the ADNI website. Images were segmented and normalized using SPM8 and ANTS software packages. Classification was performed using GLMNET library implementation of penalized logistic regression based on coordinate-wise descent optimization techniques. To avoid optimistic estimates classification accuracy, sensitivity, and specificity were determined based on a combination of three-way split of the data with nested 10-fold cross-validations. One of the main features of this approach is that classification is performed based on large scale regularization. The methodology presented here was highly accurate, sensitive, and specific when automatically classifying sMRI images of cognitive normal subjects and Alzheimer disease (AD) patients. Higher levels of accuracy, sensitivity, and specificity were achieved for gray matter (GM) volume maps (85.7, 82.9, and 90%, respectively) compared to white matter volume maps (81.1, 80.6, and 82.5%, respectively). We found that GM and white matter tissues carry useful information for discriminating patients from cognitive normal subjects using sMRI brain data. Although we have demonstrated the efficacy of this voxel-wise classification method in discriminating cognitive normal subjects from AD patients, in principle it could be applied to any clinical population.

AB - In this work we use a large scale regularization approach based on penalized logistic regression to automatically classify structural MRI images (sMRI) according to cognitive status. Its performance is illustrated using sMRI data from the Alzheimer Disease Neuroimaging Initiative (ADNI) clinical database. We downloaded sMRI data from 98 subjects (49 cognitive normal and 49 patients) matched by age and sex from the ADNI website. Images were segmented and normalized using SPM8 and ANTS software packages. Classification was performed using GLMNET library implementation of penalized logistic regression based on coordinate-wise descent optimization techniques. To avoid optimistic estimates classification accuracy, sensitivity, and specificity were determined based on a combination of three-way split of the data with nested 10-fold cross-validations. One of the main features of this approach is that classification is performed based on large scale regularization. The methodology presented here was highly accurate, sensitive, and specific when automatically classifying sMRI images of cognitive normal subjects and Alzheimer disease (AD) patients. Higher levels of accuracy, sensitivity, and specificity were achieved for gray matter (GM) volume maps (85.7, 82.9, and 90%, respectively) compared to white matter volume maps (81.1, 80.6, and 82.5%, respectively). We found that GM and white matter tissues carry useful information for discriminating patients from cognitive normal subjects using sMRI brain data. Although we have demonstrated the efficacy of this voxel-wise classification method in discriminating cognitive normal subjects from AD patients, in principle it could be applied to any clinical population.

KW - ADNI

KW - Curse of dimensionality

KW - Elastic net

KW - GLMNET

KW - High dimensional

KW - Large scale regularization

KW - Logistic regression

UR - http://www.scopus.com/inward/record.url?scp=84993994674&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84993994674&partnerID=8YFLogxK

U2 - 10.3389/fninf.2011.00022

DO - 10.3389/fninf.2011.00022

M3 - Article

C2 - 22016732

AN - SCOPUS:84993994674

VL - 5

JO - Frontiers in Neuroinformatics

JF - Frontiers in Neuroinformatics

SN - 1662-5196

M1 - 22

ER -