Using multiple diffusion MRI measures to predict alzheimer’s disease with a TV-L1 prior

The Alzheimer’S Disease Neuroimaging Initiative (ADNI)

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Microstructural measures from diffusion MRI have been used for classification purposes in neurodegenerative and psychiatric conditions. Novel diffusion reconstruction models can lead to better and more accurate measures of tissue properties: each measure provides different information on white matter microstructure in the brain, revealing different signs of disease. The diversity of computable measures makes it necessary to develop novel classification procedures to capture all of the available information from each measure. Here we introduce a multichannel regularized logistic regression algorithm that classifies individuals’ diagnostic status based on several microstructural measures, derived from their diffusion MRI scans. With the aid of a TV-L1 prior, which ensures sparsity in the classification model, the resulting linear models point to the most classifying brain regions for each of the diffusion MRI measures, giving the method additional descriptive power. We apply our regularized regression approach to classify Alzheimer’s disease patients and healthy controls in the ADNI dataset, based on their diffusion MRI data.

Original languageEnglish (US)
Title of host publicationComputational Diffusion MRI - MICCAI Workshop
PublisherSpringer Heidelberg
Pages157-166
Number of pages10
VolumePart F2
ISBN (Print)9783319541297
DOIs
StatePublished - 2017
EventMICCAI Workshop on Computational Diffusion MRI, CDMRI 2016 - Athens, Greece
Duration: Oct 17 2016Oct 21 2016

Publication series

NameMathematics and Visualization
VolumePart F2
ISSN (Print)1612-3786
ISSN (Electronic)2197-666X

Other

OtherMICCAI Workshop on Computational Diffusion MRI, CDMRI 2016
CountryGreece
CityAthens
Period10/17/1610/21/16

Fingerprint

Alzheimer's Disease
Magnetic resonance imaging
Predict
Brain
Classify
Logistics
Logistic Regression
Sparsity
Tissue
Microstructure
Linear Model
Diagnostics
Regression
Necessary
Model

ASJC Scopus subject areas

  • Modeling and Simulation
  • Geometry and Topology
  • Computer Graphics and Computer-Aided Design
  • Applied Mathematics

Cite this

The Alzheimer’S Disease Neuroimaging Initiative (ADNI) (2017). Using multiple diffusion MRI measures to predict alzheimer’s disease with a TV-L1 prior. In Computational Diffusion MRI - MICCAI Workshop (Vol. Part F2, pp. 157-166). (Mathematics and Visualization; Vol. Part F2). Springer Heidelberg. https://doi.org/10.1007/978-3-319-54130-3_13

Using multiple diffusion MRI measures to predict alzheimer’s disease with a TV-L1 prior. / The Alzheimer’S Disease Neuroimaging Initiative (ADNI).

Computational Diffusion MRI - MICCAI Workshop. Vol. Part F2 Springer Heidelberg, 2017. p. 157-166 (Mathematics and Visualization; Vol. Part F2).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

The Alzheimer’S Disease Neuroimaging Initiative (ADNI) 2017, Using multiple diffusion MRI measures to predict alzheimer’s disease with a TV-L1 prior. in Computational Diffusion MRI - MICCAI Workshop. vol. Part F2, Mathematics and Visualization, vol. Part F2, Springer Heidelberg, pp. 157-166, MICCAI Workshop on Computational Diffusion MRI, CDMRI 2016, Athens, Greece, 10/17/16. https://doi.org/10.1007/978-3-319-54130-3_13
The Alzheimer’S Disease Neuroimaging Initiative (ADNI). Using multiple diffusion MRI measures to predict alzheimer’s disease with a TV-L1 prior. In Computational Diffusion MRI - MICCAI Workshop. Vol. Part F2. Springer Heidelberg. 2017. p. 157-166. (Mathematics and Visualization). https://doi.org/10.1007/978-3-319-54130-3_13
The Alzheimer’S Disease Neuroimaging Initiative (ADNI). / Using multiple diffusion MRI measures to predict alzheimer’s disease with a TV-L1 prior. Computational Diffusion MRI - MICCAI Workshop. Vol. Part F2 Springer Heidelberg, 2017. pp. 157-166 (Mathematics and Visualization).
@inproceedings{1e0005db47324953af265429d7885610,
title = "Using multiple diffusion MRI measures to predict alzheimer’s disease with a TV-L1 prior",
abstract = "Microstructural measures from diffusion MRI have been used for classification purposes in neurodegenerative and psychiatric conditions. Novel diffusion reconstruction models can lead to better and more accurate measures of tissue properties: each measure provides different information on white matter microstructure in the brain, revealing different signs of disease. The diversity of computable measures makes it necessary to develop novel classification procedures to capture all of the available information from each measure. Here we introduce a multichannel regularized logistic regression algorithm that classifies individuals’ diagnostic status based on several microstructural measures, derived from their diffusion MRI scans. With the aid of a TV-L1 prior, which ensures sparsity in the classification model, the resulting linear models point to the most classifying brain regions for each of the diffusion MRI measures, giving the method additional descriptive power. We apply our regularized regression approach to classify Alzheimer’s disease patients and healthy controls in the ADNI dataset, based on their diffusion MRI data.",
author = "{The Alzheimer’S Disease Neuroimaging Initiative (ADNI)} and Villalon-Reina, {Julio E.} and Nir, {Talia M.} and Gutman, {Boris A.} and Neda Jahanshad and Jack, {Clifford R Jr.} and Weiner, {Michael W.} and Ofer Pasternak and Thompson, {Paul M.}",
year = "2017",
doi = "10.1007/978-3-319-54130-3_13",
language = "English (US)",
isbn = "9783319541297",
volume = "Part F2",
series = "Mathematics and Visualization",
publisher = "Springer Heidelberg",
pages = "157--166",
booktitle = "Computational Diffusion MRI - MICCAI Workshop",

}

TY - GEN

T1 - Using multiple diffusion MRI measures to predict alzheimer’s disease with a TV-L1 prior

AU - The Alzheimer’S Disease Neuroimaging Initiative (ADNI)

AU - Villalon-Reina, Julio E.

AU - Nir, Talia M.

AU - Gutman, Boris A.

AU - Jahanshad, Neda

AU - Jack, Clifford R Jr.

AU - Weiner, Michael W.

AU - Pasternak, Ofer

AU - Thompson, Paul M.

PY - 2017

Y1 - 2017

N2 - Microstructural measures from diffusion MRI have been used for classification purposes in neurodegenerative and psychiatric conditions. Novel diffusion reconstruction models can lead to better and more accurate measures of tissue properties: each measure provides different information on white matter microstructure in the brain, revealing different signs of disease. The diversity of computable measures makes it necessary to develop novel classification procedures to capture all of the available information from each measure. Here we introduce a multichannel regularized logistic regression algorithm that classifies individuals’ diagnostic status based on several microstructural measures, derived from their diffusion MRI scans. With the aid of a TV-L1 prior, which ensures sparsity in the classification model, the resulting linear models point to the most classifying brain regions for each of the diffusion MRI measures, giving the method additional descriptive power. We apply our regularized regression approach to classify Alzheimer’s disease patients and healthy controls in the ADNI dataset, based on their diffusion MRI data.

AB - Microstructural measures from diffusion MRI have been used for classification purposes in neurodegenerative and psychiatric conditions. Novel diffusion reconstruction models can lead to better and more accurate measures of tissue properties: each measure provides different information on white matter microstructure in the brain, revealing different signs of disease. The diversity of computable measures makes it necessary to develop novel classification procedures to capture all of the available information from each measure. Here we introduce a multichannel regularized logistic regression algorithm that classifies individuals’ diagnostic status based on several microstructural measures, derived from their diffusion MRI scans. With the aid of a TV-L1 prior, which ensures sparsity in the classification model, the resulting linear models point to the most classifying brain regions for each of the diffusion MRI measures, giving the method additional descriptive power. We apply our regularized regression approach to classify Alzheimer’s disease patients and healthy controls in the ADNI dataset, based on their diffusion MRI data.

UR - http://www.scopus.com/inward/record.url?scp=85019770590&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019770590&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-54130-3_13

DO - 10.1007/978-3-319-54130-3_13

M3 - Conference contribution

AN - SCOPUS:85019770590

SN - 9783319541297

VL - Part F2

T3 - Mathematics and Visualization

SP - 157

EP - 166

BT - Computational Diffusion MRI - MICCAI Workshop

PB - Springer Heidelberg

ER -