The Added Value of Diffusion-Weighted MRI-Derived Structural Connectome in Evaluating Mild Cognitive Impairment

A Multi-Cohort Validation

Qi Wang, Lei Guo, Paul M. Thompson, Clifford R. Jack, Hiroko Dodge, Liang Zhan, Jiayu Zhou

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

T1-weighted MRI has been extensively used to extract imaging biomarkers and build classification models for differentiating Alzheimer's disease (AD) patients from healthy controls, but only recently have brain connectome networks derived from diffusion-weighted MRI been used to model AD progression and various stages of disease such as mild cognitive impairment (MCI). MCI, as a possible prodromal stage of AD, has gained intense interest recently, since it may be used to assess risk factors for AD. Little work has been done to combine information from both white matter and gray matter, and it is unknown how much classification power the diffusion-weighted MRI-derived structural connectome could provide beyond information available from T1-weighted MRI. In this paper, we focused on investigating whether diffusion-weighted MRI-derived structural connectome can improve differentiating healthy controls subjects from those with MCI. Specifically, we proposed a novel feature-ranking method to build classification models using the most highly ranked feature variables to classify MCI with healthy controls. We verified our method on two independent cohorts including the second stage of Alzheimer's Disease Neuroimaging Initiative (ADNI2) database and the National Alzheimer's Coordinating Center (NACC) database. Our results indicated that 1) diffusion-weighted MRI-derived structural connectome can complement T1-weighted MRI in the classification task; 2) the feature-rank method is effective because of the identified consistent T1-weighted MRI and network feature variables on ADNI2 and NACC. Furthermore, by comparing the top-ranked feature variables from ADNI2, NACC, and combined dataset, we concluded that cross-validation using independent cohorts is necessary and highly recommended.

Original languageEnglish (US)
Pages (from-to)149-169
Number of pages21
JournalJournal of Alzheimer's Disease
Volume64
Issue number1
DOIs
StatePublished - Jan 1 2018

Fingerprint

Connectome
Diffusion Magnetic Resonance Imaging
Alzheimer Disease
Databases
Prodromal Symptoms
Neuroimaging
Disease Progression
Healthy Volunteers
Biomarkers
Cognitive Dysfunction
Brain

Keywords

  • Alzheimer's disease
  • brain network
  • diffusion MRI
  • feature extraction
  • mild cognitive impairment
  • multiple cohorts

ASJC Scopus subject areas

  • Neuroscience(all)
  • Clinical Psychology
  • Geriatrics and Gerontology
  • Psychiatry and Mental health

Cite this

The Added Value of Diffusion-Weighted MRI-Derived Structural Connectome in Evaluating Mild Cognitive Impairment : A Multi-Cohort Validation. / Wang, Qi; Guo, Lei; Thompson, Paul M.; Jack, Clifford R.; Dodge, Hiroko; Zhan, Liang; Zhou, Jiayu.

In: Journal of Alzheimer's Disease, Vol. 64, No. 1, 01.01.2018, p. 149-169.

Research output: Contribution to journalArticle

Wang, Qi ; Guo, Lei ; Thompson, Paul M. ; Jack, Clifford R. ; Dodge, Hiroko ; Zhan, Liang ; Zhou, Jiayu. / The Added Value of Diffusion-Weighted MRI-Derived Structural Connectome in Evaluating Mild Cognitive Impairment : A Multi-Cohort Validation. In: Journal of Alzheimer's Disease. 2018 ; Vol. 64, No. 1. pp. 149-169.
@article{e64f4ada3cca472fb70df8149eae7c9f,
title = "The Added Value of Diffusion-Weighted MRI-Derived Structural Connectome in Evaluating Mild Cognitive Impairment: A Multi-Cohort Validation",
abstract = "T1-weighted MRI has been extensively used to extract imaging biomarkers and build classification models for differentiating Alzheimer's disease (AD) patients from healthy controls, but only recently have brain connectome networks derived from diffusion-weighted MRI been used to model AD progression and various stages of disease such as mild cognitive impairment (MCI). MCI, as a possible prodromal stage of AD, has gained intense interest recently, since it may be used to assess risk factors for AD. Little work has been done to combine information from both white matter and gray matter, and it is unknown how much classification power the diffusion-weighted MRI-derived structural connectome could provide beyond information available from T1-weighted MRI. In this paper, we focused on investigating whether diffusion-weighted MRI-derived structural connectome can improve differentiating healthy controls subjects from those with MCI. Specifically, we proposed a novel feature-ranking method to build classification models using the most highly ranked feature variables to classify MCI with healthy controls. We verified our method on two independent cohorts including the second stage of Alzheimer's Disease Neuroimaging Initiative (ADNI2) database and the National Alzheimer's Coordinating Center (NACC) database. Our results indicated that 1) diffusion-weighted MRI-derived structural connectome can complement T1-weighted MRI in the classification task; 2) the feature-rank method is effective because of the identified consistent T1-weighted MRI and network feature variables on ADNI2 and NACC. Furthermore, by comparing the top-ranked feature variables from ADNI2, NACC, and combined dataset, we concluded that cross-validation using independent cohorts is necessary and highly recommended.",
keywords = "Alzheimer's disease, brain network, diffusion MRI, feature extraction, mild cognitive impairment, multiple cohorts",
author = "Qi Wang and Lei Guo and Thompson, {Paul M.} and Jack, {Clifford R.} and Hiroko Dodge and Liang Zhan and Jiayu Zhou",
year = "2018",
month = "1",
day = "1",
doi = "10.3233/JAD-171048",
language = "English (US)",
volume = "64",
pages = "149--169",
journal = "Journal of Alzheimer's Disease",
issn = "1387-2877",
publisher = "IOS Press",
number = "1",

}

TY - JOUR

T1 - The Added Value of Diffusion-Weighted MRI-Derived Structural Connectome in Evaluating Mild Cognitive Impairment

T2 - A Multi-Cohort Validation

AU - Wang, Qi

AU - Guo, Lei

AU - Thompson, Paul M.

AU - Jack, Clifford R.

AU - Dodge, Hiroko

AU - Zhan, Liang

AU - Zhou, Jiayu

PY - 2018/1/1

Y1 - 2018/1/1

N2 - T1-weighted MRI has been extensively used to extract imaging biomarkers and build classification models for differentiating Alzheimer's disease (AD) patients from healthy controls, but only recently have brain connectome networks derived from diffusion-weighted MRI been used to model AD progression and various stages of disease such as mild cognitive impairment (MCI). MCI, as a possible prodromal stage of AD, has gained intense interest recently, since it may be used to assess risk factors for AD. Little work has been done to combine information from both white matter and gray matter, and it is unknown how much classification power the diffusion-weighted MRI-derived structural connectome could provide beyond information available from T1-weighted MRI. In this paper, we focused on investigating whether diffusion-weighted MRI-derived structural connectome can improve differentiating healthy controls subjects from those with MCI. Specifically, we proposed a novel feature-ranking method to build classification models using the most highly ranked feature variables to classify MCI with healthy controls. We verified our method on two independent cohorts including the second stage of Alzheimer's Disease Neuroimaging Initiative (ADNI2) database and the National Alzheimer's Coordinating Center (NACC) database. Our results indicated that 1) diffusion-weighted MRI-derived structural connectome can complement T1-weighted MRI in the classification task; 2) the feature-rank method is effective because of the identified consistent T1-weighted MRI and network feature variables on ADNI2 and NACC. Furthermore, by comparing the top-ranked feature variables from ADNI2, NACC, and combined dataset, we concluded that cross-validation using independent cohorts is necessary and highly recommended.

AB - T1-weighted MRI has been extensively used to extract imaging biomarkers and build classification models for differentiating Alzheimer's disease (AD) patients from healthy controls, but only recently have brain connectome networks derived from diffusion-weighted MRI been used to model AD progression and various stages of disease such as mild cognitive impairment (MCI). MCI, as a possible prodromal stage of AD, has gained intense interest recently, since it may be used to assess risk factors for AD. Little work has been done to combine information from both white matter and gray matter, and it is unknown how much classification power the diffusion-weighted MRI-derived structural connectome could provide beyond information available from T1-weighted MRI. In this paper, we focused on investigating whether diffusion-weighted MRI-derived structural connectome can improve differentiating healthy controls subjects from those with MCI. Specifically, we proposed a novel feature-ranking method to build classification models using the most highly ranked feature variables to classify MCI with healthy controls. We verified our method on two independent cohorts including the second stage of Alzheimer's Disease Neuroimaging Initiative (ADNI2) database and the National Alzheimer's Coordinating Center (NACC) database. Our results indicated that 1) diffusion-weighted MRI-derived structural connectome can complement T1-weighted MRI in the classification task; 2) the feature-rank method is effective because of the identified consistent T1-weighted MRI and network feature variables on ADNI2 and NACC. Furthermore, by comparing the top-ranked feature variables from ADNI2, NACC, and combined dataset, we concluded that cross-validation using independent cohorts is necessary and highly recommended.

KW - Alzheimer's disease

KW - brain network

KW - diffusion MRI

KW - feature extraction

KW - mild cognitive impairment

KW - multiple cohorts

UR - http://www.scopus.com/inward/record.url?scp=85048582545&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048582545&partnerID=8YFLogxK

U2 - 10.3233/JAD-171048

DO - 10.3233/JAD-171048

M3 - Article

VL - 64

SP - 149

EP - 169

JO - Journal of Alzheimer's Disease

JF - Journal of Alzheimer's Disease

SN - 1387-2877

IS - 1

ER -