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 language | English (US) |
|---|---|
| Pages (from-to) | 149-169 |
| Number of pages | 21 |
| Journal | Journal of Alzheimer's Disease |
| Volume | 64 |
| Issue number | 1 |
| DOIs | |
| State | Published - Jan 1 2018 |
Fingerprint
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 journal › Article
}
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 -