Multivariate Analysis of structural MRI and PET (FDG and 18F-AV-45) for Alzheimer's disease and its prodromal stages

Qi Zhou; Mohammed Goryawala; Mercedes Cabrerizo; Warren Barker; David Loewenstein; Ranjan Duara; Malek Adjouadi

doi:10.1109/EMBC.2014.6943774

Multivariate Analysis of structural MRI and PET (FDG and 18F-AV-45) for Alzheimer's disease and its prodromal stages

Qi Zhou, Mohammed Goryawala, Mercedes Cabrerizo, Warren Barker, David Loewenstein, Ranjan Duara, Malek Adjouadi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Scopus citations

Abstract

A multivariate analysis method, orthogonal partial least squares to latent structures (OPLS), was used to discriminate Alzheimer's disease (AD), early and late mild cognitive impairment (EMCI and LMCI) from cognitively normal control (CN) using MRI and PET measures. FreeSurfer 5.1 generated 271 MRI features including 49 subcortical volumes, 68 cortical volumes, 68 cortical thicknesses, 70 surface areas and 16 hippocampus subfields. Subjects with all aforementioned MRI measures passing quality control and valid Fludeoxyglucose (18F) (FDG) and Florbetapir (18F) PET scans were selected from ADNI database, resulting in a total of 524 participants (137 CN, 214 EMCI, 103 LMCI and 70 AD) for the study. Altogether 286 features including 15 significant PET uptake features (7 for FDG and 8 for AV-45) were utilized for OPLS analysis. Predictive power was evaluated by Q<inf>2</inf>(Y), a quantifier of the statistical significance for class separation. The results show that MRI features (Q<inf>2</inf>(Y) =0.645), and PET features (Q<inf>2</inf>(Y) = 0.636) has comparable predictive power in separating AD from CN, and MRI features are better predictor of LMCI (Q<inf>2</inf>(Y) = 0.282) than PET (Q<inf>2</inf>(Y) = 0.294). Combination of PET and MRI has the most predictive power for LMCI and AD with Q<inf>2</inf>(Y) of 0.294 and 0.721, respectively. While for EMCI, cortical thickness was found to be the best predictor with a Q<inf>2</inf>(Y) of 0.108, suggesting cortical thickness may be the first structural change ahead of others and should be prioritized in prediction of very mild cognitive impairment.

Original language	English (US)
Title of host publication	2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1051-1054
Number of pages	4
ISBN (Print)	9781424479290
DOIs	https://doi.org/10.1109/EMBC.2014.6943774
State	Published - Nov 2 2014
Externally published	Yes
Event	2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014 - Chicago, United States Duration: Aug 26 2014 → Aug 30 2014

Other

Other	2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
Country	United States
City	Chicago
Period	8/26/14 → 8/30/14

ASJC Scopus subject areas

Health Informatics
Computer Science Applications
Biomedical Engineering

Access to Document

10.1109/EMBC.2014.6943774

Fingerprint Dive into the research topics of 'Multivariate Analysis of structural MRI and PET (FDG and 18F-AV-45) for Alzheimer's disease and its prodromal stages'. Together they form a unique fingerprint.

Cite this

Zhou, Q., Goryawala, M., Cabrerizo, M., Barker, W., Loewenstein, D., Duara, R., & Adjouadi, M. (2014). Multivariate Analysis of structural MRI and PET (FDG and 18F-AV-45) for Alzheimer's disease and its prodromal stages. In 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014 (pp. 1051-1054). [6943774] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2014.6943774

Multivariate Analysis of structural MRI and PET (FDG and 18F-AV-45) for Alzheimer's disease and its prodromal stages. / Zhou, Qi; Goryawala, Mohammed; Cabrerizo, Mercedes; Barker, Warren; Loewenstein, David; Duara, Ranjan; Adjouadi, Malek.

2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 1051-1054 6943774.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Zhou, Q, Goryawala, M, Cabrerizo, M, Barker, W, Loewenstein, D, Duara, R & Adjouadi, M 2014, Multivariate Analysis of structural MRI and PET (FDG and 18F-AV-45) for Alzheimer's disease and its prodromal stages. in 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014., 6943774, Institute of Electrical and Electronics Engineers Inc., pp. 1051-1054, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014, Chicago, United States, 8/26/14. https://doi.org/10.1109/EMBC.2014.6943774

Zhou Q, Goryawala M, Cabrerizo M, Barker W, Loewenstein D, Duara R et al. Multivariate Analysis of structural MRI and PET (FDG and 18F-AV-45) for Alzheimer's disease and its prodromal stages. In 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 1051-1054. 6943774 https://doi.org/10.1109/EMBC.2014.6943774

Zhou, Qi ; Goryawala, Mohammed ; Cabrerizo, Mercedes ; Barker, Warren ; Loewenstein, David ; Duara, Ranjan ; Adjouadi, Malek. / Multivariate Analysis of structural MRI and PET (FDG and 18F-AV-45) for Alzheimer's disease and its prodromal stages. 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 1051-1054

@inproceedings{0735e8c2eb0c480e98ebf4d91ab2ae42,

title = "Multivariate Analysis of structural MRI and PET (FDG and 18F-AV-45) for Alzheimer's disease and its prodromal stages",

abstract = "A multivariate analysis method, orthogonal partial least squares to latent structures (OPLS), was used to discriminate Alzheimer's disease (AD), early and late mild cognitive impairment (EMCI and LMCI) from cognitively normal control (CN) using MRI and PET measures. FreeSurfer 5.1 generated 271 MRI features including 49 subcortical volumes, 68 cortical volumes, 68 cortical thicknesses, 70 surface areas and 16 hippocampus subfields. Subjects with all aforementioned MRI measures passing quality control and valid Fludeoxyglucose (18F) (FDG) and Florbetapir (18F) PET scans were selected from ADNI database, resulting in a total of 524 participants (137 CN, 214 EMCI, 103 LMCI and 70 AD) for the study. Altogether 286 features including 15 significant PET uptake features (7 for FDG and 8 for AV-45) were utilized for OPLS analysis. Predictive power was evaluated by Q2(Y), a quantifier of the statistical significance for class separation. The results show that MRI features (Q2(Y) =0.645), and PET features (Q2(Y) = 0.636) has comparable predictive power in separating AD from CN, and MRI features are better predictor of LMCI (Q2(Y) = 0.282) than PET (Q2(Y) = 0.294). Combination of PET and MRI has the most predictive power for LMCI and AD with Q2(Y) of 0.294 and 0.721, respectively. While for EMCI, cortical thickness was found to be the best predictor with a Q2(Y) of 0.108, suggesting cortical thickness may be the first structural change ahead of others and should be prioritized in prediction of very mild cognitive impairment.",

author = "Qi Zhou and Mohammed Goryawala and Mercedes Cabrerizo and Warren Barker and David Loewenstein and Ranjan Duara and Malek Adjouadi",

year = "2014",

month = nov,

day = "2",

doi = "10.1109/EMBC.2014.6943774",

language = "English (US)",

isbn = "9781424479290",

pages = "1051--1054",

booktitle = "2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014 ; Conference date: 26-08-2014 Through 30-08-2014",

}

TY - GEN

T1 - Multivariate Analysis of structural MRI and PET (FDG and 18F-AV-45) for Alzheimer's disease and its prodromal stages

AU - Zhou, Qi

AU - Goryawala, Mohammed

AU - Cabrerizo, Mercedes

AU - Barker, Warren

AU - Loewenstein, David

AU - Duara, Ranjan

AU - Adjouadi, Malek

PY - 2014/11/2

Y1 - 2014/11/2

N2 - A multivariate analysis method, orthogonal partial least squares to latent structures (OPLS), was used to discriminate Alzheimer's disease (AD), early and late mild cognitive impairment (EMCI and LMCI) from cognitively normal control (CN) using MRI and PET measures. FreeSurfer 5.1 generated 271 MRI features including 49 subcortical volumes, 68 cortical volumes, 68 cortical thicknesses, 70 surface areas and 16 hippocampus subfields. Subjects with all aforementioned MRI measures passing quality control and valid Fludeoxyglucose (18F) (FDG) and Florbetapir (18F) PET scans were selected from ADNI database, resulting in a total of 524 participants (137 CN, 214 EMCI, 103 LMCI and 70 AD) for the study. Altogether 286 features including 15 significant PET uptake features (7 for FDG and 8 for AV-45) were utilized for OPLS analysis. Predictive power was evaluated by Q2(Y), a quantifier of the statistical significance for class separation. The results show that MRI features (Q2(Y) =0.645), and PET features (Q2(Y) = 0.636) has comparable predictive power in separating AD from CN, and MRI features are better predictor of LMCI (Q2(Y) = 0.282) than PET (Q2(Y) = 0.294). Combination of PET and MRI has the most predictive power for LMCI and AD with Q2(Y) of 0.294 and 0.721, respectively. While for EMCI, cortical thickness was found to be the best predictor with a Q2(Y) of 0.108, suggesting cortical thickness may be the first structural change ahead of others and should be prioritized in prediction of very mild cognitive impairment.

AB - A multivariate analysis method, orthogonal partial least squares to latent structures (OPLS), was used to discriminate Alzheimer's disease (AD), early and late mild cognitive impairment (EMCI and LMCI) from cognitively normal control (CN) using MRI and PET measures. FreeSurfer 5.1 generated 271 MRI features including 49 subcortical volumes, 68 cortical volumes, 68 cortical thicknesses, 70 surface areas and 16 hippocampus subfields. Subjects with all aforementioned MRI measures passing quality control and valid Fludeoxyglucose (18F) (FDG) and Florbetapir (18F) PET scans were selected from ADNI database, resulting in a total of 524 participants (137 CN, 214 EMCI, 103 LMCI and 70 AD) for the study. Altogether 286 features including 15 significant PET uptake features (7 for FDG and 8 for AV-45) were utilized for OPLS analysis. Predictive power was evaluated by Q2(Y), a quantifier of the statistical significance for class separation. The results show that MRI features (Q2(Y) =0.645), and PET features (Q2(Y) = 0.636) has comparable predictive power in separating AD from CN, and MRI features are better predictor of LMCI (Q2(Y) = 0.282) than PET (Q2(Y) = 0.294). Combination of PET and MRI has the most predictive power for LMCI and AD with Q2(Y) of 0.294 and 0.721, respectively. While for EMCI, cortical thickness was found to be the best predictor with a Q2(Y) of 0.108, suggesting cortical thickness may be the first structural change ahead of others and should be prioritized in prediction of very mild cognitive impairment.

UR - http://www.scopus.com/inward/record.url?scp=84929465695&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929465695&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2014.6943774

DO - 10.1109/EMBC.2014.6943774

M3 - Conference contribution

C2 - 25570142

AN - SCOPUS:84929465695

SN - 9781424479290

SP - 1051

EP - 1054

BT - 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014

Y2 - 26 August 2014 through 30 August 2014

ER -