Multiple stages classification of Alzheimer’s disease based on structural brain networks using generalized low rank approximations (GLRAM)

L. Zhan, Z. Nie, J. Ye, Yalin Wang, Y. Jin, N. Jahanshad, G. Prasad, G. I. de Zubicaray, K. L. McMahon, N. G. Martin, M. J. Wright, P. M. Thompson

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

8 Citations (Scopus)

Abstract

To classify each stage for a progressing disease such as Alzheimer’s disease is a key issue for the disease prevention and treatment. In this study, we derived structural brain networks from diffusion-weighted MRI using whole-brain tractography since there is growing interest in relating connectivity measures to clinical, cognitive, and genetic data. Relatively little work has usedmachine learning to make inferences about variations in brain networks in the progression of the Alzheimer’s disease. Here we developed a framework to utilize generalized low rank approximations of matrices (GLRAM) and modified linear discrimination analysis for unsupervised feature learning and classification of connectivity matrices. We apply the methods to brain networks derived from DWI scans of 41 people with Alzheimer’s disease, 73 people with EMCI, 38 people with LMCI, 47 elderly healthy controls and 221 young healthy controls. Our results show that this new framework can significantly improve classification accuracy when combining multiple datasets; this suggests the value of using data beyond the classification task at hand to model variations in brain connectivity.

Original languageEnglish (US)
Title of host publicationMathematics and Visualization
Publisherspringer berlin
Pages35-44
Number of pages10
Volume39
ISBN (Print)9783319111810
DOIs
StatePublished - 2014
EventMICCAI Workshop on Computational Diffusion MRI, CDMRI 2014 held under the auspices of the 17th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2014 - Boston, United States
Duration: Sep 18 2014Sep 18 2014

Publication series

NameMathematics and Visualization
Volume39
ISSN (Print)16123786
ISSN (Electronic)2197666X

Other

OtherMICCAI Workshop on Computational Diffusion MRI, CDMRI 2014 held under the auspices of the 17th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2014
CountryUnited States
CityBoston
Period9/18/149/18/14

Fingerprint

Low-rank Approximation
Alzheimer's Disease
Brain
Connectivity
Progression
Magnetic resonance imaging
Discrimination
Classify

ASJC Scopus subject areas

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

Cite this

Zhan, L., Nie, Z., Ye, J., Wang, Y., Jin, Y., Jahanshad, N., ... Thompson, P. M. (2014). Multiple stages classification of Alzheimer’s disease based on structural brain networks using generalized low rank approximations (GLRAM). In Mathematics and Visualization (Vol. 39, pp. 35-44). (Mathematics and Visualization; Vol. 39). springer berlin. https://doi.org/10.1007/978-3-319-11182-7_4

Multiple stages classification of Alzheimer’s disease based on structural brain networks using generalized low rank approximations (GLRAM). / Zhan, L.; Nie, Z.; Ye, J.; Wang, Yalin; Jin, Y.; Jahanshad, N.; Prasad, G.; de Zubicaray, G. I.; McMahon, K. L.; Martin, N. G.; Wright, M. J.; Thompson, P. M.

Mathematics and Visualization. Vol. 39 springer berlin, 2014. p. 35-44 (Mathematics and Visualization; Vol. 39).

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

Zhan, L, Nie, Z, Ye, J, Wang, Y, Jin, Y, Jahanshad, N, Prasad, G, de Zubicaray, GI, McMahon, KL, Martin, NG, Wright, MJ & Thompson, PM 2014, Multiple stages classification of Alzheimer’s disease based on structural brain networks using generalized low rank approximations (GLRAM). in Mathematics and Visualization. vol. 39, Mathematics and Visualization, vol. 39, springer berlin, pp. 35-44, MICCAI Workshop on Computational Diffusion MRI, CDMRI 2014 held under the auspices of the 17th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2014, Boston, United States, 9/18/14. https://doi.org/10.1007/978-3-319-11182-7_4
Zhan L, Nie Z, Ye J, Wang Y, Jin Y, Jahanshad N et al. Multiple stages classification of Alzheimer’s disease based on structural brain networks using generalized low rank approximations (GLRAM). In Mathematics and Visualization. Vol. 39. springer berlin. 2014. p. 35-44. (Mathematics and Visualization). https://doi.org/10.1007/978-3-319-11182-7_4
Zhan, L. ; Nie, Z. ; Ye, J. ; Wang, Yalin ; Jin, Y. ; Jahanshad, N. ; Prasad, G. ; de Zubicaray, G. I. ; McMahon, K. L. ; Martin, N. G. ; Wright, M. J. ; Thompson, P. M. / Multiple stages classification of Alzheimer’s disease based on structural brain networks using generalized low rank approximations (GLRAM). Mathematics and Visualization. Vol. 39 springer berlin, 2014. pp. 35-44 (Mathematics and Visualization).
@inproceedings{9df5d688171547e2a5aeeddb45215069,
title = "Multiple stages classification of Alzheimer’s disease based on structural brain networks using generalized low rank approximations (GLRAM)",
abstract = "To classify each stage for a progressing disease such as Alzheimer’s disease is a key issue for the disease prevention and treatment. In this study, we derived structural brain networks from diffusion-weighted MRI using whole-brain tractography since there is growing interest in relating connectivity measures to clinical, cognitive, and genetic data. Relatively little work has usedmachine learning to make inferences about variations in brain networks in the progression of the Alzheimer’s disease. Here we developed a framework to utilize generalized low rank approximations of matrices (GLRAM) and modified linear discrimination analysis for unsupervised feature learning and classification of connectivity matrices. We apply the methods to brain networks derived from DWI scans of 41 people with Alzheimer’s disease, 73 people with EMCI, 38 people with LMCI, 47 elderly healthy controls and 221 young healthy controls. Our results show that this new framework can significantly improve classification accuracy when combining multiple datasets; this suggests the value of using data beyond the classification task at hand to model variations in brain connectivity.",
author = "L. Zhan and Z. Nie and J. Ye and Yalin Wang and Y. Jin and N. Jahanshad and G. Prasad and {de Zubicaray}, {G. I.} and McMahon, {K. L.} and Martin, {N. G.} and Wright, {M. J.} and Thompson, {P. M.}",
year = "2014",
doi = "10.1007/978-3-319-11182-7_4",
language = "English (US)",
isbn = "9783319111810",
volume = "39",
series = "Mathematics and Visualization",
publisher = "springer berlin",
pages = "35--44",
booktitle = "Mathematics and Visualization",

}

TY - GEN

T1 - Multiple stages classification of Alzheimer’s disease based on structural brain networks using generalized low rank approximations (GLRAM)

AU - Zhan, L.

AU - Nie, Z.

AU - Ye, J.

AU - Wang, Yalin

AU - Jin, Y.

AU - Jahanshad, N.

AU - Prasad, G.

AU - de Zubicaray, G. I.

AU - McMahon, K. L.

AU - Martin, N. G.

AU - Wright, M. J.

AU - Thompson, P. M.

PY - 2014

Y1 - 2014

N2 - To classify each stage for a progressing disease such as Alzheimer’s disease is a key issue for the disease prevention and treatment. In this study, we derived structural brain networks from diffusion-weighted MRI using whole-brain tractography since there is growing interest in relating connectivity measures to clinical, cognitive, and genetic data. Relatively little work has usedmachine learning to make inferences about variations in brain networks in the progression of the Alzheimer’s disease. Here we developed a framework to utilize generalized low rank approximations of matrices (GLRAM) and modified linear discrimination analysis for unsupervised feature learning and classification of connectivity matrices. We apply the methods to brain networks derived from DWI scans of 41 people with Alzheimer’s disease, 73 people with EMCI, 38 people with LMCI, 47 elderly healthy controls and 221 young healthy controls. Our results show that this new framework can significantly improve classification accuracy when combining multiple datasets; this suggests the value of using data beyond the classification task at hand to model variations in brain connectivity.

AB - To classify each stage for a progressing disease such as Alzheimer’s disease is a key issue for the disease prevention and treatment. In this study, we derived structural brain networks from diffusion-weighted MRI using whole-brain tractography since there is growing interest in relating connectivity measures to clinical, cognitive, and genetic data. Relatively little work has usedmachine learning to make inferences about variations in brain networks in the progression of the Alzheimer’s disease. Here we developed a framework to utilize generalized low rank approximations of matrices (GLRAM) and modified linear discrimination analysis for unsupervised feature learning and classification of connectivity matrices. We apply the methods to brain networks derived from DWI scans of 41 people with Alzheimer’s disease, 73 people with EMCI, 38 people with LMCI, 47 elderly healthy controls and 221 young healthy controls. Our results show that this new framework can significantly improve classification accuracy when combining multiple datasets; this suggests the value of using data beyond the classification task at hand to model variations in brain connectivity.

UR - http://www.scopus.com/inward/record.url?scp=84929463229&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929463229&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-11182-7_4

DO - 10.1007/978-3-319-11182-7_4

M3 - Conference contribution

AN - SCOPUS:84929463229

SN - 9783319111810

VL - 39

T3 - Mathematics and Visualization

SP - 35

EP - 44

BT - Mathematics and Visualization

PB - springer berlin

ER -