Hierarchical anatomical brain networks for MCI prediction by partial least square analysis

Luping Zhou, Yaping Wang, Yang Li, Pew Thian Yap, Dinggang Shen

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

4 Citations (Scopus)

Abstract

Owning to its clinical accessibility, T1-weighted MRI has been extensively studied for the prediction of mild cognitive impairment (MCI) and Alzheimer's disease (AD). The tissue volumes of GM, WM and CSF are the most commonly used measures for MCI and AD prediction. We note that disease-induced structural changes may not happen at isolated spots, but in several inter-related regions. Therefore, in this paper we propose to directly extract the inter-region connectivity based features for MCI prediction. This involves constructing a brain network for each subject, with each node representing an ROI and each edge representing regional interactions. This network is also built hierarchically to improve the robustness of classification. Compared with conventional methods, our approach produces a significant larger pool of features, which if improperly dealt with, will result in intractability when used for classifier training. Therefore based on the characteristics of the network features, we employ Partial Least Square analysis to efficiently reduce the feature dimensionality to a manageable level while at the same time preserving discriminative information as much as possible. Our experiment demonstrates that without requiring any new information in addition to T1-weighted images, the prediction accuracy of MCI is statistically improved.

Original languageEnglish
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Pages1073-1080
Number of pages8
DOIs
Publication statusPublished - 2011 Sep 22
Externally publishedYes
Event2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011 - Colorado Springs, CO, United States
Duration: 2011 Jun 202011 Jun 25

Other

Other2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011
CountryUnited States
CityColorado Springs, CO
Period11/6/2011/6/25

Fingerprint

Brain
Magnetic resonance imaging
Classifiers
Tissue
Experiments

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Zhou, L., Wang, Y., Li, Y., Yap, P. T., & Shen, D. (2011). Hierarchical anatomical brain networks for MCI prediction by partial least square analysis. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 1073-1080). [5995689] https://doi.org/10.1109/CVPR.2011.5995689

Hierarchical anatomical brain networks for MCI prediction by partial least square analysis. / Zhou, Luping; Wang, Yaping; Li, Yang; Yap, Pew Thian; Shen, Dinggang.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2011. p. 1073-1080 5995689.

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

Zhou, L, Wang, Y, Li, Y, Yap, PT & Shen, D 2011, Hierarchical anatomical brain networks for MCI prediction by partial least square analysis. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 5995689, pp. 1073-1080, 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011, Colorado Springs, CO, United States, 11/6/20. https://doi.org/10.1109/CVPR.2011.5995689
Zhou L, Wang Y, Li Y, Yap PT, Shen D. Hierarchical anatomical brain networks for MCI prediction by partial least square analysis. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2011. p. 1073-1080. 5995689 https://doi.org/10.1109/CVPR.2011.5995689
Zhou, Luping ; Wang, Yaping ; Li, Yang ; Yap, Pew Thian ; Shen, Dinggang. / Hierarchical anatomical brain networks for MCI prediction by partial least square analysis. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2011. pp. 1073-1080
@inproceedings{86211d5a5eee463eb93a2fbf74f8a9c8,
title = "Hierarchical anatomical brain networks for MCI prediction by partial least square analysis",
abstract = "Owning to its clinical accessibility, T1-weighted MRI has been extensively studied for the prediction of mild cognitive impairment (MCI) and Alzheimer's disease (AD). The tissue volumes of GM, WM and CSF are the most commonly used measures for MCI and AD prediction. We note that disease-induced structural changes may not happen at isolated spots, but in several inter-related regions. Therefore, in this paper we propose to directly extract the inter-region connectivity based features for MCI prediction. This involves constructing a brain network for each subject, with each node representing an ROI and each edge representing regional interactions. This network is also built hierarchically to improve the robustness of classification. Compared with conventional methods, our approach produces a significant larger pool of features, which if improperly dealt with, will result in intractability when used for classifier training. Therefore based on the characteristics of the network features, we employ Partial Least Square analysis to efficiently reduce the feature dimensionality to a manageable level while at the same time preserving discriminative information as much as possible. Our experiment demonstrates that without requiring any new information in addition to T1-weighted images, the prediction accuracy of MCI is statistically improved.",
author = "Luping Zhou and Yaping Wang and Yang Li and Yap, {Pew Thian} and Dinggang Shen",
year = "2011",
month = "9",
day = "22",
doi = "10.1109/CVPR.2011.5995689",
language = "English",
isbn = "9781457703942",
pages = "1073--1080",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

}

TY - GEN

T1 - Hierarchical anatomical brain networks for MCI prediction by partial least square analysis

AU - Zhou, Luping

AU - Wang, Yaping

AU - Li, Yang

AU - Yap, Pew Thian

AU - Shen, Dinggang

PY - 2011/9/22

Y1 - 2011/9/22

N2 - Owning to its clinical accessibility, T1-weighted MRI has been extensively studied for the prediction of mild cognitive impairment (MCI) and Alzheimer's disease (AD). The tissue volumes of GM, WM and CSF are the most commonly used measures for MCI and AD prediction. We note that disease-induced structural changes may not happen at isolated spots, but in several inter-related regions. Therefore, in this paper we propose to directly extract the inter-region connectivity based features for MCI prediction. This involves constructing a brain network for each subject, with each node representing an ROI and each edge representing regional interactions. This network is also built hierarchically to improve the robustness of classification. Compared with conventional methods, our approach produces a significant larger pool of features, which if improperly dealt with, will result in intractability when used for classifier training. Therefore based on the characteristics of the network features, we employ Partial Least Square analysis to efficiently reduce the feature dimensionality to a manageable level while at the same time preserving discriminative information as much as possible. Our experiment demonstrates that without requiring any new information in addition to T1-weighted images, the prediction accuracy of MCI is statistically improved.

AB - Owning to its clinical accessibility, T1-weighted MRI has been extensively studied for the prediction of mild cognitive impairment (MCI) and Alzheimer's disease (AD). The tissue volumes of GM, WM and CSF are the most commonly used measures for MCI and AD prediction. We note that disease-induced structural changes may not happen at isolated spots, but in several inter-related regions. Therefore, in this paper we propose to directly extract the inter-region connectivity based features for MCI prediction. This involves constructing a brain network for each subject, with each node representing an ROI and each edge representing regional interactions. This network is also built hierarchically to improve the robustness of classification. Compared with conventional methods, our approach produces a significant larger pool of features, which if improperly dealt with, will result in intractability when used for classifier training. Therefore based on the characteristics of the network features, we employ Partial Least Square analysis to efficiently reduce the feature dimensionality to a manageable level while at the same time preserving discriminative information as much as possible. Our experiment demonstrates that without requiring any new information in addition to T1-weighted images, the prediction accuracy of MCI is statistically improved.

UR - http://www.scopus.com/inward/record.url?scp=80052887241&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052887241&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2011.5995689

DO - 10.1109/CVPR.2011.5995689

M3 - Conference contribution

SN - 9781457703942

SP - 1073

EP - 1080

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

ER -