Hierarchical anatomical brain networks for MCI prediction: Revisiting volumetric measures

Luping Zhou, Yaping Wang, Yang Li, Pew Thian Yap, Dinggang Shen, Disease Neuroimaging Initiative (ADNI) Alzheimer's Disease Neuroimaging Initiative (ADNI)

Research output: Contribution to journalArticle

56 Citations (Scopus)

Abstract

Owning to its clinical accessibility, T1-weighted MRI (Magnetic Resonance Imaging) has been extensively studied in the past decades for prediction of Alzheimer's disease (AD) and mild cognitive impairment (MCI). The volumes of gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF) are the most commonly used measurements, resulting in many successful applications. It has been widely observed that disease-induced structural changes may not occur at isolated spots, but in several inter-related regions. Therefore, for better characterization of brain pathology, we propose in this paper a means to extract inter-regional correlation based features from local volumetric measurements. Specifically, our approach involves constructing an anatomical brain network for each subject, with each node representing a Region of Interest (ROI) and each edge representing Pearson correlation of tissue volumetric measurements between ROI pairs. As second order volumetric measurements, network features are more descriptive but also more sensitive to noise. To overcome this limitation, a hierarchy of ROIs is used to suppress noise at different scales. Pairwise interactions are considered not only for ROIs with the same scale in the same layer of the hierarchy, but also for ROIs across different scales in different layers. To address the high dimensionality problem resulting from the large number of network features, a supervised dimensionality reduction method is further employed to embed a selected subset of features into a low dimensional feature space, while at the same time preserving discriminative information. We demonstrate with experimental results the efficacy of this embedding strategy in comparison with some other commonly used approaches. In addition, although the proposed method can be easily generalized to incorporate other metrics of regional similarities, the benefits of using Pearson correlation in our application are reinforced by the experimental results. Without requiring new sources of information, our proposed approach improves the accuracy of MCI prediction from 80.83% (of conventional volumetric features) to 84.35% (of hierarchical network features), evaluated using data sets randomly drawn from the ADNI (Alzheimer's Disease Neuroimaging Initiative) dataset.

Original languageEnglish
Article numbere21935
JournalPLoS One
Volume6
Issue number7
DOIs
Publication statusPublished - 2011 Jul 22
Externally publishedYes

Fingerprint

Noise
Brain
Alzheimer Disease
brain
prediction
Alzheimer disease
Neuroimaging
Cerebrospinal Fluid
Magnetic Resonance Imaging
Pathology
Cerebrospinal fluid
cerebrospinal fluid
information sources
magnetic resonance imaging
Tissue
Cognitive Dysfunction
Datasets
extracts
methodology
White Matter

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

Zhou, L., Wang, Y., Li, Y., Yap, P. T., Shen, D., & Alzheimer's Disease Neuroimaging Initiative (ADNI), D. N. I. ADNI. (2011). Hierarchical anatomical brain networks for MCI prediction: Revisiting volumetric measures. PLoS One, 6(7), [e21935]. https://doi.org/10.1371/journal.pone.0021935

Hierarchical anatomical brain networks for MCI prediction : Revisiting volumetric measures. / Zhou, Luping; Wang, Yaping; Li, Yang; Yap, Pew Thian; Shen, Dinggang; Alzheimer's Disease Neuroimaging Initiative (ADNI), Disease Neuroimaging Initiative (ADNI).

In: PLoS One, Vol. 6, No. 7, e21935, 22.07.2011.

Research output: Contribution to journalArticle

Zhou, L, Wang, Y, Li, Y, Yap, PT, Shen, D & Alzheimer's Disease Neuroimaging Initiative (ADNI), DNIADNI 2011, 'Hierarchical anatomical brain networks for MCI prediction: Revisiting volumetric measures', PLoS One, vol. 6, no. 7, e21935. https://doi.org/10.1371/journal.pone.0021935
Zhou L, Wang Y, Li Y, Yap PT, Shen D, Alzheimer's Disease Neuroimaging Initiative (ADNI) DNIADNI. Hierarchical anatomical brain networks for MCI prediction: Revisiting volumetric measures. PLoS One. 2011 Jul 22;6(7). e21935. https://doi.org/10.1371/journal.pone.0021935
Zhou, Luping ; Wang, Yaping ; Li, Yang ; Yap, Pew Thian ; Shen, Dinggang ; Alzheimer's Disease Neuroimaging Initiative (ADNI), Disease Neuroimaging Initiative (ADNI). / Hierarchical anatomical brain networks for MCI prediction : Revisiting volumetric measures. In: PLoS One. 2011 ; Vol. 6, No. 7.
@article{d93e0cc301fe47d78414b484e048666d,
title = "Hierarchical anatomical brain networks for MCI prediction: Revisiting volumetric measures",
abstract = "Owning to its clinical accessibility, T1-weighted MRI (Magnetic Resonance Imaging) has been extensively studied in the past decades for prediction of Alzheimer's disease (AD) and mild cognitive impairment (MCI). The volumes of gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF) are the most commonly used measurements, resulting in many successful applications. It has been widely observed that disease-induced structural changes may not occur at isolated spots, but in several inter-related regions. Therefore, for better characterization of brain pathology, we propose in this paper a means to extract inter-regional correlation based features from local volumetric measurements. Specifically, our approach involves constructing an anatomical brain network for each subject, with each node representing a Region of Interest (ROI) and each edge representing Pearson correlation of tissue volumetric measurements between ROI pairs. As second order volumetric measurements, network features are more descriptive but also more sensitive to noise. To overcome this limitation, a hierarchy of ROIs is used to suppress noise at different scales. Pairwise interactions are considered not only for ROIs with the same scale in the same layer of the hierarchy, but also for ROIs across different scales in different layers. To address the high dimensionality problem resulting from the large number of network features, a supervised dimensionality reduction method is further employed to embed a selected subset of features into a low dimensional feature space, while at the same time preserving discriminative information. We demonstrate with experimental results the efficacy of this embedding strategy in comparison with some other commonly used approaches. In addition, although the proposed method can be easily generalized to incorporate other metrics of regional similarities, the benefits of using Pearson correlation in our application are reinforced by the experimental results. Without requiring new sources of information, our proposed approach improves the accuracy of MCI prediction from 80.83{\%} (of conventional volumetric features) to 84.35{\%} (of hierarchical network features), evaluated using data sets randomly drawn from the ADNI (Alzheimer's Disease Neuroimaging Initiative) dataset.",
author = "Luping Zhou and Yaping Wang and Yang Li and Yap, {Pew Thian} and Dinggang Shen and {Alzheimer's Disease Neuroimaging Initiative (ADNI)}, {Disease Neuroimaging Initiative (ADNI)}",
year = "2011",
month = "7",
day = "22",
doi = "10.1371/journal.pone.0021935",
language = "English",
volume = "6",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "7",

}

TY - JOUR

T1 - Hierarchical anatomical brain networks for MCI prediction

T2 - Revisiting volumetric measures

AU - Zhou, Luping

AU - Wang, Yaping

AU - Li, Yang

AU - Yap, Pew Thian

AU - Shen, Dinggang

AU - Alzheimer's Disease Neuroimaging Initiative (ADNI), Disease Neuroimaging Initiative (ADNI)

PY - 2011/7/22

Y1 - 2011/7/22

N2 - Owning to its clinical accessibility, T1-weighted MRI (Magnetic Resonance Imaging) has been extensively studied in the past decades for prediction of Alzheimer's disease (AD) and mild cognitive impairment (MCI). The volumes of gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF) are the most commonly used measurements, resulting in many successful applications. It has been widely observed that disease-induced structural changes may not occur at isolated spots, but in several inter-related regions. Therefore, for better characterization of brain pathology, we propose in this paper a means to extract inter-regional correlation based features from local volumetric measurements. Specifically, our approach involves constructing an anatomical brain network for each subject, with each node representing a Region of Interest (ROI) and each edge representing Pearson correlation of tissue volumetric measurements between ROI pairs. As second order volumetric measurements, network features are more descriptive but also more sensitive to noise. To overcome this limitation, a hierarchy of ROIs is used to suppress noise at different scales. Pairwise interactions are considered not only for ROIs with the same scale in the same layer of the hierarchy, but also for ROIs across different scales in different layers. To address the high dimensionality problem resulting from the large number of network features, a supervised dimensionality reduction method is further employed to embed a selected subset of features into a low dimensional feature space, while at the same time preserving discriminative information. We demonstrate with experimental results the efficacy of this embedding strategy in comparison with some other commonly used approaches. In addition, although the proposed method can be easily generalized to incorporate other metrics of regional similarities, the benefits of using Pearson correlation in our application are reinforced by the experimental results. Without requiring new sources of information, our proposed approach improves the accuracy of MCI prediction from 80.83% (of conventional volumetric features) to 84.35% (of hierarchical network features), evaluated using data sets randomly drawn from the ADNI (Alzheimer's Disease Neuroimaging Initiative) dataset.

AB - Owning to its clinical accessibility, T1-weighted MRI (Magnetic Resonance Imaging) has been extensively studied in the past decades for prediction of Alzheimer's disease (AD) and mild cognitive impairment (MCI). The volumes of gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF) are the most commonly used measurements, resulting in many successful applications. It has been widely observed that disease-induced structural changes may not occur at isolated spots, but in several inter-related regions. Therefore, for better characterization of brain pathology, we propose in this paper a means to extract inter-regional correlation based features from local volumetric measurements. Specifically, our approach involves constructing an anatomical brain network for each subject, with each node representing a Region of Interest (ROI) and each edge representing Pearson correlation of tissue volumetric measurements between ROI pairs. As second order volumetric measurements, network features are more descriptive but also more sensitive to noise. To overcome this limitation, a hierarchy of ROIs is used to suppress noise at different scales. Pairwise interactions are considered not only for ROIs with the same scale in the same layer of the hierarchy, but also for ROIs across different scales in different layers. To address the high dimensionality problem resulting from the large number of network features, a supervised dimensionality reduction method is further employed to embed a selected subset of features into a low dimensional feature space, while at the same time preserving discriminative information. We demonstrate with experimental results the efficacy of this embedding strategy in comparison with some other commonly used approaches. In addition, although the proposed method can be easily generalized to incorporate other metrics of regional similarities, the benefits of using Pearson correlation in our application are reinforced by the experimental results. Without requiring new sources of information, our proposed approach improves the accuracy of MCI prediction from 80.83% (of conventional volumetric features) to 84.35% (of hierarchical network features), evaluated using data sets randomly drawn from the ADNI (Alzheimer's Disease Neuroimaging Initiative) dataset.

UR - http://www.scopus.com/inward/record.url?scp=79960471063&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960471063&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0021935

DO - 10.1371/journal.pone.0021935

M3 - Article

C2 - 21818280

AN - SCOPUS:79960471063

VL - 6

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 7

M1 - e21935

ER -