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 language | English |
|---|---|
| Article number | e21935 |
| Journal | PLoS One |
| Volume | 6 |
| Issue number | 7 |
| DOIs | |
| Publication status | Published - 2011 Jul 22 |
| Externally published | Yes |
Fingerprint
ASJC Scopus subject areas
- Agricultural and Biological Sciences(all)
- Biochemistry, Genetics and Molecular Biology(all)
- Medicine(all)
Cite this
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 journal › Article
}
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 -