Abstract
Functional connectivity (FC) network has been becoming an increasingly useful tool for understanding the cerebral working mechanism and mining sensitive biomarkers for neural/mental disease diagnosis. Currently, Pearson’s Correlation (PC) is the simplest and most commonly used scheme in FC estimation. Despite its empirical effectiveness, PC only encodes the low-order (i.e., second-order) statistics by calculating the pairwise correlations between network nodes (brain regions), which fails to capture the high-order information involved in FC (e.g., the correlations among different edges in a network). To address this issue, we propose a novel FC estimation method based on Matrix Variate Normal Distribution (MVND), which can capture both low- and high-order correlations simultaneously with a clear mathematical interpretability. Specifically, we first generate a set of BOLD subseries by the sliding window scheme, and for each subseries we construct a temporal FC network by PC. Then, we employ the constructed FC networks as samples to estimate the final low- and high-order FC networks by maximizing the likelihood of MVND. To illustrate the effectiveness of the proposed method, we conduct experiments to identify subjects with Mild Cognitive Impairment (MCI) from Normal Controls (NCs). Experimental results show that the fusion of low- and high-order FCs can generally help to improve the final classification performance, even though the high-order FCmay contain less discriminative information than its low-order counterpart. Importantly, the proposed method for simultaneous estimation of low- and high-order FCs can achieve better classification performance than the two baseline methods, i.e., the original PC method and a recent high-order FC estimation method.
| Original language | English |
|---|---|
| Article number | 3 |
| Journal | Frontiers in Neuroinformatics |
| Volume | 12 |
| DOIs | |
| Publication status | Published - 2018 Feb 6 |
Fingerprint
Keywords
- Disease diagnosis
- Functional connectivity
- High-order network
- Matrix variate normal distribution
- Mild cognitive impairment
ASJC Scopus subject areas
- Neuroscience (miscellaneous)
- Biomedical Engineering
- Computer Science Applications
Cite this
Simultaneous estimation of low- and high-order functional connectivity for identifying mild cognitive impairment. / Zhou, Yueying; Qiao, Lishan; Li, Weikai; Zhang, Limei; Shen, Dinggang.
In: Frontiers in Neuroinformatics, Vol. 12, 3, 06.02.2018.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Simultaneous estimation of low- and high-order functional connectivity for identifying mild cognitive impairment
AU - Zhou, Yueying
AU - Qiao, Lishan
AU - Li, Weikai
AU - Zhang, Limei
AU - Shen, Dinggang
PY - 2018/2/6
Y1 - 2018/2/6
N2 - Functional connectivity (FC) network has been becoming an increasingly useful tool for understanding the cerebral working mechanism and mining sensitive biomarkers for neural/mental disease diagnosis. Currently, Pearson’s Correlation (PC) is the simplest and most commonly used scheme in FC estimation. Despite its empirical effectiveness, PC only encodes the low-order (i.e., second-order) statistics by calculating the pairwise correlations between network nodes (brain regions), which fails to capture the high-order information involved in FC (e.g., the correlations among different edges in a network). To address this issue, we propose a novel FC estimation method based on Matrix Variate Normal Distribution (MVND), which can capture both low- and high-order correlations simultaneously with a clear mathematical interpretability. Specifically, we first generate a set of BOLD subseries by the sliding window scheme, and for each subseries we construct a temporal FC network by PC. Then, we employ the constructed FC networks as samples to estimate the final low- and high-order FC networks by maximizing the likelihood of MVND. To illustrate the effectiveness of the proposed method, we conduct experiments to identify subjects with Mild Cognitive Impairment (MCI) from Normal Controls (NCs). Experimental results show that the fusion of low- and high-order FCs can generally help to improve the final classification performance, even though the high-order FCmay contain less discriminative information than its low-order counterpart. Importantly, the proposed method for simultaneous estimation of low- and high-order FCs can achieve better classification performance than the two baseline methods, i.e., the original PC method and a recent high-order FC estimation method.
AB - Functional connectivity (FC) network has been becoming an increasingly useful tool for understanding the cerebral working mechanism and mining sensitive biomarkers for neural/mental disease diagnosis. Currently, Pearson’s Correlation (PC) is the simplest and most commonly used scheme in FC estimation. Despite its empirical effectiveness, PC only encodes the low-order (i.e., second-order) statistics by calculating the pairwise correlations between network nodes (brain regions), which fails to capture the high-order information involved in FC (e.g., the correlations among different edges in a network). To address this issue, we propose a novel FC estimation method based on Matrix Variate Normal Distribution (MVND), which can capture both low- and high-order correlations simultaneously with a clear mathematical interpretability. Specifically, we first generate a set of BOLD subseries by the sliding window scheme, and for each subseries we construct a temporal FC network by PC. Then, we employ the constructed FC networks as samples to estimate the final low- and high-order FC networks by maximizing the likelihood of MVND. To illustrate the effectiveness of the proposed method, we conduct experiments to identify subjects with Mild Cognitive Impairment (MCI) from Normal Controls (NCs). Experimental results show that the fusion of low- and high-order FCs can generally help to improve the final classification performance, even though the high-order FCmay contain less discriminative information than its low-order counterpart. Importantly, the proposed method for simultaneous estimation of low- and high-order FCs can achieve better classification performance than the two baseline methods, i.e., the original PC method and a recent high-order FC estimation method.
KW - Disease diagnosis
KW - Functional connectivity
KW - High-order network
KW - Matrix variate normal distribution
KW - Mild cognitive impairment
UR - http://www.scopus.com/inward/record.url?scp=85043754166&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85043754166&partnerID=8YFLogxK
U2 - 10.3389/fninf.2018.00003
DO - 10.3389/fninf.2018.00003
M3 - Article
AN - SCOPUS:85043754166
VL - 12
JO - Frontiers in Neuroinformatics
JF - Frontiers in Neuroinformatics
SN - 1662-5196
M1 - 3
ER -