TY - JOUR
T1 - Improving sparsity and modularity of high-order functional connectivity networks for MCI and ASD identification
AU - Zhou, Yueying
AU - Zhang Teng, Limei Shenghua
AU - Qiao, Lishan
AU - Shen, Dinggang
N1 - Funding Information:
We thank Yining Zhang for the insightful and helpful discussions. This work is partly supported by National Natural Science Foundation of China (61402215), and Natural Science Foundation of Shandong Province(ZR2018MF020).
Publisher Copyright:
© 2018 Zhou, Zhang, Teng, Qiao and Shen.
PY - 2018
Y1 - 2018
N2 - High-order correlation has recently been proposed to model brain functional connectivity network (FCN) for identifying neurological disorders, such as mild cognitive impairment (MCI) and autism spectrum disorder (ASD). In practice, the high-order FCN (HoFCN) can be derived from multiple low-order FCNs that are estimated separately in a series of sliding windows, and thus it in fact provides a way of integrating dynamic information encoded in a sequence of low-order FCNs. However, the estimation of low-order FCN may be unreliable due to the fact that the use of limited volumes/samples in a sliding window can significantly reduce the statistical power, which in turn affects the reliability of the resulted HoFCN. To address this issue, we propose to enhance HoFCN based on a regularized learning framework. More specifically, we first calculate an initial HoFCN using a recently developed method based on maximum likelihood estimation. Then, we learn an optimal neighborhood network of the initially estimated HoFCN with sparsity and modularity priors as regularizers. Finally, based on the improved HoFCNs, we conduct experiments to identify MCI and ASD patients from their corresponding normal controls. Experimental results show that the proposed methods outperform the baseline methods, and the improved HoFCNs with modularity prior consistently achieve the best performance.
AB - High-order correlation has recently been proposed to model brain functional connectivity network (FCN) for identifying neurological disorders, such as mild cognitive impairment (MCI) and autism spectrum disorder (ASD). In practice, the high-order FCN (HoFCN) can be derived from multiple low-order FCNs that are estimated separately in a series of sliding windows, and thus it in fact provides a way of integrating dynamic information encoded in a sequence of low-order FCNs. However, the estimation of low-order FCN may be unreliable due to the fact that the use of limited volumes/samples in a sliding window can significantly reduce the statistical power, which in turn affects the reliability of the resulted HoFCN. To address this issue, we propose to enhance HoFCN based on a regularized learning framework. More specifically, we first calculate an initial HoFCN using a recently developed method based on maximum likelihood estimation. Then, we learn an optimal neighborhood network of the initially estimated HoFCN with sparsity and modularity priors as regularizers. Finally, based on the improved HoFCNs, we conduct experiments to identify MCI and ASD patients from their corresponding normal controls. Experimental results show that the proposed methods outperform the baseline methods, and the improved HoFCNs with modularity prior consistently achieve the best performance.
KW - Autism spectrum disorder
KW - Dynamic network
KW - Functional connectivity network
KW - High-order correlation
KW - Mild cognitive impairment
KW - Modularity
UR - http://www.scopus.com/inward/record.url?scp=85079125344&partnerID=8YFLogxK
U2 - 10.3389/fnins.2018.00959
DO - 10.3389/fnins.2018.00959
M3 - Article
AN - SCOPUS:85079125344
SN - 1662-4548
VL - 12
JO - Frontiers in Neuroscience
JF - Frontiers in Neuroscience
M1 - 959
ER -