TY - JOUR
T1 - Learning Brain Functional Networks With Latent Temporal Dependency for MCI Identification
AU - Xue, Yanfang
AU - Zhang, Yining
AU - Zhang, Limei
AU - Lee, Seong Whan
AU - Qiao, Lishan
AU - Shen, Dinggang
N1 - Funding Information:
Manuscript received March 25, 2021; accepted July 28, 2021. Date of publication August 4, 2021; date of current version January 20, 2022. This work was supported by the National Natural Science Foundation of China under Grants 61976110 and 11931008, and in part by the Natural Science Foundation of Shandong Province under Grant ZR2018MF020. (Corresponding author: Lishan Qiao.) Yanfang Xue, Yining Zhang, and Limei Zhang are with the School of Mathematical Sciences, Liaocheng University, China.
Publisher Copyright:
© 1964-2012 IEEE.
PY - 2022/2/1
Y1 - 2022/2/1
N2 - Resting-state functional magnetic resonance imaging (rs-fMRI) has become a popular non-invasive way of diagnosing neurological disorders or their early stages by probing functional connectivity between different brain regions of interest (ROIs) across subjects. In the past decades, researchers have proposed many methods to estimate brain functional networks (BFNs) based on blood-oxygen-level-dependent (BOLD) signals captured by rs-fMRI. However, most of the existing methods estimate BFNs under the assumption that signals are independently sampled, which ignores the temporal dependency and sequential order of different time points (or volumes). To address this problem, in this paper, we first propose a novel BFN estimation model by introducing a latent variable to control the sequence of volumes for encoding the temporal dependency and sequential information of signals into the estimated BFNs. Then, we develop an efficient learning algorithm to solve the proposed model by the alternating optimization scheme. To verify the effectiveness of the proposed method, the estimated BFNs are used to identify subjects with mild cognitive impairment (MCIs) from normal controls (NCs). Experimental results show that our method outperforms the baseline methods in the terms of classification performance.
AB - Resting-state functional magnetic resonance imaging (rs-fMRI) has become a popular non-invasive way of diagnosing neurological disorders or their early stages by probing functional connectivity between different brain regions of interest (ROIs) across subjects. In the past decades, researchers have proposed many methods to estimate brain functional networks (BFNs) based on blood-oxygen-level-dependent (BOLD) signals captured by rs-fMRI. However, most of the existing methods estimate BFNs under the assumption that signals are independently sampled, which ignores the temporal dependency and sequential order of different time points (or volumes). To address this problem, in this paper, we first propose a novel BFN estimation model by introducing a latent variable to control the sequence of volumes for encoding the temporal dependency and sequential information of signals into the estimated BFNs. Then, we develop an efficient learning algorithm to solve the proposed model by the alternating optimization scheme. To verify the effectiveness of the proposed method, the estimated BFNs are used to identify subjects with mild cognitive impairment (MCIs) from normal controls (NCs). Experimental results show that our method outperforms the baseline methods in the terms of classification performance.
KW - Alzheimer's disease (AD)
KW - brain functional networks (BFNs)
KW - mild cognitive impairment (MCI)
KW - sequential information
KW - temporal dependency
UR - http://www.scopus.com/inward/record.url?scp=85112598365&partnerID=8YFLogxK
U2 - 10.1109/TBME.2021.3102015
DO - 10.1109/TBME.2021.3102015
M3 - Article
C2 - 34347591
AN - SCOPUS:85112598365
SN - 0018-9294
VL - 69
SP - 590
EP - 601
JO - IEEE Transactions on Biomedical Engineering
JF - IEEE Transactions on Biomedical Engineering
IS - 2
ER -