TY - JOUR
T1 - Multimodal hyper-connectivity of functional networks using functionally-weighted LASSO for MCI classification
AU - Li, Yang
AU - Liu, Jingyu
AU - Gao, Xinqiang
AU - Jie, Biao
AU - Kim, Minjeong
AU - Yap, Pew Thian
AU - Wee, Chong Yaw
AU - Shen, Dinggang
N1 - Funding Information:
This work was supported by the National Natural Science Foundation of China [61671042, 61403016, 61573023], Beijing Natural Science Foundation [4172037], Open Fund Project of Fujian Provincial Key Laboratory in Minjiang University [MJUKF201702], and Engineering and Physical Sciences Research Council (EPSRC) under Grant EP/I011056/1 and Platform Grant EP/H00453X/1, U.K.
Funding Information:
This work was supported by the National Natural Science Foundation of China [ 61671042 , 61403016, 61573023 ], Beijing Natural Science Foundation [ 4172037 ], Open Fund Project of Fujian Provincial Key Laboratory in Minjiang University [ MJUKF201702 ], and Engineering and Physical Sciences Research Council (EPSRC) under Grant EP/I011056/1 and Platform Grant EP/H00453X/1 , U.K.
Publisher Copyright:
© 2018 Elsevier B.V.
PY - 2019/2
Y1 - 2019/2
N2 - Recent works have shown that hyper-networks derived from blood-oxygen-level-dependent (BOLD) fMRI, where an edge (called hyper-edge) can be connected to more than two nodes, are effective biomarkers for MCI classification. Although BOLD fMRI is a high temporal resolution fMRI approach to assess alterations in brain networks, it cannot pinpoint to a single correlation of neuronal activity since BOLD signals are composite. In contrast, arterial spin labeling (ASL) is a lower temporal resolution fMRI technique for measuring cerebral blood flow (CBF) that can provide quantitative, direct brain network physiology measurements. This paper proposes a novel sparse regression algorithm for inference of the integrated hyper-connectivity networks from BOLD fMRI and ASL fMRI. Specifically, a least absolution shrinkage and selection operator (LASSO) algorithm, which is constrained by the functional connectivity derived from ASL fMRI, is employed to estimate hyper-connectivity for characterizing BOLD-fMRI-based functional interaction among multiple regions. An ASL-derived functional connectivity is constructed by using an Ultra-GroupLASSO-UOLS algorithm, where the combination of ultra-least squares (ULS) criterion with a group LASSO (GroupLASSO) algorithm is applied to detect the topology of ASL-based functional connectivity networks, and then an ultra-orthogonal least squares (UOLS) algorithm is used to estimate the connectivity strength. By combining the complementary characterization conveyed by rs-fMRI and ASL fMRI, our multimodal hyper-networks demonstrated much better discriminative characteristics than either the conventional pairwise connectivity networks or the unimodal hyper-connectivity networks. Experimental results on publicly available ADNI dataset demonstrate that the proposed method outperforms the existing single modality based sparse functional connectivity inference methods.
AB - Recent works have shown that hyper-networks derived from blood-oxygen-level-dependent (BOLD) fMRI, where an edge (called hyper-edge) can be connected to more than two nodes, are effective biomarkers for MCI classification. Although BOLD fMRI is a high temporal resolution fMRI approach to assess alterations in brain networks, it cannot pinpoint to a single correlation of neuronal activity since BOLD signals are composite. In contrast, arterial spin labeling (ASL) is a lower temporal resolution fMRI technique for measuring cerebral blood flow (CBF) that can provide quantitative, direct brain network physiology measurements. This paper proposes a novel sparse regression algorithm for inference of the integrated hyper-connectivity networks from BOLD fMRI and ASL fMRI. Specifically, a least absolution shrinkage and selection operator (LASSO) algorithm, which is constrained by the functional connectivity derived from ASL fMRI, is employed to estimate hyper-connectivity for characterizing BOLD-fMRI-based functional interaction among multiple regions. An ASL-derived functional connectivity is constructed by using an Ultra-GroupLASSO-UOLS algorithm, where the combination of ultra-least squares (ULS) criterion with a group LASSO (GroupLASSO) algorithm is applied to detect the topology of ASL-based functional connectivity networks, and then an ultra-orthogonal least squares (UOLS) algorithm is used to estimate the connectivity strength. By combining the complementary characterization conveyed by rs-fMRI and ASL fMRI, our multimodal hyper-networks demonstrated much better discriminative characteristics than either the conventional pairwise connectivity networks or the unimodal hyper-connectivity networks. Experimental results on publicly available ADNI dataset demonstrate that the proposed method outperforms the existing single modality based sparse functional connectivity inference methods.
KW - Arterial spin labeling (ASL)
KW - Hyper-connectivity network
KW - Mild cognitive impairment (MCI)
KW - Multimodality
KW - Ultra-least squares (ULS)
KW - Weighted LASSO
UR - http://www.scopus.com/inward/record.url?scp=85056984235&partnerID=8YFLogxK
U2 - 10.1016/j.media.2018.11.006
DO - 10.1016/j.media.2018.11.006
M3 - Article
C2 - 30472348
AN - SCOPUS:85056984235
SN - 1361-8415
VL - 52
SP - 80
EP - 96
JO - Medical Image Analysis
JF - Medical Image Analysis
ER -