Predicting Human Intrinsic Functional Connectivity From Structural Connectivity: An Artificial Neural Network Approach

被引:5
作者
Lin, Ying [1 ]
Ma, Junji [1 ]
Huang, Bingjing [1 ]
Zhang, Jinbo [1 ]
Zhang, Yining [1 ]
Dai, Zhengjia [1 ]
机构
[1] Sun Yat Sen Univ, Dept Psychol, Guangzhou 510006, Peoples R China
来源
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING | 2021年 / 8卷 / 03期
基金
中国国家自然科学基金;
关键词
Predictive models; Feature extraction; Task analysis; Shape; Computational modeling; Brain modeling; Artificial neural networks; Resting-state fMRI; diffusion MRI; computational model; artificial neural network; brain connectivity; RESTING-STATE; BRAIN NETWORKS; ARCHITECTURE; DIFFUSION; MODELS; MRI; INFORMATION; ACTIVATION;
D O I
10.1109/TNSE.2021.3102667
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
How structural connectivity (SC) constrains and shapes functional connectivity (FC) in the human brain to support rich cognitive functions has long been a core issue in neuroscience. Although evidence accumulate to suggest that FC strength is correlated with multiple aspects of SC, few studies has analyzed the SC-to-FC relationship in a multivariate manner. This paper proposed a novel usage of the feedforward neural network to predict FC strength as a nonlinear combination of 115 features that described the geometric and topological aspects of SC. The resulting model outperformed four state-of-the-art models in both terms of predictive power and generalizability. Model interpretation analyses found that the geometric features were generally more predictive than the topological ones, providing novel evidence for the significant impact of geometric relationships on FC generation. Comparison of feature contributions to predicting FC with different structural properties further revealed the crucial role of indirect structural paths for inducing FC, particularly between disconnected and/or distanced regions. Together, our results suggested that the flexible FC is significantly but unevenly influenced by the combination of geometric and topological characteristics of the structural network. The proposed framework would also be used for link prediction on top of an underlying topology.
引用
收藏
页码:2625 / 2638
页数:14
相关论文
共 82 条
[1]   The Anatomical Distance of Functional Connections Predicts Brain Network Topology in Health and Schizophrenia [J].
Alexander-Bloch, Aaron F. ;
Vertes, Petra E. ;
Stidd, Reva ;
Lalonde, Francois ;
Clasen, Liv ;
Rapoport, Judith ;
Giedd, Jay ;
Bullmore, Edward T. ;
Gogtay, Nitin .
CEREBRAL CORTEX, 2013, 23 (01) :127-138
[2]   Unified segmentation [J].
Ashburner, J ;
Friston, KJ .
NEUROIMAGE, 2005, 26 (03) :839-851
[3]   Big Data Meet Cyber-Physical Systems: A Panoramic Survey [J].
Atat, Rachad ;
Liu, Lingjia ;
Wu, Jinsong ;
Li, Guangyu ;
Ye, Chunxuan ;
Yi, Yang .
IEEE ACCESS, 2018, 6 :73603-73636
[4]   Automated classification of Alzheimer's disease and mild cognitive impairment using a single MRI and deep neural networks [J].
Basaia, Silvia ;
Agosta, Federica ;
Wagner, Luca ;
Canu, Elisa ;
Magnani, Giuseppe ;
Santangelo, Roberto ;
Filippi, Massimo .
NEUROIMAGE-CLINICAL, 2019, 21
[5]   Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review [J].
Bernal, Jose ;
Kushibar, Kaisar ;
Asfaw, Daniel S. ;
Valverde, Sergi ;
Oliver, Arnau ;
Marti, Robert ;
Llado, Xavier .
ARTIFICIAL INTELLIGENCE IN MEDICINE, 2019, 95 :64-81
[6]   Generative models for network neuroscience: prospects and promise [J].
Betzel, Richard F. ;
Bassett, Danielle S. .
JOURNAL OF THE ROYAL SOCIETY INTERFACE, 2017, 14 (136)
[7]   The economy of brain network organization [J].
Bullmore, Edward T. ;
Sporns, Olaf .
NATURE REVIEWS NEUROSCIENCE, 2012, 13 (05) :336-349
[8]   Complex brain networks: graph theoretical analysis of structural and functional systems [J].
Bullmore, Edward T. ;
Sporns, Olaf .
NATURE REVIEWS NEUROSCIENCE, 2009, 10 (03) :186-198
[9]   An Automatic Design of Factors in a Human-Pose Estimation System Using Neural Networks [J].
Chan, Kai-Chi ;
Koh, Cheng-Kok ;
Lee, C. S. George .
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2016, 46 (07) :875-887
[10]   Activity flow over resting-state networks shapes cognitive task activations [J].
Cole, Michael W. ;
Ito, Takuya ;
Bassett, Danielle S. ;
Schultz, Douglas H. .
NATURE NEUROSCIENCE, 2016, 19 (12) :1718-1726