An Ant Colony Optimization Algorithm Merged With Multiple Source Information for Learning Brain Effective Connectivity Networks

被引：0
|
作者：
Ji J.-Z. [1 ]
Liu J.-D. [1 ]
Zou A.-X. [1 ]
Yang C.-C. [1 ]
机构：
[1] Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Faculty of Information Technology, Beijing University of Technology, Beijing
来源：
Zidonghua Xuebao/Acta Automatica Sinica | 2021年 / 47卷 / 04期
基金：
中国国家自然科学基金;
关键词：
Ant colony optimization; Brain effective connectivity network; Heuristic function revision; Multiple source information fusion; Search space compression;
D O I：
10.16383/j.aas.c180680
中图分类号：
学科分类号：
摘要：
The research of brain effective connectivity (EC) networks is an important topic within the community of human brain connectome, where identifying brain EC networks from neuroimaging data has become an effective tool which can evaluate normal brain functions and their injuries associated with neurodegenerative diseases. For learning brain EC networks from functional magnetic resonance imaging data, this paper proposes an ant colony optimization algorithm merged with multiple source information, called ACOMM-EC. First, the new algorithm employs diffusion tensor imaging data to acquire anatomical constraint information among regions of interest (ROIs), and uses Pearson positive correlated information to restrict the search spaces of feasible solutions so that many unnecessary searches of ants can be avoided. And then, by combining the joint active information between two nodes of an arc and the original heuristic function, a new heuristic function with a better heuristic ability is given to induct the process of stochastic searches, which enhances the purpose of ants searching, and improves the optimization efficiency. Finally, the algorithm is tested on different data and compared with some recently proposed algorithms. The results show that the two strategies are effective, and the solution quality of the new algorithm precedes the other algorithms while the convergence speed is faster. Copyright © 2021 Acta Automatica Sinica. All rights reserved.
引用
收藏
页码：864 / 881
页数：17
相关论文
共 40 条
  • [1] Lehrer J., Neuroscience: making connections, Nature News, 457, 7229, pp. 524-527, (2009)
  • [2] Liang Xia, Wang Jin-Hui, He Yong, Human connectome: Structural and functional brain networks, Chinese Science Bulletin, 55, 16, pp. 1565-1583, (2010)
  • [3] Zuo Xi-Nian, Zhang Zhe, He Yong, Et al., The human functional conncetome: Its methodology, developmental trajectory and behavioral association, Chinese Science Bulletin, 57, 35, pp. 3399-3413, (2012)
  • [4] Warnick R, Guindani M, Erhardt E, Et al., A Bayesian approach for estimating dynamic functional network connectivity in fMRI data, Journal of the American Statistical Association, 113, 521, pp. 134-151, (2018)
  • [5] Pallares V, Insabato A, Sanjuan A, Et al., Extracting orthogonal subject-and condition-specific signatures from fMRI data using whole-brain effective connectivity, Neuroimage, 178, pp. 238-254, (2018)
  • [6] Smith S M, Miller K L, Salimi-Khorshidi G, Et al., Network modelling methods for FMRI, Neuroimage, 54, 2, pp. 875-891, (2011)
  • [7] Scherr M, Utz L, Tahmasian M, Et al., Effective connectivity in the default mode network is distinctively disrupted in Alzheimer's disease -- a simultaneous resting-state FDG-PET/fMRI study, Human Brain Mapping, (2019)
  • [8] Liu J, Ji J, Zhang A, Liang P., An ant colony optimization algorithm for learning brain effective connectivity network from fMRI data, Proceedings of the 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 360-367, (2016)
  • [9] Seth A K., A MATLAB toolbox for Granger causal connectivity analysis, Journal of Neuroscience Methods, 186, 2, pp. 262-273, (2010)
  • [10] Goebel R, Roebroeck A, Kim D S, Et al., Investigating directed cortical interactions in time-resolved fMRI data using vector autoregressive modeling and Granger causality mapping, Magnetic Resonance Imaging, 21, 10, pp. 1251-1261, (2003)
1234