Brain functional network reconstruction based on compressed sensing and fast iterative shrinkage-thresholding algorithm_Journal of Biomedical Engineering

Authors：

GUO Qing ^1,2 ,  TENG Yueyang ^1,2 , TONG Can ^1,2 , LI Disen ¹ , WANG Xuefei ¹

1. College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110169, P.R.China;
2. Key Laboratory for Medical Imaging Intelligent Computing of Ministry of Education, Shenyang 110169, P.R.China;

Corresponding author：

TENG Yueyang, Email: tengyy@bmie.neu.edu.cn

Keywords：

brain functional network; compressed sensing; fast iterative shrinkage-thresholding algorithm; least absolute shrinkage and selection operator

DOI：

10.7507/1001-5515.201908024

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

The construction of brain functional network based on resting-state functional magnetic resonance imaging (fMRI) is an effective method to reveal the mechanism of human brain operation, but the common brain functional network generally contains a lot of noise, which leads to wrong analysis results. In this paper, the least absolute shrinkage and selection operator (LASSO) model in compressed sensing is used to reconstruct the brain functional network. This model uses the sparsity of L₁-norm penalty term to avoid over fitting problem. Then, it is solved by the fast iterative shrinkage-thresholding algorithm (FISTA), which updates the variables through a shrinkage threshold operation in each iteration to converge to the global optimal solution. The experimental results show that compared with other methods, this method can improve the accuracy of noise reduction and reconstruction of brain functional network to more than 98%, effectively suppress the noise, and help to better explore the function of human brain in noisy environment.

Citation： GUO Qing, TENG Yueyang, TONG Can, LI Disen, WANG Xuefei. Brain functional network reconstruction based on compressed sensing and fast iterative shrinkage-thresholding algorithm. Journal of Biomedical Engineering, 2020, 37(5): 855-862. doi: 10.7507/1001-5515.201908024 Copy

1.	Kundu S, Jin Ming, Pierce J, et al. Estimating dynamic brain functional networks using multi-subject fMRI data. Neuroimage, 2018, 183: 635-649.
2.	Poulakis K, Pereira J B, Mecocci P, et al. Heterogeneous patterns of brain atrophy in Alzheimer's disease. Neurobiol Aging, 2018, 65: 98-108.
3.	Li Y, Yang H, Lei B, et al. Novel effective connectivity inference using ultra-group constrained orthogonal forward regression and elastic multilayer perceptron classifier for MCI identification. IEEE Trans Med Imaging, 2019, 38(5): 1227-1239.
4.	Sato J R, Calebe V M, de Siqueira S S, et al. Complex network measures in autism spectrum disorders. IEEE/ACM Trans Comput Biol Bioinform, 2018, 15(2): 581-587.
5.	Liao X, Vasilakos A V, He Yong. Small-world human brain networks: perspectives and challenges. Neurosci Biobehav Rev, 2017, 77: 286-300.
6.	Smyser C D, Neil J J. Use of resting-state functional MRI to study brain development and injury in neonates. Semin Perinatol, 2015, 39(2): 130-140.
7.	Li H, Zhou H, Yang Yang, et al. More randomized and resilient in the topological properties of functional brain networks in patients with major depressive disorder. J Clin Neurosci, 2017, 44: 274-278.
8.	Zhang F, Qiu L, Yuan Lili, et al. Evidence for progressive brain abnormalities in early schizophrenia: a cross-sectional structural and functional connectivity study. Schizophr Res, 2014, 159(1): 31-35.
9.	Hillary F G, Grafman J H. Injured brains and adaptive networks: the benefits and costs of hyperconnectivity. Trends Cogn Sci, 2017, 21(5): 385-401.
10.	Gross S, Vionnet L, Kasper L, et al. Physiology recording with magnetic field probes for fMRI denoising. Neuroimage, 2017, 154: 106-114.
11.	Kundu P, Voon V, Balchandani P, et al. Multi-echo fMRI: a review of applications in fMRI denoising and analysis of BOLD signals. Neuroimage, 2017, 154: 59-80.
12.	Bhadra A, Datta J, Polson N G, et al. Lasso meets horseshoe: a survey. Stat Sci, 2019, 34(3): 405-427.
13.	Daubechies I, Defrise M, Mol C D. An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun Pure Appl Math, 2004, 57(11): 1413-1457.
14.	Teng Yueyang, Qing Guo, Wang Ge. Smoothing L0- and L1-Norm regularizers and their relations to non-local means for CT reconstruction//Developments in X-Ray Tomography XII, San Diego: SPIE, 2019: 11113.
15.	Yao Z, Zou Ying, Zheng W, et al. Structural alterations of the brain preceded functional alterations in major depressive disorder patients: evidence from multimodal connectivity. J Affect Disord, 2019, 253: 107-117.
16.	Lee H, Lee D S, Kang H, et al. Sparse brain network recovery under compressed sensing. IEEE Trans Med Imaging, 2011, 30(5): 1154-1165.
17.	Lee J D, Sun D L, Sun Y, et al. Exact post-selection inference, with application to the lasso. Ann Stat, 2016, 44(3): 907-927.
18.	Beck A, Teboulle M. A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J Imaging Sci, 2009, 2(1): 183-202.
19.	Katta R, Reddy G D, Sukavanam N. Computation of control for linear approximately controllable system using weighted Tikhonov regularization. Appl Math Comput, 2018, 317: 252-263.
20.	Chung M K, Hanson J L, Ye J, et al. Persistent homology in sparse regression and its application to brain morphometry. IEEE Trans Med Imaging, 2015, 34(9): 1928-1939.
21.	Huang S, Li J, Sun L, et al. Learning brain connectivity of Alzheimer's disease by sparse inverse covariance estimation. Neuroimage, 2010, 50(3): 935-949.
22.	Yu Renping, Zhang Han, An Le, et al. Correlation-weighted sparse group representation for brain network construction in MCI classification. Hum Brain Mapp, 2017, 38(5): 2370-2383.
23.	Sun Y, Lim J, Dai Zhongxiang, et al. The effects of a mid-task break on the brain connectome in healthy participants: a resting-state functional MRI study. Neuroimage, 2017, 152: 19-30.
24.	Dosenbach N U, Fair D A, Cohen A L, et al. A dual-networks architecture of top-down control. Trends Cogn Sci, 2008, 12(3): 99-105.

1. Kundu S, Jin Ming, Pierce J, et al. Estimating dynamic brain functional networks using multi-subject fMRI data. Neuroimage, 2018, 183: 635-649.
2. Poulakis K, Pereira J B, Mecocci P, et al. Heterogeneous patterns of brain atrophy in Alzheimer's disease. Neurobiol Aging, 2018, 65: 98-108.
3. Li Y, Yang H, Lei B, et al. Novel effective connectivity inference using ultra-group constrained orthogonal forward regression and elastic multilayer perceptron classifier for MCI identification. IEEE Trans Med Imaging, 2019, 38(5): 1227-1239.
4. Sato J R, Calebe V M, de Siqueira S S, et al. Complex network measures in autism spectrum disorders. IEEE/ACM Trans Comput Biol Bioinform, 2018, 15(2): 581-587.
5. Liao X, Vasilakos A V, He Yong. Small-world human brain networks: perspectives and challenges. Neurosci Biobehav Rev, 2017, 77: 286-300.
6. Smyser C D, Neil J J. Use of resting-state functional MRI to study brain development and injury in neonates. Semin Perinatol, 2015, 39(2): 130-140.
7. Li H, Zhou H, Yang Yang, et al. More randomized and resilient in the topological properties of functional brain networks in patients with major depressive disorder. J Clin Neurosci, 2017, 44: 274-278.
8. Zhang F, Qiu L, Yuan Lili, et al. Evidence for progressive brain abnormalities in early schizophrenia: a cross-sectional structural and functional connectivity study. Schizophr Res, 2014, 159(1): 31-35.
9. Hillary F G, Grafman J H. Injured brains and adaptive networks: the benefits and costs of hyperconnectivity. Trends Cogn Sci, 2017, 21(5): 385-401.
10. Gross S, Vionnet L, Kasper L, et al. Physiology recording with magnetic field probes for fMRI denoising. Neuroimage, 2017, 154: 106-114.
11. Kundu P, Voon V, Balchandani P, et al. Multi-echo fMRI: a review of applications in fMRI denoising and analysis of BOLD signals. Neuroimage, 2017, 154: 59-80.
12. Bhadra A, Datta J, Polson N G, et al. Lasso meets horseshoe: a survey. Stat Sci, 2019, 34(3): 405-427.
13. Daubechies I, Defrise M, Mol C D. An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun Pure Appl Math, 2004, 57(11): 1413-1457.
14. Teng Yueyang, Qing Guo, Wang Ge. Smoothing L0- and L1-Norm regularizers and their relations to non-local means for CT reconstruction//Developments in X-Ray Tomography XII, San Diego: SPIE, 2019: 11113.
15. Yao Z, Zou Ying, Zheng W, et al. Structural alterations of the brain preceded functional alterations in major depressive disorder patients: evidence from multimodal connectivity. J Affect Disord, 2019, 253: 107-117.
16. Lee H, Lee D S, Kang H, et al. Sparse brain network recovery under compressed sensing. IEEE Trans Med Imaging, 2011, 30(5): 1154-1165.
17. Lee J D, Sun D L, Sun Y, et al. Exact post-selection inference, with application to the lasso. Ann Stat, 2016, 44(3): 907-927.
18. Beck A, Teboulle M. A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J Imaging Sci, 2009, 2(1): 183-202.
19. Katta R, Reddy G D, Sukavanam N. Computation of control for linear approximately controllable system using weighted Tikhonov regularization. Appl Math Comput, 2018, 317: 252-263.
20. Chung M K, Hanson J L, Ye J, et al. Persistent homology in sparse regression and its application to brain morphometry. IEEE Trans Med Imaging, 2015, 34(9): 1928-1939.
21. Huang S, Li J, Sun L, et al. Learning brain connectivity of Alzheimer's disease by sparse inverse covariance estimation. Neuroimage, 2010, 50(3): 935-949.
22. Yu Renping, Zhang Han, An Le, et al. Correlation-weighted sparse group representation for brain network construction in MCI classification. Hum Brain Mapp, 2017, 38(5): 2370-2383.
23. Sun Y, Lim J, Dai Zhongxiang, et al. The effects of a mid-task break on the brain connectome in healthy participants: a resting-state functional MRI study. Neuroimage, 2017, 152: 19-30.
24. Dosenbach N U, Fair D A, Cohen A L, et al. A dual-networks architecture of top-down control. Trends Cogn Sci, 2008, 12(3): 99-105.

Journal of Biomedical Engineering

Brain functional network reconstruction based on compressed sensing and fast iterative shrinkage-thresholding algorithm

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content