基于多目标优化约束独立成分分析方法的fMRI数据分析研究

doi:10.3969/j.issn.0258-8021.2021.01.03

Abstract
Figure/Table
References
Related Citation (7)

Download: PDF (20062 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Constrained independent component analysis (CICA) greatly improves the performance of blind source signal analysis of independent component analysis (ICA) by incorporating priori information, nevertheless, the current CICA method has some problems, such as the difficulty in obtaining prior information, selecting threshold parameters of prior information constraints, and using priori information effectively, which need to be improved. Targeting to these problems, this paper established a CICA model that simultaneously integrated temporal and spatial priori information on the basis of multi-objective optimization framework, and solved the problem of selecting threshold parameters in CICA through multi-objective optimization strategy. Furthermore, an adaptive mining algorithm was proposed to extract intrinsic a priori information from the fMRI data of multiple subjects to guide the analysis of fMRI group data, thus providing a new way for CICA to obtain priori information. Finally, 10 simulated data, 5 task-state and 23 resting-state fMRI data were used to verify the effectiveness of the proposed method. The results showed that the spatio-temporal source signals obtained by multi-objective optimization based CICA (MOPCICA) were generally superior to those obtained by ICA, CICA with temporal reference (CICA-tR) and CICA with spatial reference (CICA-sR) (P<0.05) (in the simulation data, the corresponding spatial AUC and temporal correlation coefficients were 0.75±0.05, 0.62±0.02, 0.72±0.03, 0.71±0.06 and 0.81±0.13, 0.67±0.04, 0.74±0.09, 0.77±0.13, respectively); while the spatial independence was superior to CICA-tR and CICA-sR (P<0.05) (in the task-related data, the corresponding kurtosis and negentropy were 69.20±23.36, 17.60±13.22, 36.71±13.43 and 0.031 2±0.007 7,0.003 7±0.002 1,0.018 4±0.004 5, respectively), which indicated that it had a better performance for the blind source signal recovery. Meanwhile, the correlation coefficient between the group component obtained by MOPCICA through using the fMRI intrinsic priori information in the resting state data and the corresponding component of each subject in the group was on average higher than that of ICA, CICA-nR and CICA-fR (P<0.05), which were 0.46±0.08, 0.44±0.08, 0.45±0.08 and 0.44±0.08 separately, thus can better represented the commonality of the subjects in the group. Therefore, it has a great significance for the fMRI brain functional connectivity detection.

Key words： functional magnetic resonance imaging constrained independent component analysis intrinsic prior information multi-objective optimization

Received: 11 March 2019

PACS:

R318

Corresponding Authors: *E-mail: shiyuhu@shmtu.edu.cn

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Shi Yuhu
	Zeng Weiming
	Deng Jin
	Wang Nizhuan

Cite this article:

Shi Yuhu,Zeng Weiming,Deng Jin, et al. Study on fMRI Data Analysis Based on Multi-Objective Optimization CICA[J]. Chinese Journal of Biomedical Engineering, 2021, 40(1): 19-32.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2021.01.03 OR http://cjbme.csbme.org/EN/Y2021/V40/I1/19

[1] Cao Jin, Worsley K. The geometry of correlation fields with an application to functional connectivity of the brain[J]. The Annals of Applied Probability, 1999, 9 (4): 1021-1057.
[2] Sun FT, Miller LM, D'Esposito M. Measuring interregional functional connectivity using coherence and partial coherence analyses of fMRI data[J]. Neuroimage, 2004, 21 (2): 647-658.
[3] Friston KJ, Holmes AP, Worsley KJ, et al. Statistical parametric maps in functional imaging: a general linear approach[J]. Human Brain Mapping, 1994, 2 (4): 189-210.
[4] Golay X, Kollias S, Stoll G, et al. A new correlation-based fuzzy logic clustering algorithm for fMRI[J]. Magnetic Resonance in Medicine, 1998, 40 (2): 249-260.
[5] Cordes D, Haughton V, Carew J, et al. Hierarchical clustering to measure connectivity in fMRI resting-state data[J]. Magnetic Resonance Imaging, 2002, 20 (4): 305-317.
[6] Frey BJ, Dueck D. Clustering by passing messages between data points [J]. Science, 2007, 315 (5814): 972-976.
[7] Zhang Jiang, Li Dahuan, Chen Huafu, et al. Analysis of activity in fMRI data using affinity propagation clustering [J]. Computer Methods in Biomechanics and Biomedical Engineering, 2011, 14 (3): 271-281.
[8] Alexander ME, Baumgartner R. The importance of appropriate (sparse) representation of data: Application to de-noising fMRI time courses[J]. NeuroImage, 2001, 13 (6): 60-60.
[9] Georgiev P, Theis F, Cichocki A, et al. Sparse component analysis: a new tool for data mining[J]. Data Mining in Biomedicine, 2007: 91-116.
[10] Daubechies I, Roussos E, Takerkart S, et al. Independent component analysis for brain fMRI does not select for independence[J]. Proceedings of the National Academy of Sciences, 2009, 106 (26): 10415-10422.
[11] Comon P. Independent component analysis, A new concept? [J]. Signal Processing, 1994, 36 (3): 287-314.
[12] Calhoun VD, Adali T. Unmixing fMRI with independent component analysis[J]. IEEE Engineering in Medicine and Biology Magazine, 2006, 25 (2): 79-90.
[13] 白保东, 刘健, 柯丽, 等. 基于时空ICA 的脑功能成像思维干扰消除[J]. 仪器仪表学报, 2013, 34 (9): 2095-2102.
[14] McKeown MJ, Makeig S, Brown GG, et al. Analysis of fMRI data by blind separation into spatial independent component analysis[J]. Human Brain Mapping, 1998, 6 (3): 160-188.
[15] Calhoun VD, Adali T, Pearlson, GD, et al. Spatial and temporal independent component analysis of functional MRI data containing a pair of task related waveforms[J]. Human Brain Mapping, 2001, 13 (1): 43-53.
[16] Stone JV, Porrill J, Porter NR, et al. Spatiotemporal independent component analysis of event-Related fMRI data using skewed probability density functions[J]. NeuroImage, 2002, 15 (2): 407-421.
[17] Beckmann C, Smith S. Probabilistic independent component analysis for functional magnetic resonance imaging[J]. IEEE Transactions on Medical Imaging, 2004, 23 (2): 137-152.
[18] Moher Alsady T, Blessing EM, Beissner F. MICA—A toolbox for masked independent component analysis of fMRI data [J]. Human Brain Mapping, 2016, 37(10): 3544-3556.
[19] Calhoun VD, Adali T, Pearlson GD, et al. A method for making group inferences from functional MRI data using independent component analysis[J]. Human Brain Mapping, 2001, 14 (3): 140-151.
[20] Calhoun VD, Silva RF, Adalı T, et al. Comparison of PCA approaches for very large group ICA[J]. NeuroImage, 2015, 118: 662-666.
[21] Svensén M, Kruggel F, Benali H. ICA of fMRI group study data[J]. NeuroImage, 2002, 16 (3): 551-563.
[22] James CJ, Gibson OJ. Temporally constrained ICA: An application to artifact rejection in electro-magnetic brain signal analysis [J]. IEEE Transactions on Biomedical Engineering, 2003, 50 (9): 1108-1116.
[23] Calhoun VD, Adali T, Stevens MC, et al. Semi-blind ICA of fMRI: A method for utilizing hypothesis-derived time courses in a spatial ICA analysis[J]. NeuroImage, 2005, 25 (2): 527-538.
[24] Huang Deshuang, Mi Jianxun. A new constrained independent component analysis method[J]. IEEE Transactions on Neural Networks, 2007, 18 (5): 1532-1535.
[25] Zhang Zhilin. Morphologically constrained ICA for extracting weak temporally correlated signals[J]. Neurocomputing, 2008, 71 (7): 1669-1679.
[26] Zhang Hongjuan, Shi Zhenwei, Guo Chonghui, et al. Semi-blind source extraction algorithm for fetal electrocardiogram based on generalized autocorrelations and reference signals[J]. Journal of Computational and Applied Mathematics, 2009, 223 (1): 409-420.
[27] Lu Wei, Rajapakse JC. Constrained independent component analysis[C]// Proceedings of the 13th International Conference on Neural Information Processing Systems (NIPS2000). Cambridge: MIT Press, 2000, 13: 570-576.
[28] Lu Wei, Rajapakse JC. ICA with reference [J]. Neurocomputing, 2006, 69 (16): 2244-2257.
[29] Lin Qiuhua, Liu Jingyu, Zheng Yongrui, et al. Semiblind spatial ICA of fMRI using spatial constraints[J]. Human Brain Mapping, 2010, 31 (7): 1076-1088.
[30] Lu Wei, Rajapakse JC. Approach and applications of constrained ICA[J]. IEEE Transactions on Neural Networks, 2005, 16 (1): 203-212.
[31] Ma Xinyue, Zhang Hang, Zhao Xiaojie, et al. Semi-blind independent component analysis of fMRI based on real-time fMRI system[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2013, 21 (3): 416-426.
[32] Soldati N, Calhoun VD, Bruzzone L, et al. ICA analysis of fMRI with real-time constraints: an evaluation of fast detection performance as function of algorithms, parameters and a priori conditions[J]. Frontiers in Human Neuroscience, 2013, 7 (7): 19.
[33] Barros AK, Vigario R, Jousmaki V, et al. Extraction of event related signals from multi-channel bio-electrical measurements[J]. IEEE Transactions on Biomedical Engineering, 2000, 47 (5): 583-588.
[34] Du Yuhui, Fan Yong. Group information guided ICA for fMRI data analysis[J]. NeuroImage, 2013, 69:157-197.
[35] Wang Zhi, Xia Maogeng, Jin Zhen, et al. Temporally and spatially constrained ICA of fMRI data analysis[J]. PLoS ONE, 2014, 9 (4): e94211.
[36] Li YO, Adalı T, Calhoun VD. Estimating the number of independent components for functional magnetic resonance imaging data[J]. Human Brain Mapping, 2007, 28 (11): 1251-1266.
[37] Himberg J, Hyvärinen A, Esposito F. Validating the independent components of neuroimaging time series via clustering and visualization[J]. Neuroimage, 2004, 22 (3): 1214-1222.
[38] Shi Yuhu, Zeng Weiming, Wang Nizhuan, et al. A new method for independent component analysis with priori information based on multi-objective optimization[J]. Journal of Neuroscience Methods, 2017, 283: 72-82.
[39] Klamroth K, Jørgen T. Constrained optimization using multiple objective programming[J]. Journal of Global Optimization, 2007, 37 (3): 325-355.
[40] Friston KJ, Frith CD, Turner R, et al. Characterizing evoked hemodynamics with fMRI [J]. NeuroImage, 1995, 2 (2): 157–165.
[41] Erhardt EB, Allen A, Wei YT, et al. SimTB, A simulation toolbox for fMRI data under a model of spatiotemporal separability[J]. NeuroImage, 2012, 59: 4160-4167.
[42] Shi Yuhu, Zeng Weiming, Wang Nizhuan, et al. A new constrained spatiotemporal ICA method based on multi-objective optimization for fMRI data analysis[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2018, 26: 1690-1699.
[43] Shi Yuhu, Zeng Weiming, Tang Xiaoyan, et al. An improved multi-objective optimization-based CICA method with data-driver temporal reference for group fMRI data analysis[J]. Medical & Biological Engineering & Computing, 2017, 56: 683-694.
[44] Shi Yuhu, Zeng Weiming, Wang Nizhuan, et al. A novel fMRI group data analysis method based on data-driven reference extracting from group subjects[J]. Computer Methods and Programs Biomedicine, 2015, 122(3): 362-371.