GPU-based parallel group ICA for functional magnetic resonance data

Computer Methods and Programs in Biomedicine

Volumn 119, Issue 1, 2015, Pages 9-16

  Jing, Yanshan ^a   Zeng, Weiming ^a   Wang, Nizhuan ^a   Ren, Tianlong ^a   Shi, Yingchao ^a   Yin, Jun ^a   Xu, Qi ^a  

^a SHANGHAI MARITIME UNIVERSITY   (China)

Author keywords

FMRI; GPGPU; Group ICA; Parallel computing

Indexed keywords

COMPUTER GRAPHICS; COST BENEFIT ANALYSIS; INDEPENDENT COMPONENT ANALYSIS; INFORMATION ANALYSIS; MAGNETIC RESONANCE IMAGING; PARALLEL ARCHITECTURES; PARALLEL PROCESSING SYSTEMS; PRINCIPAL COMPONENT ANALYSIS; PROGRAM PROCESSORS;

FMRI; FUNCTIONAL CONNECTIVITY; FUNCTIONAL MAGNETIC RESONANCE IMAGING; GENERAL-PURPOSE COMPUTING; GPGPU; GRAPHICS PROCESSING UNIT; INDEPENDENT COMPONENT ANALYSIS(ICA); PARALLEL IMPLEMENTATIONS;

DATA HANDLING;

ARTICLE; AUDITORY CORTEX; COMPUTER; COMPUTER PROGRAM; COST; DATA ANALYSIS; DATA PROCESSING; DEFAULT MODE NETWORK; FRONTAL LOBE; FUNCTIONAL MAGNETIC RESONANCE IMAGING; GRAPHIC PROCESSING UNIT; IMAGE PROCESSING; INDEPENDENT COMPONENT ANALYSIS; LEARNING ALGORITHM; MATHEMATICAL COMPUTING; OCCIPITAL CORTEX; PARIETAL LOBE; PRECUNEUS; SINGULAR VALUE DECOMPOSITION; VISUAL CORTEX; ARTIFICIAL NEURAL NETWORK; BIOLOGY; BRAIN; COMPUTER ASSISTED DIAGNOSIS; FUNCTIONAL NEUROIMAGING; HUMAN; INFORMATION PROCESSING; NUCLEAR MAGNETIC RESONANCE IMAGING; PHYSIOLOGY; PRINCIPAL COMPONENT ANALYSIS; STATISTICS AND NUMERICAL DATA;

AUTOMATIC DATA PROCESSING; BRAIN; COMPUTATIONAL BIOLOGY; FUNCTIONAL NEUROIMAGING; HUMANS; IMAGE INTERPRETATION, COMPUTER-ASSISTED; MAGNETIC RESONANCE IMAGING; NEURAL NETWORKS (COMPUTER); PRINCIPAL COMPONENT ANALYSIS; SOFTWARE;

EID: 84924548399     PISSN: 01692607     EISSN: 18727565     Source Type: Journal    
DOI: 10.1016/j.cmpb.2015.02.002     Document Type: Article

References (26)

1. Yao C., Liu Y., Yao J., et al. Augment low-field intra-operative MRI with preoperative MRI using a hybrid non-rigid registration method. Comput. Methods Programs Biomed. 2014, 117(2):114-124.
2. Gembris D., Neeb M., Gipp M., et al. Correlation analysis on GPU systems using NVIDIA's CUDA. J. Real-time Image Process. 2011, 6(4):275-280.
3. Eklund A., Andersson M., Knutsson H. fMRI analysis on the GPU-possibilities and challenges. Comput. Methods Programs Biomed. 2012, 105(2):145-161.
4. da Silva A.R.F. cudaBayesreg: parallel implementation of a Bayesian multilevel model for fMRI data analysis. J. Stat. Softw. 2011, 44(i04).
5. Scheinost D., Hampson M., Qiu M., et al. A graphics processing unit accelerated motion correction algorithm and modular system for real-time fMRI. Neuroinformatics 2013, 1-10.
6. Jiménez J., Ruiz de Miras J. Fast box-counting algorithm on GPU. Comput. Methods Programs Biomed. 2012, 108(3):1229-1242.
7. Wei Q., Patkar S., Pai D.K. Fast ray-tracing of human eye optics on Graphics Processing Units. Comput. Methods Programs Biomed. 2014, 114(3):302-314.
8. Nickolls J., Dally W.J. The GPU computing era. Micro, IEEE 2010, 30(2):56-69.
9. Comon P. Independent component analysis: a new concept?. Signal Process. 1994, 36(3):287-314.
10. Hyvärinen A., Oja E. Independent component analysis: algorithms and applications. Neural Netw. 2000, 13(4):411-430.
11. Bell A.J., Sejnowski T.J. An information-maximization approach to blind separation and blind deconvolution. Neural Comput. 1995, 7(6):1129-1159.
12. Amari S., Cichocki A., Yang H.H. A new learning algorithm for blind signal separation. Adv. Neural Inf. Process. Syst. 1996, 757-763.
13. Cardoso J.F., Laheld B.H. Equivariant adaptive source separation. IEEE Trans. Signal Process. 1996, 44(12):3017-3030.
14. Calhoun V.D., Adali T., Pearlson G.D., et al. A method for making group inferences from functional MRI data using independent component analysis. Hum. Brain Mapp. 2001, 14(3):140-151.
15. Schöpf V., Kasess C.H., Lanzenberger R., et al. Fully exploratory network ICA (FENICA) on resting-state fMRI data. J. Neurosci. Methods 2010, 192(2):207-213.
16. Wang N., Zeng W., Chen L. A fast-FENICA method on resting state fMRI data. J. Neurosci. Methods 2012, 209(1):1-12.
17. Calhoun V.D., Liu J., Adali T. A review of group ICA for fMRI data and ICA for joint inference of imaging, genetic, and ERP data. NeuroImage 2009, 45(1):S163-S172.
18. MATLAB®. The Math Works Inc. http://www.mathworks.cn/products/matlab/.
19. Gustafson J.L. Reevaluating Amdahl's law. Commun. ACM 1988, 31(5):532-533.
20. Humphrey J.R., Price D.K., Spagnoli K.E., et al. CULA: hybrid GPU accelerated linear algebra routines. Int. Soc. Opt. Photonics 2010, 770502.
21. SIAM LAPACK Users' Guide 1999.
22. CUDA C Programming Guide 2012, July, NVIDIA Corporation.
23. Raimondo F., Kamienkowski J.E., Sigman M., et al. CUDAICA: GPU optimization of infomax-ICA EEG analysis. Comput. Intell. Neurosci. 2012, 2.
24. Binary Compiled Version of runica() 2013, http://sccn.ucsd.edu/eeglab/binica/.
25. Tesla C2075 GPU - Nvidia. http://www.nvidia.cn/object/workstation-solutions-tesla-cn.html.
26. Whitehead N., Fit-Florea A. Precision & Performance: Floating Point and IEEE 754 Compliance for NVIDIA GPUs. Tech. rep. 2012, NVIDIA, (accessed 28.04.12). https://developer.nvidia.com/sites/default/files/akamai/cuda/files/NVIDIA-CUDA-Floating-Point.pdf.