TY - JOUR
T1 - Automatic Recognition of fMRI-Derived Functional Networks Using 3-D Convolutional Neural Networks
AU - Zhao, Yu
AU - Dong, Qinglin
AU - Zhang, Shu
AU - Zhang, Wei
AU - Chen, Hanbo
AU - Jiang, Xi
AU - Guo, Lei
AU - Hu, Xintao
AU - Han, Junwei
AU - Liu, Tianming
N1 - Funding Information:
Manuscript received March 4, 2017; revised April 8, 2017 and May 7, 2017; accepted May 17, 2017. Date of publication June 15, 2017; date of current version August 20, 2018. This paper has supplementary downloadable material available at http://ieeexplore.ieee.org. This work was supported in part by the National Institute of Health (R01 DA-033393, R01 AG-042599) and in part by the National Science Foundation (IIS-1149260, CBET-1302089, BCS-1439051, and DBI-1564736). (Corresponding author: Tianming Liu.) Y. Zhao, Q. Dong, S. Zhang, W. Zhang, H. Chen, and X. Jiang are with the Cortical Architecture Imaging and Discovery Lab, Department of Computer Science and Bioimaging Research Center, University of Georgia.
Publisher Copyright:
© 1964-2012 IEEE.
PY - 2018/9
Y1 - 2018/9
N2 - Current functional magnetic resonance imaging (fMRI) data modeling techniques, such as independent component analysis and sparse coding methods, can effectively reconstruct dozens or hundreds of concurrent interacting functional brain networks simultaneously from the whole brain fMRI signals. However, such reconstructed networks have no correspondences across different subjects. Thus, automatic, effective, and accurate classification and recognition of these large numbers of fMRI-derived functional brain networks are very important for subsequent steps of functional brain analysis in cognitive and clinical neuroscience applications. However, this task is still a challenging and open problem due to the tremendous variability of various types of functional brain networks and the presence of various sources of noises. In recognition of the fact that convolutional neural networks (CNN) has superior capability of representing spatial patterns with huge variability and dealing with large noises, in this paper, we design, apply, and evaluate a deep 3-D CNN framework for automatic, effective, and accurate classification and recognition of large number of functional brain networks reconstructed by sparse representation of whole-brain fMRI signals. Our extensive experimental results based on the Human Connectome Project fMRI data showed that the proposed deep 3-D CNN can effectively and robustly perform functional networks classification and recognition tasks, while maintaining a high tolerance for mistakenly labeled training instances. This study provides a new deep learning approach for modeling functional connectomes based on fMRI data.
AB - Current functional magnetic resonance imaging (fMRI) data modeling techniques, such as independent component analysis and sparse coding methods, can effectively reconstruct dozens or hundreds of concurrent interacting functional brain networks simultaneously from the whole brain fMRI signals. However, such reconstructed networks have no correspondences across different subjects. Thus, automatic, effective, and accurate classification and recognition of these large numbers of fMRI-derived functional brain networks are very important for subsequent steps of functional brain analysis in cognitive and clinical neuroscience applications. However, this task is still a challenging and open problem due to the tremendous variability of various types of functional brain networks and the presence of various sources of noises. In recognition of the fact that convolutional neural networks (CNN) has superior capability of representing spatial patterns with huge variability and dealing with large noises, in this paper, we design, apply, and evaluate a deep 3-D CNN framework for automatic, effective, and accurate classification and recognition of large number of functional brain networks reconstructed by sparse representation of whole-brain fMRI signals. Our extensive experimental results based on the Human Connectome Project fMRI data showed that the proposed deep 3-D CNN can effectively and robustly perform functional networks classification and recognition tasks, while maintaining a high tolerance for mistakenly labeled training instances. This study provides a new deep learning approach for modeling functional connectomes based on fMRI data.
KW - convolutional neural networks
KW - deep learning
KW - fMRI
KW - functional brain networks
KW - recognition
UR - http://www.scopus.com/inward/record.url?scp=85023159605&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85023159605&partnerID=8YFLogxK
U2 - 10.1109/TBME.2017.2715281
DO - 10.1109/TBME.2017.2715281
M3 - Article
C2 - 28641239
AN - SCOPUS:85023159605
SN - 0018-9294
VL - 65
SP - 1975
EP - 1984
JO - IEEE Transactions on Biomedical Engineering
JF - IEEE Transactions on Biomedical Engineering
IS - 9
M1 - 7949139
ER -