TY - GEN
T1 - Latent source mining in FMRI data via deep neural network
AU - Huang, Heng
AU - Hu, Xintao
AU - Han, Junwei
AU - Lv, Jinglei
AU - Liu, Nian
AU - Guo, Lei
AU - Liu, Tianming
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/6/15
Y1 - 2016/6/15
N2 - Independent component analysis (ICA) and its variants have been the dominant methods to the problem of blind source separation (BSS) for functional magnetic resonance imaging (fMRI) data. However, the functional interactions among spatially distributed brain regions and concurrent brain networks deteriorate the basic assumption in ICA-based BSS, that is, the spatial independence of the sources. In this paper, we proposed a novel method for BSS based on recently advanced deep neural network (DNN) algorithm, aiming to detect both internal and functional interaction-induced latent sources simultaneously. We used the motor task fMRI data in the Human Connectome Project (HCP) as a test-bed in the experiments. The results demonstrated the feasibility and effectiveness of the proposed method and its outperformance compared with ICA.
AB - Independent component analysis (ICA) and its variants have been the dominant methods to the problem of blind source separation (BSS) for functional magnetic resonance imaging (fMRI) data. However, the functional interactions among spatially distributed brain regions and concurrent brain networks deteriorate the basic assumption in ICA-based BSS, that is, the spatial independence of the sources. In this paper, we proposed a novel method for BSS based on recently advanced deep neural network (DNN) algorithm, aiming to detect both internal and functional interaction-induced latent sources simultaneously. We used the motor task fMRI data in the Human Connectome Project (HCP) as a test-bed in the experiments. The results demonstrated the feasibility and effectiveness of the proposed method and its outperformance compared with ICA.
KW - ICA
KW - blind source separation
KW - deep neural network
KW - fMRI
KW - restricted Boltzmann machine
UR - https://www.scopus.com/pages/publications/84978415201
U2 - 10.1109/ISBI.2016.7493348
DO - 10.1109/ISBI.2016.7493348
M3 - 会议稿件
AN - SCOPUS:84978415201
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 638
EP - 641
BT - 2016 IEEE International Symposium on Biomedical Imaging
PB - IEEE Computer Society
T2 - 13th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016
Y2 - 13 April 2016 through 16 April 2016
ER -