Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/ISBI.2016.7493348 | 2016 IEEE 13TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI) |
Keywords | Field | DocType |
fMRI, blind source separation, deep neural network, restricted Boltzmann machine, ICA | Restricted Boltzmann machine,Human Connectome Project,Pattern recognition,Functional magnetic resonance imaging,Computer science,Speech recognition,Independent component analysis,Artificial intelligence,Artificial neural network,Blind signal separation | Conference |
ISSN | Citations | PageRank |
1945-7928 | 3 | 0.45 |
References | Authors | |
6 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Heng Huang | 1 | 3080 | 203.21 |
Xintao Hu | 2 | 118 | 13.53 |
Junwei Han | 3 | 3501 | 194.57 |
Jinglei Lv | 4 | 205 | 26.70 |
Nian Liu | 5 | 318 | 12.08 |
Lei Guo | 6 | 181 | 11.67 |
Tianming Liu | 7 | 1033 | 112.95 |