Latent source mining in FMRI via restricted Boltzmann machine
- 18 February 2018
- journal article
- research article
- Published by Wiley in Human Brain Mapping
- Vol. 39 (6) , 2368-2380
Abstract
Blind source separation (BSS) is commonly used in functional magnetic resonance imaging (fMRI) data analysis. Recently, BSS models based on restricted Boltzmann machine (RBM), one of the building blocks of deep learning models, have been shown to improve brain network identification compared to conventional single matrix factorization models such as independent component analysis (ICA). These models, however, trained RBM on fMRI volumes, and are hence challenged by model complexity and limited training set. In this article, we propose to apply RBM to fMRI time courses instead of volumes for BSS. The proposed method not only interprets fMRI time courses explicitly to take advantages of deep learning models in latent feature learning but also substantially reduces model complexity and increases the scale of training set to improve training efficiency. Our experimental results based on Human Connectome Project (HCP) datasets demonstrated the superiority of the proposed method over ICA and the one that applied RBM to fMRI volumes in identifying task‐related components, resulted in more accurate and specific representations of task‐related activations. Moreover, our method separated out components representing intermixed effects between task events, which could reflect inherent interactions among functionally connected brain regions. Our study demonstrates the value of RBM in mining complex structures embedded in large‐scale fMRI data and its potential as a building block for deeper models in fMRI data analysis.Keywords
Funding Information
- National Natural Science Foundation of China (61473234, 61333017, 61522207)
- NSF (IIS‐1149260, NIH R01 DA033393, NIH R01 AG042599, NSF CBET‐1302089, NSF BCS‐1439051, NSF DBI‐1564736)
This publication has 57 references indexed in Scilit:
- Bounding the Bias of Contrastive Divergence LearningNeural Computation, 2011
- Toward discovery science of human brain functionProceedings of the National Academy of Sciences, 2010
- Correspondence of the brain's functional architecture during activation and restProceedings of the National Academy of Sciences, 2009
- Neurodegenerative Diseases Target Large-Scale Human Brain NetworksNeuron, 2009
- A unified framework for group independent component analysis for multi-subject fMRI dataNeuroImage, 2008
- Consistent resting-state networks across healthy subjectsProceedings of the National Academy of Sciences, 2006
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Tensorial extensions of independent component analysis for multisubject FMRI analysisNeuroImage, 2005
- Brain dynamics during natural viewing conditions—A new guide for mapping connectivity in vivoNeuroImage, 2005
- An Information-Maximization Approach to Blind Separation and Blind DeconvolutionNeural Computation, 1995