Format

Send to

Choose Destination
Neuroimage. 2014 Aug 1;96:245-60. doi: 10.1016/j.neuroimage.2014.03.048. Epub 2014 Mar 28.

Restricted Boltzmann machines for neuroimaging: an application in identifying intrinsic networks.

Author information

1
Mind Research Network, Albuquerque, NM 87106, USA; Department of Computer Science, University of New Mexico, Albuquerque, NM 87131, USA.
2
Mind Research Network, Albuquerque, NM 87106, USA; Department of Computer Science, University of New Mexico, Albuquerque, NM 87131, USA. Electronic address: vcalhoun@mrn.org.
3
Department of Computer Science, University of Toronto, Toronto, ON M5S 2J7, Canada.
4
Mind Research Network, Albuquerque, NM 87106, USA; Department of Biological and Medical Psychology, University of Bergen 5009, Norway.
5
University of Maryland Baltimore County, Baltimore, MD 21250, USA.
6
Mind Research Network, Albuquerque, NM 87106, USA.

Abstract

Matrix factorization models are the current dominant approach for resolving meaningful data-driven features in neuroimaging data. Among them, independent component analysis (ICA) is arguably the most widely used for identifying functional networks, and its success has led to a number of versatile extensions to group and multimodal data. However there are indications that ICA may have reached a limit in flexibility and representational capacity, as the majority of such extensions are case-driven, custom-made solutions that are still contained within the class of mixture models. In this work, we seek out a principled and naturally extensible approach and consider a probabilistic model known as a restricted Boltzmann machine (RBM). An RBM separates linear factors from functional brain imaging data by fitting a probability distribution model to the data. Importantly, the solution can be used as a building block for more complex (deep) models, making it naturally suitable for hierarchical and multimodal extensions that are not easily captured when using linear factorizations alone. We investigate the capability of RBMs to identify intrinsic networks and compare its performance to that of well-known linear mixture models, in particular ICA. Using synthetic and real task fMRI data, we show that RBMs can be used to identify networks and their temporal activations with accuracy that is equal or greater than that of factorization models. The demonstrated effectiveness of RBMs supports its use as a building block for deeper models, a significant prospect for future neuroimaging research.

KEYWORDS:

DBN; ICA; Intrinsic networks; RBM; fMRI

PMID:
24680869
PMCID:
PMC4348021
DOI:
10.1016/j.neuroimage.2014.03.048
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Elsevier Science Icon for PubMed Central
Loading ...
Support Center