Deep learning for neuroimaging: A validation study

Sergey M. Plis, Devon R. Hjelm, Ruslan Slakhutdinov, Elena A. Allen, H. Jeremy Bockholt, Jeffrey D. Long, Hans Johnson, Jane Paulsen, Jessica Turner, Vince D. Calhoun

Research output: Contribution to journalArticlepeer-review

259 Scopus citations


Deep learning methods have recently made notable advances in the tasks of classification and representation learning. These tasks are important for brain imaging and neuroscience discovery, making the methods attractive for porting to a neuroimager's toolbox. Success of these methods is, in part, explained by the flexibility of deep learning models. However, this flexibility makes the process of porting to new areas a difficult parameter optimization problem. In this work we demonstrate our results (and feasible parameter ranges) in application of deep learning methods to structural and functional brain imaging data. These methods include deep belief networks and their building block the restricted Boltzmann machine. We also describe a novel constraint-based approach to visualizing high dimensional data. We use it to analyze the effect of parameter choices on data transformations. Our results show that deep learning methods are able to learn physiologically important representations and detect latent relations in neuroimaging data.

Original languageEnglish (US)
Article numberArticle 229
JournalFrontiers in Neuroscience
Issue number8 JUL
StatePublished - 2014


  • Classification
  • Intrinsic networks
  • MRI
  • Unsupervised learning
  • fMRI

ASJC Scopus subject areas

  • General Neuroscience


Dive into the research topics of 'Deep learning for neuroimaging: A validation study'. Together they form a unique fingerprint.

Cite this