Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

Overview of DYnamic NEtwork Modelling (DYNEMO).

DEEP LEARNING MODELS

We develop models using tools from deep learning, such as recurrent neural networks (RNNs). These models can overcome some of the limitations of Hidden Markov Models (HMMs), such as the short memory (the Markovian constraint) and mutual exclusivity of states.

A model we are developing is DYnamic NEtwork Modelling (DYNEMO). This model is inspired by a popular deep learning framework known as the variational autoencoder. Dynemo uses amortised inference to learn a hidden state description of neuroimaging data. Each state represents a large-scale brain network. The temporal dynamics of state switches are captured by an RNN [2].

Tools for performing this kind of analyses are available in the osl-dynamics Python toolbox.

References

  1. Pervaiz U, Vidaurre D, Gohil C, Smith S, Woolrich M. Multi-dynamic Modelling Reveals Strongly Time-varying Resting fMRI Correlations. Medical image analysis 2022. https://doi.org/10.1016/j.media.2022.102366
  2. Chetan GohilEvan RobertsRyan TimmsAlex SkatesCameron HigginsAndrew QuinnUsama PervaizJoost van AmersfoortPascal NotinYarin GalStanislaw AdaszewskiMark Woolrich. Mixtures of large-scale dynamic functional brain network modes. bioRxiv 2022.05.03.490453; doi: https://doi.org/10.1101/2022.05.03.490453