Temporal Dynamic Model for Resting State fMRI Data: A Neural Ordinary Differential Equation approach
This work addresses brain image prediction for neuroscience applications, but it is incremental as it applies existing Neural ODE methods to fMRI data.
The paper tackled predicting future brain images from resting state fMRI sequences using a Neural ODE-based model, achieving an average spatial correlation of 0.5 for trajectory prediction and enabling trait prediction.
The objective of this paper is to provide a temporal dynamic model for resting state functional Magnetic Resonance Imaging (fMRI) trajectory to predict future brain images based on the given sequence. To this end, we came up with the model that takes advantage of representation learning and Neural Ordinary Differential Equation (Neural ODE) to compress the fMRI image data into latent representation and learn to predict the trajectory following differential equation. Latent space was analyzed by Gaussian Mixture Model. The learned fMRI trajectory embedding can be used to explain the variance of the trajectory and predict human traits for each subject. This method achieves average 0.5 spatial correlation for the whole predicted trajectory, and provide trained ODE parameter for further analysis.