Jointly Discriminative and Generative Recurrent Neural Networks for Learning from fMRI

TL;DR

This paper introduces a novel RNN model that combines discriminative and generative learning to improve classification of fMRI data and enhance interpretability of brain functional communities.

Contribution

The paper proposes a multitask LSTM-based RNN that jointly learns to classify and generate fMRI data, improving accuracy and interpretability over existing methods.

Findings

Enhanced classification accuracy on autism vs. control datasets.

Generated functional communities align with known brain structures.

Model provides more interpretable insights into brain activity.

Abstract

Recurrent neural networks (RNNs) were designed for dealing with time-series data and have recently been used for creating predictive models from functional magnetic resonance imaging (fMRI) data. However, gathering large fMRI datasets for learning is a difficult task. Furthermore, network interpretability is unclear. To address these issues, we utilize multitask learning and design a novel RNN-based model that learns to discriminate between classes while simultaneously learning to generate the fMRI time-series data. Employing the long short-term memory (LSTM) structure, we develop a discriminative model based on the hidden state and a generative model based on the cell state. The addition of the generative model constrains the network to learn functional communities represented by the LSTM nodes that are both consistent with the data generation as well as useful for the classification task. We apply our approach to the classification of subjects with autism vs. healthy controls using several datasets from the Autism Brain Imaging Data Exchange. Experiments show that our jointly discriminative and generative model improves classification learning while also producing robust and meaningful functional communities for better model understanding.