Self-Supervised Mental Disorder Classifiers via Time Reversal

TL;DR

This paper introduces a self-supervised approach that pre-trains models on the temporal direction of fMRI data to improve brain disorder classification, especially useful in data-scarce medical settings.

Contribution

It demonstrates that learning time direction in ICA-based fMRI data enhances model generalization and convergence in downstream brain disorder classification tasks.

Findings

Pre-training on time direction improves classification accuracy.

Learning causal relations aids in faster model convergence.

Models generalize well with limited data.

Abstract

Data scarcity is a notable problem, especially in the medical domain, due to patient data laws. Therefore, efficient Pre-Training techniques could help in combating this problem. In this paper, we demonstrate that a model trained on the time direction of functional neuro-imaging data could help in any downstream task, for example, classifying diseases from healthy controls in fMRI data. We train a Deep Neural Network on Independent components derived from fMRI data using the Independent component analysis (ICA) technique. It learns time direction in the ICA-based data. This pre-trained model is further trained to classify brain disorders in different datasets. Through various experiments, we have shown that learning time direction helps a model learn some causal relation in fMRI data that helps in faster convergence, and consequently, the model generalizes well in downstream classification tasks even with fewer data records.