Transfer Learning of fMRI Dynamics

TL;DR

This paper introduces a self-supervised transfer learning approach that pre-trains on healthy fMRI data and effectively applies to small datasets for early diagnosis of disorders like schizophrenia, improving classification and learning speed.

Contribution

It presents a novel transfer learning method that leverages healthy control fMRI dynamics to enhance disorder classification in small datasets, addressing data scarcity issues.

Findings

Enables disorder classification from small fMRI datasets.

Speeds up learning process in disorder detection.

Demonstrates effective transfer across datasets and diagnostic categories.

Abstract

As a mental disorder progresses, it may affect brain structure, but brain function expressed in brain dynamics is affected much earlier. Capturing the moment when brain dynamics express the disorder is crucial for early diagnosis. The traditional approach to this problem via training classifiers either proceeds from handcrafted features or requires large datasets to combat the $m>>n$ problem when a high dimensional fMRI volume only has a single label that carries learning signal. Large datasets may not be available for a study of each disorder, or rare disorder types or sub-populations may not warrant for them. In this paper, we demonstrate a self-supervised pre-training method that enables us to pre-train directly on fMRI dynamics of healthy control subjects and transfer the learning to much smaller datasets of schizophrenia. Not only we enable classification of disorder directly based on fMRI dynamics in small data but also significantly speed up the learning when possible. This is encouraging evidence of informative transfer learning across datasets and diagnostic categories.