Fader Networks for domain adaptation on fMRI: ABIDE-II study

TL;DR

This paper introduces a novel domain adaptation method using Fader Networks with 3D autoencoders to improve brain pathology classification across different fMRI scanning sites, outperforming existing methods on ABIDE data.

Contribution

First application of domain adaptation with Fader Networks on raw neuroimaging data for improved cross-site classification.

Findings

Outperforms existing approaches on ABIDE data

Achieves better transferability between scanning sites

Demonstrates effectiveness of domain irrelevant latent space

Abstract

ABIDE is the largest open-source autism spectrum disorder database with both fMRI data and full phenotype description. These data were extensively studied based on functional connectivity analysis as well as with deep learning on raw data, with top models accuracy close to 75\% for separate scanning sites. Yet there is still a problem of models transferability between different scanning sites within ABIDE. In the current paper, we for the first time perform domain adaptation for brain pathology classification problem on raw neuroimaging data. We use 3D convolutional autoencoders to build the domain irrelevant latent space image representation and demonstrate this method to outperform existing approaches on ABIDE data.