Mitigating analytical variability in fMRI results with style transfer

TL;DR

This paper introduces a novel style transfer approach using GANs and Diffusion Models to enhance the reproducibility of fMRI results across different pipelines, aiding data augmentation in neuroimaging.

Contribution

It proposes a new method to convert fMRI statistic maps across pipelines by treating pipelines as style components, utilizing advanced generative models for improved reproducibility.

Findings

Style transfer effectively standardizes fMRI maps across pipelines.

Generative models improve data augmentation for neuroimaging studies.

Proposed methods outperform traditional approaches in transfer quality.

Abstract

We propose a novel approach to improve the reproducibility of neuroimaging results by converting statistic maps across different functional MRI pipelines. We make the assumption that pipelines used to compute fMRI statistic maps can be considered as a style component and we propose to use different generative models, among which, Generative Adversarial Networks (GAN) and Diffusion Models (DM) to convert statistic maps across different pipelines. We explore the performance of multiple GAN frameworks, and design a new DM framework for unsupervised multi-domain styletransfer. We constrain the generation of 3D fMRI statistic maps using the latent space of an auxiliary classifier that distinguishes statistic maps from different pipelines and extend traditional sampling techniques used in DM to improve the transition performance. Our experiments demonstrate that our proposed methods aresuccessful: pipelines can indeed be transferred as a style component, providing animportant source of data augmentation for future medical studies.