Mitigating Analytical Variability in fMRI with Style Transfer

Abstract

We propose a novel approach to facilitate the re-use 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 harmonize statistic maps across different pipelines. We explore the performance of multiple GAN and DM frameworks for unsupervised multi-domain style transfer. We developed an auxiliary classifier that distinguishes statistic maps from different pipelines, allowing us to validate pipeline transfer, but also to extend traditional sampling techniques used in DM to improve the transition performance. Our experiments demonstrate that our proposed methods are successful: pipelines can indeed be transferred as a style component, providing an important source of data augmentation for future studies.