Mitigating analytical variability in fMRI results with style transfer
This work addresses variability in neuroimaging results for medical research, offering a data augmentation method, though it appears incremental as it applies existing style transfer techniques to a new domain.
The authors tackled the problem of reproducibility in fMRI analysis by converting statistic maps across different pipelines using style transfer, demonstrating that pipelines can be treated as a style component and successfully transferred with generative models like GANs and diffusion models.
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.