Mitigating analytical variability in fMRI results with style transfer - Inserm - Institut national de la santé et de la recherche médicale Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Mitigating analytical variability in fMRI results with style transfer

Résumé

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 style transfer. 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 are successful: pipelines can indeed be transferred as a style component, providing an important source of data augmentation for future medical studies.
Fichier principal
Vignette du fichier
elsarticle-template-num.pdf (1.01 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

inserm-04531405 , version 1 (03-04-2024)
inserm-04531405 , version 2 (13-09-2024)

Licence

Identifiants

  • HAL Id : inserm-04531405 , version 2

Citer

Elodie Germani, Camille Maumet, Elisa Fromont. Mitigating analytical variability in fMRI results with style transfer. 2024. ⟨inserm-04531405v2⟩
51 Consultations
55 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More