Mitigating analytical variability in fMRI with style transfer

Elodie Germani, Camille Maumet, Elisa Fromont
Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, PMLR 301:475-493, 2026.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v301-germani26a, title = {Mitigating analytical variability in fMRI with style transfer}, author = {Germani, Elodie and Maumet, Camille and Fromont, Elisa}, booktitle = {Proceedings of The 8th International Conference on Medical Imaging with Deep Learning}, pages = {475--493}, year = {2026}, editor = {Tasdizen, Tolga and Elhabian, Shireen and Summers, Ronald and Chen, Chen and Koch, Lisa and Zhuang, Yan}, volume = {301}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v301/main/assets/germani26a/germani26a.pdf}, url = {https://proceedings.mlr.press/v301/germani26a.html}, 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.} }
Endnote
%0 Conference Paper %T Mitigating analytical variability in fMRI with style transfer %A Elodie Germani %A Camille Maumet %A Elisa Fromont %B Proceedings of The 8th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Tolga Tasdizen %E Shireen Elhabian %E Ronald Summers %E Chen Chen %E Lisa Koch %E Yan Zhuang %F pmlr-v301-germani26a %I PMLR %P 475--493 %U https://proceedings.mlr.press/v301/germani26a.html %V 301 %X 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.
APA
Germani, E., Maumet, C. & Fromont, E.. (2026). Mitigating analytical variability in fMRI with style transfer. Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 301:475-493 Available from https://proceedings.mlr.press/v301/germani26a.html.

Related Material