Abstract
Magneticresonanceimagesofthesamesubjectlookmarkedly
different across field strengths, which complicates the comparison and
pooling of data across sites. We address cross-field brain-MRI transla-
tion for the MRIxFields2026 challenge, and in particular its Task 3: a
single model that translates between any directed pair of the five field
strengths and across three contrasts. We phrase the problem as a con-
ditional flow matching path: because the source and target volumes are
spatially registered, we learn a velocity field that carries the source slice
directly to the target slice, rather than starting from noise. To learn this
mapping from only three paired subjects, the unified model is trained
in three stages: a degradation-bridge pretraining that distills a restora-
tion prior from the abundant unpaired retrospective cohort, a cross-field
finetuning over all directed pairs on the paired cohort, and an adversar-
ial refinement that sharpens the output. At inference, we integrate the
learned velocity with a second-order Heun solver in a handful of steps.
A restoration prior learned without any paired data already reaches a
mean SSIM of 0.837, and each subsequent training stage improves on
it. A single 6.3M-parameter model thereby covers all 60 field-pair and
contrast combinations, with inference in five solver steps per slice. On
the challenge evaluation set the model reaches a mean SSIM of 0.909,
averaged over the three contrasts, outperforming regression and diffusion
baselines built on the identical network on all three challenge metrics.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/MRIxFields2026_012.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=CiZZ2TPgBV
BibTex
@InProceedings{ImrBar_Conditional_MICCAISAT2026,
author = { Imre, Baris AND Salehi, Aram AND Baljer, Levente AND Webb, Andrew AND Staring, Marius AND Ilicak, Efe},
title = { { Conditional Flow Matching for Cross-Field MRI Harmonisation } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17274},
month = {pending},
page = {pending}
}