发表机构
Leiden University Medical Center; Radboud University Medical Center; King’s College London; University of Illinois（莱顿大学医学中心; 拉德堡德大学医学中心; 伦敦国王学院; 伊利诺伊大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对MRIxFields2026挑战赛任务3，采用条件流匹配方法，构建630万参数的单一模型，实现跨场MRI转换，在挑战赛指标上优于回归和扩散基线。
AI 中文摘要
同一受试者的磁共振图像在不同场强下会呈现显著差异，这使得不同站点间的数据比较与汇集变得复杂。我们针对MRIxFields2026挑战赛的跨场脑部MRI转换任务，特别是其任务3：构建一个单一模型，可在五个场强的任意有向对之间进行转换，且覆盖三种对比度。我们将该问题表述为条件流匹配路径：由于源体积与目标体积已完成空间配准，我们学习一个速度场，将源切片直接转换为目标切片，而非从噪声开始。为仅从三个配对受试者中学习该映射，该统一模型分三个阶段训练：退化桥预训练，从大量未配对的回顾性队列中提炼出恢复先验；在配对队列上对所有有向对进行跨场微调；以及对抗性精调以锐化输出。推理时，我们将学习到的速度与二阶Heun求解器结合，仅需少量步骤即可完成。未使用任何配对数据学习到的恢复先验已达到0.837的平均SSIM，后续每个训练阶段均在此基础上有所提升。一个630万参数的单一模型因此覆盖了全部60个场强-对比度组合，每个切片的推理仅需5个求解器步骤。在挑战赛评估集上，该模型在三种对比度上的平均SSIM达到0.909，在全部三个挑战赛指标上均优于基于相同网络构建的回归和扩散基线。
英文摘要
Magnetic resonance images of the same subject look markedly different across field strengths, which complicates the comparison and pooling of data across sites. We address cross-field brain-MRI translation 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 conditional 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 restoration prior from the abundant unpaired retrospective cohort, a cross-field finetuning over all directed pairs on the paired cohort, and an adversarial 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.
Comments10 pages, 2 figures
