用无增强MRI生成真实脑部增强MRI，提升诊断效率与安全性。
Synthesizing Accurate and Realistic T1-weighted Contrast-Enhanced MR Images using Posterior-Mean Rectified Flow
- 分两阶段：先用3D U-Net预测后验均值，再用时序条件流优化纹理。
- 生成图像FID达12.46，比初始估计降低68.7%，结构误差仅高27%。
- 适合神经肿瘤影像生成，临床部署中兼顾真实感与解剖精度。
对比增强（CE）T1加权磁共振成像在神经肿瘤诊断中至关重要，但需使用含钆造影剂，增加成本与扫描时间，带来环境和患者安全风险。本文提出一种两阶段后验均值修正流（PMRF）框架，从非增强输入合成三维脑部增强MRI。首先，基于块的3D U-Net预测体素级后验均值（最小化均方误差）；随后，通过时序条件3D修正流对初估结果进行精细化，引入真实纹理同时保持结构保真度。模型在多机构配对的前后增强T1w数据集（BraTS 2023–2025）上训练。在360个多样化测试样本上，最优生成结果实现轴向FID为12.46、KID为0.007，相比后验均值降低约68.7%的FID，体积均方误差仅为0.057（较后验均值高出约27%）。定性评估表明，该方法能真实还原病灶边界与血管细节，有效平衡感知真实度与失真度，具备临床应用潜力。
原文摘要 · Abstract (English)
Contrast-enhanced (CE) T1-weighted MRI is central to neuro-oncologic diagnosis but requires gadolinium-based agents, which add cost and scan time, raise environmental concerns, and may pose risks to patients. In this work, we propose a two-stage Posterior-Mean Rectified Flow (PMRF) pipeline for synthesizing volumetric CE brain MRI from non-contrast inputs. First, a patch-based 3D U-Net predicts the voxel-wise posterior mean (minimizing MSE). Then, this initial estimate is refined by a time-conditioned 3D rectified flow to incorporate realistic textures without compromising structural fidelity. We train this model on a multi-institutional collection of paired pre- and post-contrast T1w volumes (BraTS 2023-2025). On a held-out test set of 360 diverse volumes, our best refined outputs achieve an axial FID of $12.46$ and KID of $0.007$ ($\sim 68.7\%$ lower FID than the posterior mean) while maintaining low volumetric MSE of $0.057$ ($\sim 27\%$ higher than the posterior mean). Qualitative comparisons confirm that our method restores lesion margins and vascular details realistically, effectively navigating the perception-distortion trade-off for clinical deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。