用多模态信息提升零样本MRI重建的准确性与可靠性
MPFlow: Multi-modal Posterior-Guided Flow Matching for Zero-Shot MRI Reconstruction
- 引入跨模态引导的流匹配框架，利用辅助影像提升重建质量
- 仅用20%采样步数达到扩散模型图像质量，肿瘤伪影减少15%以上
- 适合临床中已有高质量结构扫描的MRI重建任务
零样本MRI重建依赖生成先验，但单一模态无条件先验在严重病态情况下易产生幻觉。临床中常有高质量结构扫描等互补模态数据可用，现有方法缺乏利用这些信息的机制。我们提出MPFlow，一种基于修正流的零样本多模态重建框架，在推理时无需重训练生成先验即可利用辅助MRI模态提升解剖保真度。通过自监督预训练策略PAMRI（Patch-level Multi-modal MR Image Pretraining）学习跨模态共享表征，采样过程联合数据一致性和跨模态特征对齐。在HCP和BraTS数据集上的实验表明，MPFlow仅使用20%采样步数即可达到扩散基线的图像质量，且肿瘤幻觉减少超过15%（分割Dice分数），证明跨模态引导可实现更可靠、高效的零样本MRI重建。
原文摘要 · Abstract (English)
Zero-shot MRI reconstruction relies on generative priors, but single-modality unconditional priors produce hallucinations under severe ill-posedness. In many clinical workflows, complementary MRI acquisitions (e.g. high-quality structural scans) are routinely available, yet existing reconstruction methods lack mechanisms to leverage this additional information. We propose MPFlow, a zero-shot multi-modal reconstruction framework built on rectified flow that incorporates auxiliary MRI modalities at inference time without retraining the generative prior to improve anatomical fidelity. Cross-modal guidance is enabled by our proposed self-supervised pretraining strategy, Patch-level Multi-modal MR Image Pretraining (PAMRI), which learns shared representations across modalities. Sampling is jointly guided by data consistency and cross-modal feature alignment using pre-trained PAMRI, systematically suppressing intrinsic and extrinsic hallucinations. Extensive experiments on HCP and BraTS show that MPFlow matches diffusion baselines on image quality using only 20% of sampling steps while reducing tumor hallucinations by more than 15% (segmentation dice score). This demonstrates that cross-modal guidance enables more reliable and efficient zero-shot MRI reconstruction.
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。