MPFlow: Multi-modal Posterior-Guided Flow Matching for Zero-Shot MRI Reconstruction
This addresses the issue of unreliable reconstructions in clinical MRI workflows by enabling more efficient and anatomically faithful zero-shot methods, though it is incremental as it builds on existing generative priors.
The paper tackled the problem of hallucinations in zero-shot MRI reconstruction under severe ill-posedness by proposing MPFlow, a multi-modal framework that leverages auxiliary MRI modalities at inference time without retraining, resulting in matching image quality with 20% fewer sampling steps and reducing tumor hallucinations by over 15% in segmentation dice score.
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.