Implicit visual knowledge in a large latent diffusion model (LLDM) pre-trained on natural images is rich and hypothetically universal to natural and medical images. To test this hypothesis, we introduce a novel framework for Unsupervised Undersampled MRI Reconstruction by Prompting a pre-trained large latent Diffusion model ( U$^2$MRPD). Existing data-driven, supervised undersampled MRI reconstruction networks are typically of limited generalizability and adaptability toward diverse data acquisition scenarios; yet U$^2$MRPD supports image-specific MRI reconstruction by prompting an LLDM with an MRSampler tailored for complex-valued MRI images. With any single-source or diverse-source MRI dataset, U$^2$MRPD's performance is further boosted by an MRAdapter while keeping the generative image priors intact. Experiments on multiple datasets show that U$^2$MRPD achieves comparable or better performance than supervised and MRI diffusion methods on in-domain datasets while demonstrating the best generalizability on out-of-domain datasets. To the best of our knowledge, U$^2$MRPD is the {\bf first} unsupervised method that demonstrates the universal prowess of a LLDM, %trained on magnitude-only natural images in medical imaging, attaining the best adaptability for both MRI database-free and database-available scenarios and generalizability towards out-of-domain data.

翻译：大型潜在扩散模型（LLDM）在自然图像上预训练所蕴含的隐式视觉知识丰富且假设对自然图像与医学图像具有普适性。为验证该假设，我们提出一种新颖框架——通过提示预训练大型潜在扩散模型实现无监督欠采样MRI重建（U$^2$MRPD）。现有数据驱动的有监督欠采样MRI重建网络通常对多样化数据采集场景的泛化性与适应性有限；而U$^2$MRPD通过为复数MRI图像定制的MRSampler提示LLDM，支持图像特异性MRI重建。对于单源或多源MRI数据集，U$^2$MRPD的性能可通过MRAdapter进一步提升，同时保持生成图像先验不变。多数据集实验表明，U$^2$MRPD在域内数据集上达到与有监督方法及MRI扩散方法相当或更优的性能，并在域外数据集上展现出最佳泛化能力。据我们所知，U$^2$MRPD是**首个**证明LLDM（基于幅度自然图像训练）在医学成像中具有普适能力的无监督方法，实现了对无MRI数据库与有数据库场景的最佳适应性及对域外数据的泛化能力。