U$^2$MRPD: Unsupervised undersampled MRI reconstruction by prompting a large latent diffusion model

arXiv:2402.10609v1 Announce Type: cross
Abstract: 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 …

abstract arxiv cs.cv cs.lg diffusion diffusion model eess.iv framework hypothesis images knowledge medical mri natural novel prompting test type unsupervised visual