Likelihood-Separable Diffusion Inference for Multi-Image MRI Super-Resolution

TL;DR

This paper introduces a diffusion-based method for multi-image MRI super-resolution that leverages likelihood separability to improve reconstruction quality without complex joint modeling, achieving state-of-the-art results.

Contribution

It generalizes diffusion-based inverse problem solvers for multi-image MRI super-resolution using likelihood separability, enabling efficient reconstruction of high-quality isotropic images from low-resolution data.

Findings

Achieves state-of-the-art super-resolution in anisotropic MRI volumes.

Enables reconstruction of near-isotropic anatomy from routine 2D acquisitions.

Demonstrates substantial improvements over single-image super-resolution methods.

Abstract

Diffusion models are the current state-of-the-art for solving inverse problems in imaging. Their impressive generative capability allows them to approximate sampling from a prior distribution, which alongside a known likelihood function permits posterior sampling without retraining the model. While recent methods have made strides in advancing the accuracy of posterior sampling, the majority focuses on single-image inverse problems. However, for modalities such as magnetic resonance imaging (MRI), it is common to acquire multiple complementary measurements, each low-resolution along a different axis. In this work, we generalize common diffusion-based inverse single-image problem solvers for multi-image super-resolution (MISR) MRI. We show that the DPS likelihood correction allows an exactly-separable gradient decomposition across independently acquired measurements, enabling MISR without constructing a joint operator, modifying the diffusion model, or increasing network function evaluations. We derive MISR versions of DPS, DMAP, DPPS, and diffusion-based PnP/ADMM, and demonstrate substantial gains over SISR across $4\times/8\times/16\times$ anisotropic degradations. Our results achieve state-of-the-art super-resolution of anisotropic MRI volumes and, critically, enable reconstruction of near-isotropic anatomy from routine 2D multi-slice acquisitions, which are otherwise highly degraded in orthogonal views.