Investigating the Feasibility of Patch-based Inference for Generalized Diffusion Priors in Inverse Problems for Medical Images

TL;DR

This paper investigates the use of patch-based inference with diffusion priors for MRI image inverse problems, aiming to improve efficiency and adaptability over traditional whole-image methods.

Contribution

It demonstrates the feasibility of patch-based training and inference for diffusion priors in medical imaging, including necessary adaptations and performance analysis.

Findings

Patch-based methods reduce memory usage

Minor adaptations prevent artifacts in patch inference

Patch-based approaches are adaptable across tasks and datasets

Abstract

Plug-and-play approaches to solving inverse problems such as restoration and super-resolution have recently benefited from Diffusion-based generative priors for natural as well as medical images. However, solutions often use the standard albeit computationally intensive route of training and inferring with the whole image on the diffusion prior. While patch-based approaches to evaluating diffusion priors in plug-and-play methods have received some interest, they remain an open area of study. In this work, we explore the feasibility of the usage of patches for training and inference of a diffusion prior on MRI images. We explore the minor adaptation necessary for artifact avoidance, the performance and the efficiency of memory usage of patch-based methods as well as the adaptability of whole image training to patch-based evaluation - evaluating across multiple plug-and-play methods, tasks and datasets.