INFusion: Diffusion Regularized Implicit Neural Representations for 2D and 3D accelerated MRI reconstruction

TL;DR

This paper introduces INFusion, a novel method that enhances implicit neural representations for MRI reconstruction by integrating pre-trained diffusion models, enabling improved 2D and 3D accelerated MRI imaging, especially on large-scale datasets.

Contribution

The work presents a new diffusion regularization technique for INRs, including a hybrid 3D approach, to improve MRI reconstruction quality and scalability beyond previous methods.

Findings

Enhanced INR training with diffusion regularization in 2D.

Feasibility of INR training with diffusion regularization on large 3D datasets.

Improved MRI reconstruction quality demonstrated in experiments.

Abstract

Implicit Neural Representations (INRs) are a learning-based approach to accelerate Magnetic Resonance Imaging (MRI) acquisitions, particularly in scan-specific settings when only data from the under-sampled scan itself are available. Previous work demonstrates that INRs improve rapid MRI through inherent regularization imposed by neural network architectures. Typically parameterized by fully-connected neural networks, INRs support continuous image representations by taking a physical coordinate location as input and outputting the intensity at that coordinate. Previous work has applied unlearned regularization priors during INR training and have been limited to 2D or low-resolution 3D acquisitions. Meanwhile, diffusion based generative models have received recent attention as they learn powerful image priors decoupled from the measurement model. This work proposes INFusion, a technique that regularizes the optimization of INRs from under-sampled MR measurements with pre-trained diffusion models for improved image reconstruction. In addition, we propose a hybrid 3D approach with our diffusion regularization that enables INR application on large-scale 3D MR datasets. 2D experiments demonstrate improved INR training with our proposed diffusion regularization, and 3D experiments demonstrate feasibility of INR training with diffusion regularization on 3D matrix sizes of 256 by 256 by 80.