Denoising Diffusion Probabilistic Models for Magnetic Resonance Fingerprinting

TL;DR

This paper introduces a novel conditional diffusion probabilistic model for Magnetic Resonance Fingerprinting (MRF) reconstruction, demonstrating superior performance over existing methods in brain scan data.

Contribution

It is the first to apply diffusion models to MRF reconstruction, enhancing accuracy and efficiency in highly undersampled MRI scans.

Findings

Outperforms deep learning and compressed sensing methods in MRF reconstruction

Effective in highly accelerated, undersampled MRI acquisitions

Provides strategies to improve computational efficiency

Abstract

Magnetic Resonance Fingerprinting (MRF) is a time-efficient approach to quantitative MRI, enabling the mapping of multiple tissue properties from a single, accelerated scan. However, achieving accurate reconstructions remains challenging, particularly in highly accelerated and undersampled acquisitions, which are crucial for reducing scan times. While deep learning techniques have advanced image reconstruction, the recent introduction of diffusion models offers new possibilities for imaging tasks, though their application in the medical field is still emerging. Notably, diffusion models have not yet been explored for the MRF problem. In this work, we propose for the first time a conditional diffusion probabilistic model for MRF image reconstruction. Qualitative and quantitative comparisons on in-vivo brain scan data demonstrate that the proposed approach can outperform established deep learning and compressed sensing algorithms for MRF reconstruction. Extensive ablation studies also explore strategies to improve computational efficiency of our approach.