Deep Image Priors for Magnetic Resonance Fingerprinting with pretrained Bloch-consistent denoising autoencoders

TL;DR

This paper introduces a novel method combining deep image priors with a Bloch-consistent autoencoder to improve Magnetic Resonance Fingerprinting, achieving faster and more accurate results without needing ground truth data.

Contribution

The work presents a new approach that integrates deep image priors with a pretrained Bloch-consistent autoencoder for improved MRF reconstruction without ground truth.

Findings

Faster reconstruction compared to existing methods

Achieves equivalent or better accuracy in MRF mapping

Operates without ground truth data

Abstract

The estimation of multi-parametric quantitative maps from Magnetic Resonance Fingerprinting (MRF) compressed sampled acquisitions, albeit successful, remains a challenge due to the high underspampling rate and artifacts naturally occuring during image reconstruction. Whilst state-of-the-art DL methods can successfully address the task, to fully exploit their capabilities they often require training on a paired dataset, in an area where ground truth is seldom available. In this work, we propose a method that combines a deep image prior (DIP) module that, without ground truth and in conjunction with a Bloch consistency enforcing autoencoder, can tackle the problem, resulting in a method faster and of equivalent or better accuracy than DIP-MRF.