StoDIP: Efficient 3D MRF image reconstruction with deep image priors and stochastic iterations

TL;DR

StoDIP is a novel 3D MRF image reconstruction algorithm that leverages deep image priors and stochastic iterations to efficiently produce high-quality volumetric MRI maps without ground-truth data.

Contribution

It extends the Deep Image Prior method to 3D MRF imaging, introducing stochastic updates and efficient transformations for faster, high-quality reconstructions.

Findings

Outperforms baseline methods in quantitative metrics.

Produces qualitatively superior 3D MRI maps.

Faster convergence compared to traditional DIP.

Abstract

Magnetic Resonance Fingerprinting (MRF) is a time-efficient approach to quantitative MRI for multiparametric tissue mapping. The reconstruction of quantitative maps requires tailored algorithms for removing aliasing artefacts from the compressed sampled MRF acquisitions. Within approaches found in the literature, many focus solely on two-dimensional (2D) image reconstruction, neglecting the extension to volumetric (3D) scans despite their higher relevance and clinical value. A reason for this is that transitioning to 3D imaging without appropriate mitigations presents significant challenges, including increased computational cost and storage requirements, and the need for large amount of ground-truth (artefact-free) data for training. To address these issues, we introduce StoDIP, a new algorithm that extends the ground-truth-free Deep Image Prior (DIP) reconstruction to 3D MRF imaging. StoDIP employs memory-efficient stochastic updates across the multicoil MRF data, a carefully selected neural network architecture, as well as faster nonuniform FFT (NUFFT) transformations. This enables a faster convergence compared against a conventional DIP implementation without these features. Tested on a dataset of whole-brain scans from healthy volunteers, StoDIP demonstrated superior performance over the ground-truth-free reconstruction baselines, both quantitatively and qualitatively.