StoDIP: Efficient 3D MRF image reconstruction with deep image priors and stochastic iterations
This work addresses a domain-specific problem for medical imaging researchers and clinicians by enabling more efficient 3D MRF reconstruction without ground-truth data, though it is incremental as it builds on existing deep image prior methods.
The paper tackled the challenge of 3D Magnetic Resonance Fingerprinting (MRF) image reconstruction, which is computationally intensive and lacks ground-truth data, by introducing StoDIP, an algorithm that uses deep image priors and stochastic iterations to achieve faster convergence and superior performance over baselines on whole-brain scans.
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.