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

arXiv: https://arxiv.org/abs/2408.02367 · HTML: https://mlsanity.com/paper/2408.02367/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 5 Aug 2024.

## Builds on (most cited first, 10 of 10)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Plug-and-Play Image Restoration with Deep Denoiser Prior](https://mlsanity.com/paper/2008.13751/) (2020)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [Time-Dependent Deep Image Prior for Dynamic MRI](https://mlsanity.com/paper/1910.01684/) (2019)
- [MR fingerprinting Deep RecOnstruction NEtwork (DRONE)](https://mlsanity.com/paper/1710.05267/) (2017)
- [cuFINUFFT: a load-balanced GPU library for general-purpose nonuniform FFTs](https://mlsanity.com/paper/2102.08463/) (2021)
- [Compressive MR Fingerprinting reconstruction with Neural Proximal Gradient iterations](https://mlsanity.com/paper/2006.15271/) (2020)
- [Designing contrasts for rapid, simultaneous parameter quantification and flow visualization with quantitative transient-state imaging](https://mlsanity.com/paper/1901.07800/) (2019)
- [Magnetic Resonance Fingerprinting with compressed sensing and distance metric learning](https://mlsanity.com/paper/2209.08734/) (2022)

## Built on by (most cited first, 2 of 2)

- [Tada-DIP: Input-adaptive Deep Image Prior for One-shot 3D Image Reconstruction](https://mlsanity.com/paper/2512.03962/) (2025)
- [MRI2Qmap: multi-parametric quantitative mapping with MRI-driven denoising priors](https://mlsanity.com/paper/2603.11316/) (2026)

## Abstract (arXiv)

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.