# An unsupervised method for MRI recovery: Deep image prior with structured sparsity

arXiv: https://arxiv.org/abs/2501.01482 · HTML: https://mlsanity.com/paper/2501.01482/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 2 Jan 2025.

## Builds on (most cited first, 20 of 20)

- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [fastMRI: An Open Dataset and Benchmarks for Accelerated MRI](https://mlsanity.com/paper/1811.08839/) (2018)
- [MoDL: Model Based Deep Learning Architecture for Inverse Problems](https://mlsanity.com/paper/1712.02862/) (2017)
- [Learning a Variational Network for Reconstruction of Accelerated MRI Data](https://mlsanity.com/paper/1704.00447/) (2017)
- [Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks](https://mlsanity.com/paper/1810.03982/) (2018)
- [Deep learning for undersampled MRI reconstruction](https://mlsanity.com/paper/1709.02576/) (2017)
- [Plug and play methods for magnetic resonance imaging (long version)](https://mlsanity.com/paper/1903.08616/) (2019)
- [Time-Dependent Deep Image Prior for Dynamic MRI](https://mlsanity.com/paper/1910.01684/) (2019)
- [Physics-Driven Deep Learning for Computational Magnetic Resonance Imaging](https://mlsanity.com/paper/2203.12215/) (2022)
- [Early Stopping for Deep Image Prior](https://mlsanity.com/paper/2112.06074/) (2021)
- [OCMR (v1.0)--Open-Access Multi-Coil k-Space Dataset for Cardiovascular Magnetic Resonance Imaging](https://mlsanity.com/paper/2008.03410/) (2020)
- [The Spectral Bias of the Deep Image Prior](https://mlsanity.com/paper/1912.08905/) (2019)
- [Dynamic imaging using a deep generative SToRM (Gen-SToRM) model](https://mlsanity.com/paper/2102.00034/) (2021)
- [Technical Report (v1.0)--Pseudo-random Cartesian Sampling for Dynamic MRI](https://mlsanity.com/paper/2206.03630/) (2022)
- [Dynamic imaging using Motion-Compensated SmooThness Regularization on Manifolds (MoCo-SToRM)](https://mlsanity.com/paper/2112.03380/) (2021)
- [Low-rank and Adaptive Sparse Signal (LASSI) Models for Highly Accelerated Dynamic Imaging](https://mlsanity.com/paper/1611.04069/) (2016)
- [Attention-aware non-rigid image registration for accelerated MR imaging](https://mlsanity.com/paper/2404.17621/) (2024)
- [Deep Image prior with StruCtUred Sparsity (DISCUS) for dynamic MRI reconstruction](https://mlsanity.com/paper/2312.00953/) (2023)
- [Analytical model for the approximation of hysteresis loop and its application to the scanning tunneling microscope](https://mlsanity.com/paper/2006.02784/) (2020)
- [Surface Coil Intensity Correction for MRI](https://mlsanity.com/paper/2312.00936/) (2023)

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

- [CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction](https://mlsanity.com/paper/2603.04438/) (2026)
- [Evaluating the Impact of Medical Image Reconstruction on Downstream AI Fairness and Performance](https://mlsanity.com/paper/2604.10904/) (2026)

## Abstract (arXiv)

Objective: To propose and validate an unsupervised MRI reconstruction method that does not require fully sampled k-space data. Materials and Methods: The proposed method, deep image prior with structured sparsity (DISCUS), extends the deep image prior (DIP) by introducing group sparsity to frame-specific code vectors, enabling the discovery of a low-dimensional manifold for capturing temporal variations. discus was validated using four studies: (I) simulation of a dynamic Shepp-Logan phantom to demonstrate its manifold discovery capabilities, (II) comparison with compressed sensing and DIP-based methods using simulated single-shot late gadolinium enhancement (LGE) image series from six distinct digital cardiac phantoms in terms of normalized mean square error (NMSE) and structural similarity index measure (SSIM), (III) evaluation on retrospectively undersampled single-shot LGE data from eight patients, and (IV) evaluation on prospectively undersampled single-shot LGE data from eight patients, assessed via blind scoring from two expert readers. Results: DISCUS outperformed competing methods, demonstrating superior reconstruction quality in terms of NMSE and SSIM (Studies I--III) and expert reader scoring (Study IV). Discussion: An unsupervised image reconstruction method is presented and validated on simulated and measured data. These developments can benefit applications where acquiring fully sampled data is challenging.