# Generalized Deep Learning-based Proximal Gradient Descent for MR Reconstruction

arXiv: https://arxiv.org/abs/2211.16881 · HTML: https://mlsanity.com/paper/2211.16881/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 30 Nov 2022.

## Builds on (most cited first, 6 of 6)

- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [MoDL: Model Based Deep Learning Architecture for Inverse Problems](https://mlsanity.com/paper/1712.02862/) (2017)
- [A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction](https://mlsanity.com/paper/1704.02422/) (2017)
- [MRI Reconstruction Using Deep Bayesian Estimation](https://mlsanity.com/paper/1909.01127/) (2019)
- [SANTIS: Sampling-Augmented Neural neTwork with Incoherent Structure for MR image reconstruction](https://mlsanity.com/paper/1812.03278/) (2018)
- [Compressive MR Fingerprinting reconstruction with Neural Proximal Gradient iterations](https://mlsanity.com/paper/2006.15271/) (2020)

## Built on by (most cited first, 1 of 1)

- [GA-HQS: MRI reconstruction via a generically accelerated unfolding approach](https://mlsanity.com/paper/2304.02883/) (2023)

## Abstract (arXiv)

The data consistency for the physical forward model is crucial in inverse problems, especially in MR imaging reconstruction. The standard way is to unroll an iterative algorithm into a neural network with a forward model embedded. The forward model always changes in clinical practice, so the learning component's entanglement with the forward model makes the reconstruction hard to generalize. The deep learning-based proximal gradient descent was proposed and use a network as regularization term that is independent of the forward model, which makes it more generalizable for different MR acquisition settings. This one-time pre-trained regularization is applied to different MR acquisition settings and was compared to conventional L1 regularization showing ~3 dB improvement in the peak signal-to-noise ratio. We also demonstrated the flexibility of the proposed method in choosing different undersampling patterns.