# Neural Network-based Reconstruction in Compressed Sensing MRI Without Fully-sampled Training Data

arXiv: https://arxiv.org/abs/2007.14979 · HTML: https://mlsanity.com/paper/2007.14979/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2020.

## Built on by (most cited first, 14 of 14)

- [Adaptive Diffusion Priors for Accelerated MRI Reconstruction](https://mlsanity.com/paper/2207.05876/) (2022)
- [Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers](https://mlsanity.com/paper/2105.08059/) (2021)
- [DSFormer: A Dual-domain Self-supervised Transformer for Accelerated Multi-contrast MRI Reconstruction](https://mlsanity.com/paper/2201.10776/) (2022)
- [Dual-Domain Self-Supervised Learning for Accelerated Non-Cartesian MRI Reconstruction](https://mlsanity.com/paper/2302.09244/) (2023)
- [Regularization-Agnostic Compressed Sensing MRI Reconstruction with Hypernetworks](https://mlsanity.com/paper/2101.02194/) (2021)
- [Computing Multiple Image Reconstructions with a Single Hypernetwork](https://mlsanity.com/paper/2202.11009/) (2022)
- [Analyzing the Sample Complexity of Self-Supervised Image Reconstruction Methods](https://mlsanity.com/paper/2305.19079/) (2023)
- [Benchmarking Self-Supervised Learning Methods for Accelerated MRI Reconstruction](https://mlsanity.com/paper/2502.14009/) (2025)
- [Hyper-Convolutions via Implicit Kernels for Medical Imaging](https://mlsanity.com/paper/2202.02701/) (2022)
- [Joint Optimization of Hadamard Sensing and Reconstruction in Compressed Sensing Fluorescence Microscopy](https://mlsanity.com/paper/2105.07961/) (2021)
- [Biomedical Image Reconstruction: A Survey](https://mlsanity.com/paper/2301.11813/) (2023)
- [Dual-domain Multi-path Self-supervised Diffusion Model for Accelerated MRI Reconstruction](https://mlsanity.com/paper/2503.18836/) (2025)
- [HyDRA: Hybrid Denoising Regularization for Measurement-Only DEQ Training](https://mlsanity.com/paper/2601.01228/) (2026)
- [Next-Acceleration-Scale Prediction for Autoregressive MRI Reconstruction](https://mlsanity.com/paper/2605.19354/) (2026)

## Abstract (arXiv)

Compressed Sensing MRI (CS-MRI) has shown promise in reconstructing under-sampled MR images, offering the potential to reduce scan times. Classical techniques minimize a regularized least-squares cost function using an expensive iterative optimization procedure. Recently, deep learning models have been developed that model the iterative nature of classical techniques by unrolling iterations in a neural network. While exhibiting superior performance, these methods require large quantities of ground-truth images and have shown to be non-robust to unseen data. In this paper, we explore a novel strategy to train an unrolled reconstruction network in an unsupervised fashion by adopting a loss function widely-used in classical optimization schemes. We demonstrate that this strategy achieves lower loss and is computationally cheap compared to classical optimization solvers while also exhibiting superior robustness compared to supervised models. Code is available at https://github.com/alanqrwang/HQSNet.