# SDUM: A Scalable Deep Unrolled Model for Universal MRI Reconstruction

arXiv: https://arxiv.org/abs/2512.17137 · HTML: https://mlsanity.com/paper/2512.17137/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 58 references that are in the map.
- First posted on arXiv 19 Dec 2025.

## Builds on (most cited first, 30 of 38)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [fastMRI: An Open Dataset and Benchmarks for Accelerated MRI](https://mlsanity.com/paper/1811.08839/) (2018)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [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)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [Score-based diffusion models for accelerated MRI](https://mlsanity.com/paper/2110.05243/) (2021)
- [The Little Engine that Could: Regularization by Denoising (RED)](https://mlsanity.com/paper/1611.02862/) (2016)
- [Robust Compressed Sensing MRI with Deep Generative Priors](https://mlsanity.com/paper/2108.01368/) (2021)
- [End-to-End Variational Networks for Accelerated MRI Reconstruction](https://mlsanity.com/paper/2004.06688/) (2020)
- [Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning](https://mlsanity.com/paper/2206.12126/) (2022)
- [A Deep Cascade of Convolutional Neural Networks for MR Image Reconstruction](https://mlsanity.com/paper/1703.00555/) (2017)

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

- [UEPS: Robust and Efficient MRI Reconstruction](https://mlsanity.com/paper/2603.18572/) (2026)

## Abstract (arXiv)

Clinical MRI encompasses diverse imaging protocols--spanning anatomical targets (cardiac, brain, knee), contrasts (T1, T2, mapping), sampling patterns (Cartesian, radial, spiral, kt-space), and acceleration factors--yet current deep learning reconstructions are typically protocol-specific, hindering generalization and deployment. We introduce Scalable Deep Unrolled Model (SDUM), a universal framework combining a Restormer-based reconstructor, a learned coil sensitivity map estimator (CSME), sampling-aware weighted data consistency (SWDC), universal conditioning (UC) on cascade index and protocol metadata, and progressive cascade expansion training. SDUM exhibits foundation-model-like scaling behavior: reconstruction quality follows PSNR ~ log(parameters) with correlation r=0.986 (R2=0.973) up to 18 cascades, demonstrating predictable performance gains with model depth. A single SDUM trained on heterogeneous data achieves state-of-the-art results across all four CMRxRecon2025 challenge tracks--multi-center, multi-disease, 5T, and pediatric--without task-specific fine-tuning, surpassing specialized baselines by up to +1.0~dB. On CMRxRecon2024, SDUM outperforms the winning method PromptMR+ by +0.55~dB; on fastMRI brain, it exceeds PC-RNN by +1.8~dB. Ablations validate each component: SWDC +0.43~dB over standard DC, per-cascade CSME +0.51~dB, UC +0.38~dB. These results establish SDUM as a practical path toward universal, scalable MRI reconstruction.