# Scale-Equivariant Unrolled Neural Networks for Data-Efficient Accelerated MRI Reconstruction

Source: [Scale-Equivariant Unrolled Neural Networks for Data-Efficient Accelerated MRI Reconstruction](<https://www.sota2.com/research/paper/68fa6c571e209131cea3367a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-24T18:08:42.397Z

Authors: Beliz Gunel, Arda Sahiner, Arjun D. Desai, Akshay S. Chaudhari, Shreyas Vasanawala, Mert Pilanci, John Pauly

Published: 2022-04-21T23:29:52.000Z

## Abstract

Unrolled neural networks have enabled state-of-the-art reconstruction performance and fast inference times for the accelerated magnetic resonance imaging (MRI) reconstruction task. However, these approaches depend on fully-sampled scans as ground truth data which is either costly or not possible to acquire in many clinical medical imaging applications; hence, reducing dependence on data is desirable. In this work, we propose modeling the proximal operators of unrolled neural networks with scale-equivariant convolutional neural networks in order to improve the data-efficiency and robustness to drifts in scale of the images that might stem from the variability of patient anatomies or change in field-of-view across different MRI scanners. Our approach demonstrates strong improvements over the state-of-the-art unrolled neural networks under the same memory constraints both with and without data augmentations on both in-distribution and out-of-distribution scaled images without significantly increasing the train or inference time.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [MRI Reconstruction on mridata 3D FSE multi-coil knee (in-distribution 1.0)](<https://www.sota2.com/research/sota/mri-reconstruction-on-mridata-3d-fse-multi-coil-knee-in-distribution-1-0.md>): MRI Reconstruction; mridata 3D FSE multi-coil knee Original in-distribution 1.0; SSIM: 91.1.

- [MRI Reconstruction on mridata 3D FSE multi-coil knee Scaled a=0.9 1.0](<https://www.sota2.com/research/sota/mri-reconstruction-on-mridata-3d-fse-multi-coil-knee-scaled-a-0-9-1-0.md>): MRI Reconstruction; mridata 3D FSE multi-coil knee Scaled a=0.9 1.0; SSIM: 0.956.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2204.10436>)

[PDF](<https://arxiv.org/pdf/2204.10436.pdf>)

[Implementation](<https://github.com/ad12/meddlr>)