# Sigma-net: Ensembled Iterative Deep Neural Networks for Accelerated Parallel MR Image Reconstruction

arXiv: https://arxiv.org/abs/1912.05480 · HTML: https://mlsanity.com/paper/1912.05480/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2019.

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

- [Assessment of Data Consistency through Cascades of Independently Recurrent Inference Machines for fast and robust accelerated MRI reconstruction](https://mlsanity.com/paper/2111.15498/) (2021)
- [Adapting model-based deep learning to multiple acquisition conditions: Ada-MoDL](https://mlsanity.com/paper/2304.11238/) (2023)

## Abstract (arXiv)

We explore an ensembled Sigma-net for fast parallel MR imaging, including parallel coil networks, which perform implicit coil weighting, and sensitivity networks, involving explicit sensitivity maps. The networks in Sigma-net are trained in a supervised way, including content and GAN losses, and with various ways of data consistency, i.e., proximal mappings, gradient descent and variable splitting. A semi-supervised finetuning scheme allows us to adapt to the k-space data at test time, which, however, decreases the quantitative metrics, although generating the visually most textured and sharp images. For this challenge, we focused on robust and high SSIM scores, which we achieved by ensembling all models to a Sigma-net.