# Performance of a GPU- and Time-Efficient Pseudo 3D Network for Magnetic Resonance Image Super-Resolution and Motion Artifact Reduction

arXiv: https://arxiv.org/abs/2111.14259 · HTML: https://mlsanity.com/paper/2111.14259/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 47 references that are in the map.
- First posted on arXiv 28 Nov 2021.

## Builds on (most cited first, 17 of 17)

- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [Deep Evidential Regression](https://mlsanity.com/paper/1910.02600/) (2019)
- [Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning](https://mlsanity.com/paper/2012.09816/) (2020)
- [A General and Adaptive Robust Loss Function](https://mlsanity.com/paper/1701.03077/) (2017)
- [Efficient and Accurate MRI Super-Resolution using a Generative Adversarial Network and 3D Multi-Level Densely Connected Network](https://mlsanity.com/paper/1803.01417/) (2018)
- [Brain MRI Super Resolution Using 3D Deep Densely Connected Neural Networks](https://mlsanity.com/paper/1801.02728/) (2018)
- [Multi-Contrast MRI Super-Resolution via a Multi-Stage Integration Network](https://mlsanity.com/paper/2105.08949/) (2021)
- [Channel Splitting Network for Single MR Image Super-Resolution](https://mlsanity.com/paper/1810.06453/) (2018)
- [Suppressing Model Overfitting for Image Super-Resolution Networks](https://mlsanity.com/paper/1906.04809/) (2019)
- [Convolutional Neural Networks with Intermediate Loss for 3D Super-Resolution of CT and MRI Scans](https://mlsanity.com/paper/2001.01330/) (2020)
- [Simultaneous super-resolution and motion artifact removal in diffusion-weighted MRI using unsupervised deep learning](https://mlsanity.com/paper/2105.00240/) (2021)
- [Anisotropic Super Resolution in Prostate MRI using Super Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1912.09497/) (2019)

## Built on by (most cited first, 4 of 4)

- [The Unreasonable Effectiveness of Deep Evidential Regression](https://mlsanity.com/paper/2205.10060/) (2022)
- [Unsupervised Representation Learning for 3D MRI Super Resolution with Degradation Adaptation](https://mlsanity.com/paper/2205.06891/) (2022)
- [Efficient MRI Parallel Imaging Reconstruction by K-Space Rendering via Generalized Implicit Neural Representation](https://mlsanity.com/paper/2309.06067/) (2023)
- [Unpaired MRI Super Resolution with Contrastive Learning](https://mlsanity.com/paper/2310.15767/) (2023)

## Abstract (arXiv)

Shortening acquisition time and reducing motion artifacts are the most critical challenges in magnetic resonance imaging (MRI). Deep learning-based image restoration has emerged as a promising solution capable of generating high-resolution and motion-artifact-free MRI images from low-resolution images acquired with shortened acquisition times or from motion-artifact-corrupted images. To facilitate clinical integration, a time- and GPU-efficient network with reliable accuracy is essential. In this study, we adopted a unified 2D deep learning framework for pseudo-3D MRI image super-resolution reconstruction (SRR) and motion artifact reduction (MAR). The optimal down-sampling factors to optimize the acquisition time in SRR were identified. Training for MAR was performed using publicly available in vivo data, employing a novel standardized method to induce motion artifacts of varying severity in a controlled way. The accuracy of the network was evaluated through a pixel-wise uncertainty map, and performance was benchmarked against state-of-the-art methods. The results demonstrated that the down-sampling factor of 1x1x2 for x2 acceleration and 2x2x2 for x4 acceleration was optimal. For SRR, the proposed TS-RCAN outperformed the 3D networks of mDCSRN and ReCNN, with an improvement of more than 0.01 in SSIM and 1.5 dB in PSNR while reducing GPU load by up to and inference time by up to 90%. For MAR, TS-RCAN exceeded UNet's performance by up to 0.014 in SSIM and 1.48 dB in PSNR. Additionally, TS-RCAN provided uncertainty information, which can be used to estimate the quality of the reconstructed images. TS-RCAN has potential use for SRR and MAR in the clinical setting.