SRR-Net: A Super-Resolution-Involved Reconstruction Method for High Resolution MR Imaging
Not on the map. Why?
Abstract (arXiv)
Improving the image resolution and acquisition speed of magnetic resonance imaging (MRI) is a challenging problem. There are mainly two strategies dealing with the speed-resolution trade-off: (1) k-space undersampling with high-resolution acquisition, and (2) a pipeline of lower resolution image reconstruction and image super-resolution. However, these approaches either have limited performance at certain high acceleration factor or suffer from the error accumulation of two-step structure. In this paper, we combine the idea of MR reconstruction and image super-resolution, and work on recovering HR images from low-resolution under-sampled k-space data directly. Particularly, the SR-involved reconstruction can be formulated as a variational problem, and a learnable network unrolled from its solution algorithm is proposed. A discriminator was introduced to enhance the detail refining performance. Experiment results using in-vivo HR multi-coil brain data indicate that the proposed SRR-Net is capable of recovering high-resolution brain images with both good visual quality and perceptual quality.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 10 of its 23 references that are in the map. First posted on arXiv 13 Apr 2021.
Builds on
10 of 23 references.
References · 10
- 2017Improved Training of Wasserstein GANscited by 2,235
- 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
- 2017A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstructioncited by 232
- 2018The 2018 PIRM Challenge on Perceptual Image Super-resolutioncited by 156
- 2017Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstructioncited by 105
- 2018Efficient and Accurate MRI Super-Resolution using a Generative Adversarial Network and 3D Multi-Level Densely Connected Networkcited by 64
- 2018Brain MRI Super Resolution Using 3D Deep Densely Connected Neural Networkscited by 46
- 2019MRI Super-Resolution with Ensemble Learning and Complementary Priorscited by 27
- 2019Enhanced generative adversarial network for 3D brain MRI super-resolutioncited by 27
- 2018DIMENSION: Dynamic MR Imaging with Both K-space and Spatial Prior Knowledge Obtained via Multi-Supervised Network Trainingcited by 26
Built on by
Citing papers per year: 2021: 1.
1 paper.