Efficient and Accurate MRI Super-Resolution using a Generative Adversarial Network and 3D Multi-Level Densely Connected Network
By Yuhua Chen, Feng Shi, Anthony G. Christodoulou, Zhengwei Zhou, Yibin Xie, Debiao Li. International Conference on Medical Image Computing and Computer-Assisted Intervention, 2018
351 citations recorded by the source corpus.
High-resolution (HR) magnetic resonance images (MRI) provide detailed anatomical information important for clinical application and quantitative image analysis. However, HR MRI conventionally comes at the cost of longer scan time, smaller spatial coverage, and lower signal-to-noise ratio (SNR). Recent studies have shown that single image super-resolution (SISR), a technique to recover HR details from one single low-resolution (LR) input image, could provide high-quality image details with the help of advanced deep convolutional neural networks (CNN). However, deep neural networks consume memory heavily and run slowly, especially in 3D settings. In this paper, we propose a novel 3D neural network design, namely a multi-level densely connected super-resolution network (mDCSRN) with generative adversarial network (GAN)-guided training. The mDCSRN quickly trains and inferences and the GAN promotes realistic output hardly distinguishable from original HR images. Our results from experiments on a dataset with 1,113 subjects show that our new architecture beats other popular deep learning methods in recovering 4x resolution-downgraded im-ages and runs 6x faster.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/d5a0e097232834fb9eefed3a77fccad78e0a9cf0
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Shadi Albarqouni
- Christoph Baur
- B. van Ginneken
- Anirban Mukhopadhyay
- Nassir Navab
- Shenghong Ju
- Arjan Kuijper
- Paul S. Babyn
Citations in the corpus
- Generative Adversarial Network in Medical Imaging: A Review (2018, methodology): “The basic pix2pix framework has been used for low dose CT denoising (Wolterink et al., 2017b), MR reconstruction (Chen et al., 2018b; Kim et al., 2018; Dar et al., 2018b; Shitrit and Raviv, 2017), and PET denoising (Wang et al., 2018b).”
- GANs for Medical Image Analysis (2018, background): “[73] proposes DAN — a combination of DCAN [74] and VGG16 — which is trained with both supervised and unsupervised strategies to provide high-quality segmentation masks for unseen images.”
- CT Super-Resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE) (2018, methodology): “For several imaging modalities, DL-based SR methods were successfully developed [38]–[41].”