Efficient and Accurate MRI Super-Resolution using a Generative Adversarial Network and 3D Multi-Level Densely Connected Network
This addresses the need for efficient and accurate high-resolution MRI generation for clinical applications, though it is incremental as it builds on existing deep learning and GAN techniques.
The paper tackled the problem of slow and memory-intensive 3D MRI super-resolution by proposing a novel 3D neural network design with GAN-guided training, achieving results that beat other deep learning methods in recovering 4x resolution-downgraded images and running 6x faster.
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.