Brain MRI Super Resolution Using 3D Deep Densely Connected Neural Networks

Abstract

Magnetic resonance image (MRI) in high spatial resolution provides detailed anatomical information and is often necessary for accurate quantitative analysis. However, high spatial resolution typically comes at the expense of longer scan time, less spatial coverage, and lower signal to noise ratio (SNR). Single Image Super-Resolution (SISR), a technique aimed to restore high-resolution (HR) details from one single low-resolution (LR) input image, has been improved dramatically by recent breakthroughs in deep learning. In this paper, we introduce a new neural network architecture, 3D Densely Connected Super-Resolution Networks (DCSRN) to restore HR features of structural brain MR images. Through experiments on a dataset with 1,113 subjects, we demonstrate that our network outperforms bicubic interpolation as well as other deep learning methods in restoring 4x resolution-reduced images.

Accepted by ISBI'18

Cited by in corpus (18)

• Generative Adversarial Network in Medical Imaging: A Review
• A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises
• Multi-Contrast Super-Resolution MRI Through a Progressive Network
• Channel Splitting Network for Single MR Image Super-Resolution
• High-throughput molecular imaging via deep learning enabled Raman spectroscopy
• MRI Super-Resolution with Ensemble Learning and Complementary Priors
• An Arbitrary Scale Super-Resolution Approach for 3D MR Images via Implicit Neural Representation
• Fully Automated Multi-Organ Segmentation in Abdominal Magnetic Resonance Imaging with Deep Neural Networks
• VolumeNet: A Lightweight Parallel Network for Super-Resolution of Medical Volumetric Data
• Deep MR Brain Image Super-Resolution Using Spatio-Structural Priors
• 3D Segmentation Guided Style-based Generative Adversarial Networks for PET Synthesis
• Model-Guided Multi-Contrast Deep Unfolding Network for MRI Super-resolution Reconstruction
• Anisotropic Super Resolution in Prostate MRI using Super Resolution Generative Adversarial Networks
• fVDB: A Deep-Learning Framework for Sparse, Large-Scale, and High-Performance Spatial Intelligence
• SuperFormer: Volumetric Transformer Architectures for MRI Super-Resolution
• Performance of a GPU- and Time-Efficient Pseudo 3D Network for Magnetic Resonance Image Super-Resolution and Motion Artifact Reduction
• Unsupervised Representation Learning for 3D MRI Super Resolution with Degradation Adaptation
• Magnitude-image based data-consistent deep learning method for MRI super resolution