MRI Super-Resolution with Ensemble Learning and Complementary Priors

Abstract

Magnetic resonance imaging (MRI) is a widely used medical imaging modality. However, due to the limitations in hardware, scan time, and throughput, it is often clinically challenging to obtain high-quality MR images. The super-resolution approach is potentially promising to improve MR image quality without any hardware upgrade. In this paper, we propose an ensemble learning and deep learning framework for MR image super-resolution. In our study, we first enlarged low resolution images using 5 commonly used super-resolution algorithms and obtained differentially enlarged image datasets with complementary priors. Then, a generative adversarial network (GAN) is trained with each dataset to generate super-resolution MR images. Finally, a convolutional neural network is used for ensemble learning that synergizes the outputs of GANs into the final MR super-resolution images. According to our results, the ensemble learning results outcome any one of GAN outputs. Compared with some state-of-the-art deep learning-based super-resolution methods, our approach is advantageous in suppressing artifacts and keeping more image details.

References in corpus (5)

• Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss
• fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
• CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)
• 3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network
• Brain MRI Super Resolution Using 3D Deep Densely Connected Neural Networks

Cited by in corpus (12)

• Multi-Contrast Super-Resolution MRI Through a Progressive Network
• VolumeNet: A Lightweight Parallel Network for Super-Resolution of Medical Volumetric Data
• Cine Cardiac MRI Motion Artifact Reduction Using a Recurrent Neural Network
• Task Transformer Network for Joint MRI Reconstruction and Super-Resolution
• Towards Label-Free 3D Segmentation of Optical Coherence Tomography Images of the Optic Nerve Head Using Deep Learning
• Deep learning for fast MR imaging: a review for learning reconstruction from incomplete k-space data
• SRR-Net: A Super-Resolution-Involved Reconstruction Method for High Resolution MR Imaging
• Towards Ultrafast MRI via Extreme k-Space Undersampling and Superresolution
• Localized Motion Artifact Reduction on Brain MRI Using Deep Learning with Effective Data Augmentation Techniques
• High-Resolution Pelvic MRI Reconstruction Using a Generative Adversarial Network with Attention and Cyclic Loss
• Brain Graph Super-Resolution Using Adversarial Graph Neural Network with Application to Functional Brain Connectivity
• IREM: High-Resolution Magnetic Resonance (MR) Image Reconstruction via Implicit Neural Representation