MRI Super-Resolution with Ensemble Learning and Complementary Priors
This addresses the challenge of obtaining high-quality MRI images for medical applications without hardware upgrades, though it appears incremental as it builds on existing super-resolution algorithms and GANs.
The paper tackles the problem of low-quality MRI images by proposing an ensemble learning and deep learning framework for super-resolution, which synergizes outputs from multiple GANs to suppress artifacts and retain more details, outperforming individual GANs and some state-of-the-art methods.
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.