High-resolution (HR) magnetic resonance imaging (MRI) provides detailed anatomical information that is critical for diagnosis in the clinical application. However, HR MRI typically comes at the cost of long scan time, small spatial coverage, and low
signal-to-noise ratio (SNR). Recent studies showed that with a deep convolutional neural network (CNN), HR generic images could be recovered from low-resolution (LR) inputs via single image super-resolution (SISR) approaches. Additionally, previous works have shown that a deep 3D CNN can generate high-quality SR MRIs by using learned image priors. However, 3D CNN with deep structures, have a large number of parameters and are computationally expensive. In this paper, we propose a novel 3D CNN architecture, namely a multi-level densely connected super-resolution network (mDCSRN), which is light-weight, fast and accurate. We also show that with the generative adversarial network (GAN)-guided training, the mDCSRN-GAN provides appealing sharp SR images with rich texture details that are highly comparable with the referenced HR images. Our results from experiments on a large public dataset with 1,113 subjects showed that this new architecture outperformed other popular deep learning methods in recovering 4x resolution-downgraded images in both quality and speed.
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 cov
erage, 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.
Objective: The purpose of this manuscript is to accelerate cardiac diffusion tensor imaging (CDTI) by integrating low-rankness and compressed sensing. Methods: Diffusion-weighted images exhibit both transform sparsity and low-rankness. These properti
es can jointly be exploited to accelerate CDTI, especially when a phase map is applied to correct for the phase inconsistency across diffusion directions, thereby enhancing low-rankness. The proposed method is evaluated both ex vivo and in vivo, and is compared to methods using either a low-rank or sparsity constraint alone. Results: Compared to using a low-rank or sparsity constraint alone, the proposed method preserves more accurate helix angle features, the transmural continuum across the myocardium wall, and mean diffusivity at higher acceleration, while yielding significantly lower bias and higher intraclass correlation coefficient. Conclusion: Low-rankness and compressed sensing together facilitate acceleration for both ex vivo and in vivo CDTI, improving reconstruction accuracy compared to employing either constraint alone. Significance: Compared to previous methods for accelerating CDTI, the proposed method has the potential to reach higher acceleration while preserving myofiber architecture features which may allow more spatial coverage, higher spatial resolution and shorter temporal footprint in the future.
