Search

Deep learning (DL) has emerged as a leading approach in accelerating MRI. It employs deep neural networks to extract knowledge from available datasets and then applies the trained networks to reconstruct accurate images from limited measurements. Unlike natural image restoration problems, MRI involves physics‐based imaging processes, unique data properties, and diverse imaging tasks. This domain knowledge needs to be integrated with data‐driven approaches. Our review will introduce the significant challenges faced by such knowledge‐driven DL approaches in the context of fast MRI along with several notable solutions, which include learning neural networks and addressing different imaging application scenarios. The traits and trends of these techniques have also been given which have shifted from supervised learning to semi‐supervised learning, and finally, to unsupervised learning methods. In addition, MR vendors' choices of DL reconstruction have been provided along with some discussions on open questions and future directions, which are critical for the reliable imaging systems. [ABSTRACT FROM AUTHOR]

Magnetic resonance (MR) image reconstruction and super-resolution are two prominent techniques to restore high-quality images from undersampled or low-resolution k-space data to accelerate MR imaging. Combining undersampled and low-resolution acquisition can further improve the acceleration factor. Existing methods often treat the techniques of image reconstruction and super-resolution separately or combine them sequentially for image recovery, which can result in error propagation and suboptimal results. In this work, we propose a novel framework for joint image reconstruction and super-resolution, aiming to efficiently image recovery and enable fast imaging. Specifically, we designed a framework with a reconstruction module and a super-resolution module to formulate multi-task learning. The reconstruction module utilizes a model-based optimization approach, ensuring data fidelity with the acquired k-space data. Moreover, a deep spatial feature transform is employed to enhance the information transition between the two modules, facilitating better integration of image reconstruction and super-resolution. Experimental evaluations on two datasets demonstrate that our proposed method can provide superior performance both quantitatively and qualitatively. [ABSTRACT FROM AUTHOR]

Lately, deep learning technology has been extensively investigated for accelerating dynamic magnetic resonance (MR) imaging, with encouraging progresses achieved. However, without fully sampled reference data for training, the current approaches may have limited abilities in recovering fine details or structures. To address this challenge, this paper proposes a self-supervised collaborative learning framework (SelfCoLearn) for accurate dynamic MR image reconstruction from undersampled k-space data directly. The proposed SelfCoLearn is equipped with three important components, namely, dual-network collaborative learning, reunderampling data augmentation and a special-designed co-training loss. The framework is flexible and can be integrated into various model-based iterative un-rolled networks. The proposed method has been evaluated on an in vivo dataset and was compared to four state-of-the-art methods. The results show that the proposed method possesses strong capabilities in capturing essential and inherent representations for direct reconstructions from the undersampled k-space data and thus enables high-quality and fast dynamic MR imaging. [ABSTRACT FROM AUTHOR]

Dynamic MR image reconstruction from incomplete k‐space data has generated great research interest due to its capability in reducing scan time. Nevertheless, the reconstruction problem is still challenging due to its ill‐posed nature. Most existing methods either suffer from long iterative reconstruction time or explore limited prior knowledge. This paper proposes a dynamic MR imaging method with both k‐space and spatial prior knowledge integrated via multi‐supervised network training, dubbed as DIMENSION. Specifically, the DIMENSION architecture consists of a frequential prior network for updating the k‐space with its network prediction and a spatial prior network for capturing image structures and details. Furthermore, a multi‐supervised network training technique is developed to constrain the frequency domain information and the spatial domain information. The comparisons with classical k‐t FOCUSS, k‐t SLR, L+S and the state‐of‐the‐art CNN‐based method on in vivo datasets show our method can achieve improved reconstruction results in shorter time. [ABSTRACT FROM AUTHOR]

Deep learning methods have achieved attractive performance in dynamic MR cine imaging. However, most of these methods are driven only by the sparse prior of MR images, while the important low-rank (LR) prior of dynamic MR cine images is not explored, which may limit further improvements in dynamic MR reconstruction. In this paper, a learned singular value thresholding (Learned-SVT) operator is proposed to explore low-rank priors in dynamic MR imaging to obtain improved reconstruction results. In particular, we put forward a model-based unrolling sparse and low-rank network for dynamic MR imaging, dubbed as SLR-Net. SLR-Net is defined over a deep network flow graph, which is unrolled from the iterative procedures in the iterative shrinkage-thresholding algorithm (ISTA) for optimizing a sparse and LR-based dynamic MRI model. Experimental results on a single-coil scenario show that the proposed SLR-Net can further improve the state-of-the-art compressed sensing (CS) methods and sparsity-driven deep learning-based methods with strong robustness to different undersampling patterns, both qualitatively and quantitatively. Besides, SLR-Net has been extended to a multi-coil scenario, and achieved excellent reconstruction results compared with a sparsity-driven multi-coil deep learning-based method under a high acceleration. Prospective reconstruction results on an open real-time dataset further demonstrate the capability and flexibility of the proposed method on real-time scenarios. [ABSTRACT FROM AUTHOR]

The aim of this work is to implement real-time 3D MR thermometry for high intensity focused ultrasound (HIFU) monitoring. Volumetric MR thermometry was implemented based on a 3D echo-shifted sequence with short TR to improve temperature sensitivity. The 3D acquisition was accelerated in two phase encoding directions with controlled aliasing in volumetric parallel imaging (CAIPIRINHA). Image reconstruction was run in an open source reconstruction platform (Gadgetron). Phantom experiments showed the proposed volumetric thermometry was comparable to the fiber optical thermometer. In-vivo animal experiments in rabbit thigh showed that the temperature error before and after 4× acceleration was less than 0.65 °C. Finally, real-time 3D thermometry with temporal resolution ~3 s and spatial resolution 2 × 2 × 5 mm3 (spatial coverage 192 × 192 × 80 mm3) was achieved with Gadgetron reconstruction. Real-time temperature monitoring was achieved in-vivo by using parallel imaging accelerated 3D echo-shifted sequence with Gadgetron reconstruction. [ABSTRACT FROM AUTHOR]

Recently, untrained neural networks (UNNs) have shown satisfactory performances for MR image reconstruction on random sampling trajectories without using additional full-sampled training data. However, the existing UNN-based approaches lack the modeling of physical priors, resulting in poor performance in some common scenarios (e.g., partial Fourier (PF), regular sampling, etc.) and the lack of theoretical guarantees for reconstruction accuracy. To bridge this gap, we propose a safeguarded k -space interpolation method for MRI using a specially designed UNN with a tripled architecture driven by three physical priors of the MR images (or k -space data), including transform sparsity, coil sensitivity smoothness, and phase smoothness. We also prove that the proposed method guarantees tight bounds for interpolated k -space data accuracy. Finally, ablation experiments show that the proposed method can characterize the physical priors of MR images well. Additionally, experiments show that the proposed method consistently outperforms traditional parallel imaging methods and existing UNNs, and is even competitive against supervised-trained deep learning methods in PF and regular undersampling reconstruction. • A physical prior-driven untrained neural network was proposed for MRI reconstruction. • The accuracy of the proposed model's MRI reconstruction was analyzed. • Experimental results confirmed model's superiority in MRI reconstruction. [ABSTRACT FROM AUTHOR]

Purpose: The application of compressed sensing (CS) technology in magnetic resonance imaging (MRI) is to accelerate the MRI scan speed by incoherent undersampling of k-space data and nonlinear iterative reconstruction of MRI images. This paper generalizes the existing rosette trajectories to configure the sampling patterns for undersampled k-space data acquisition in MRI scans. The arch and curvature characteristics of the generalized rosette trajectories are analyzed to explore their feasibility and advantages for CS reconstruction of MRI images. Methods: Two key properties crucial to the CS MRI application, the scan speed and sampling incoherence of the generalized rosette trajectories, are analyzed. The analysis on the scan speed of generalized rosette trajectories is based on the transversal time derived from the curvature of the trajectories, and the sampling incoherence is based on the evaluation of the point spread function for the measurement matrix. The results of analysis are supported by extensive simulations where the performances of rosette, spiral, and radial sampling patterns at different acceleration factors are compared. Results: It is shown that compared with spiral trajectories, the arch and curvature characteristics of the generalized rosette trajectories are more feasible to meet the physical requirements of undersampled k-space data acquisition in terms of time shortness and scan area. It is further shown that the sampling pattern of the rosette trajectory has higher incoherence than that of the other trajectories and can thus achieve higher reconstruction performance. Reconstruction performances illustrate that the rosette trajectory can achieve about 10% higher peak signal-to-noise ratio than radial and spiral trajectories under the high acceleration factor R = 10. Conclusions: The generalized rosette trajectories can be a desirable candidate for CS reconstruction of MRI. [ABSTRACT FROM AUTHOR]

Abstract Cloud cover is a common problem in optical remote sensing images due to its contamination of the reflectance from the Earth's surface. Cloud removal has become a necessary preprocessing step for most applications. In this paper, we develop an effective thin cloud removal method with the help of a noise-adjusted principal components transform model (CR-NAPCT). We discover that cloud-contaminated data has the highest signal-to-noise ratio (S/N) due to its high spatial correlation, and are shown in the first NAPCT component (NAPC1) in the NAPCT data. Image restoration is achieved by performing an inverse NAPCT after removing the cloud component in NAPC1. In the experiments, both simulated and real images from Landsat 8 were used to assess the performance of the proposed method quantitatively and qualitatively. The results show that the CR-NAPCT method is effective in eliminating thin cloud effects and performs better than the existing similar approaches tested. [ABSTRACT FROM AUTHOR]

• A model-based unrolled low-rank plus sparse network (L+S-Net) for dynamic MR reconstruction is proposed. • A learned singular value thresholding (LSVT) was introduced to exploit the deep low rank prior in dynamic MR. • The iterative steps are unrolled into a network whose regularization parameters are learned during training instead of the empirical selection. • The convergence analysis guarantees the performance of the reconstruction theoretically. • Retrospective and prospective study on single-coil/multi-coil datasets show that the L+S-Net can improve the reconstruction result both qualitatively and quantitatively. [Display omitted] In dynamic magnetic resonance (MR) imaging, low-rank plus sparse (L+S) decomposition, or robust principal component analysis (PCA), has achieved stunning performance. However, the selection of the parameters of L+S is empirical, and the acceleration rate is limited, which are common failings of iterative compressed sensing MR imaging (CS-MRI) reconstruction methods. Many deep learning approaches have been proposed to address these issues, but few of them use a low-rank prior. In this paper, a model-based low-rank plus sparse network, dubbed L+S-Net, is proposed for dynamic MR reconstruction. In particular, we use an alternating linearized minimization method to solve the optimization problem with low-rank and sparse regularization. Learned soft singular value thresholding is introduced to ensure the clear separation of the L component and S component. Then, the iterative steps are unrolled into a network in which the regularization parameters are learnable. We prove that the proposed L+S-Net achieves global convergence under two standard assumptions. Experiments on retrospective and prospective cardiac cine datasets show that the proposed model outperforms state-of-the-art CS and existing deep learning methods and has great potential for extremely high acceleration factors (up to 24 ×). [ABSTRACT FROM AUTHOR]