scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Image reconstruction of compressed sensing MRI using graph-based redundant wavelet transform.

01 Jan 2016-Medical Image Analysis (Elsevier)-Vol. 27, pp 93-104
TL;DR: A graph-based redundant wavelet transform is introduced to sparsely represent magnetic resonance images in iterative image reconstructions and outperforms several state-of-the-art reconstruction methods in removing artifacts and achieves fewer reconstruction errors on the tested datasets.
About: This article is published in Medical Image Analysis.The article was published on 2016-01-01. It has received 150 citations till now. The article focuses on the topics: Iterative reconstruction & Wavelet transform.
Citations
More filters
Journal ArticleDOI
TL;DR: This paper provides a deep learning-based strategy for reconstruction of CS-MRI, and bridges a substantial gap between conventional non-learning methods working only on data from a single image, and prior knowledge from large training data sets.
Abstract: Compressed sensing magnetic resonance imaging (CS-MRI) enables fast acquisition, which is highly desirable for numerous clinical applications. This can not only reduce the scanning cost and ease patient burden, but also potentially reduce motion artefacts and the effect of contrast washout, thus yielding better image quality. Different from parallel imaging-based fast MRI, which utilizes multiple coils to simultaneously receive MR signals, CS-MRI breaks the Nyquist–Shannon sampling barrier to reconstruct MRI images with much less required raw data. This paper provides a deep learning-based strategy for reconstruction of CS-MRI, and bridges a substantial gap between conventional non-learning methods working only on data from a single image, and prior knowledge from large training data sets. In particular, a novel conditional Generative Adversarial Networks-based model (DAGAN)-based model is proposed to reconstruct CS-MRI. In our DAGAN architecture, we have designed a refinement learning method to stabilize our U-Net based generator, which provides an end-to-end network to reduce aliasing artefacts. To better preserve texture and edges in the reconstruction, we have coupled the adversarial loss with an innovative content loss. In addition, we incorporate frequency-domain information to enforce similarity in both the image and frequency domains. We have performed comprehensive comparison studies with both conventional CS-MRI reconstruction methods and newly investigated deep learning approaches. Compared with these methods, our DAGAN method provides superior reconstruction with preserved perceptual image details. Furthermore, each image is reconstructed in about 5 ms, which is suitable for real-time processing.

835 citations


Cites background from "Image reconstruction of compressed ..."

  • ..., total variation (TV) [17]–[19], discrete cosine transforms [20]–[22] and discrete wavelet transforms [23]–[25]....

    [...]

Journal ArticleDOI
TL;DR: Two versions of a novel deep learning architecture are proposed, dubbed as ADMM-CSNet, by combining the traditional model-based CS method and data-driven deep learning method for image reconstruction from sparsely sampled measurements, which achieved favorable reconstruction accuracy in fast computational speed compared with the traditional and the other deep learning methods.
Abstract: Compressive sensing (CS) is an effective technique for reconstructing image from a small amount of sampled data. It has been widely applied in medical imaging, remote sensing, image compression, etc. In this paper, we propose two versions of a novel deep learning architecture, dubbed as ADMM-CSNet, by combining the traditional model-based CS method and data-driven deep learning method for image reconstruction from sparsely sampled measurements. We first consider a generalized CS model for image reconstruction with undetermined regularizations in undetermined transform domains, and then two efficient solvers using Alternating Direction Method of Multipliers (ADMM) algorithm for optimizing the model are proposed. We further unroll and generalize the ADMM algorithm to be two deep architectures, in which all parameters of the CS model and the ADMM algorithm are discriminatively learned by end-to-end training. For both applications of fast CS complex-valued MR imaging and CS imaging of real-valued natural images, the proposed ADMM-CSNet achieved favorable reconstruction accuracy in fast computational speed compared with the traditional and the other deep learning methods.

470 citations

Journal ArticleDOI
TL;DR: Wang et al. as discussed by the authors proposed a projected iterative soft thresholding algorithm (pISTA) and its acceleration pFISTA for CS-MRI image reconstruction, which exploit sparsity of the magnetic resonance (MR) images under the redundant representation of tight frames.
Abstract: Compressed sensing (CS) has exhibited great potential for accelerating magnetic resonance imaging (MRI). In CS-MRI, we want to reconstruct a high-quality image from very few samples in a short time. In this paper, we propose a fast algorithm, called projected iterative soft-thresholding algorithm (pISTA), and its acceleration pFISTA for CS-MRI image reconstruction. The proposed algorithms exploit sparsity of the magnetic resonance (MR) images under the redundant representation of tight frames. We prove that pISTA and pFISTA converge to a minimizer of a convex function with a balanced tight frame sparsity formulation. The pFISTA introduces only one adjustable parameter, the step size, and we provide an explicit rule to set this parameter. Numerical experiment results demonstrate that pFISTA leads to faster convergence speeds than the state-of-art counterpart does, while achieving comparable reconstruction errors. Moreover, reconstruction errors incurred by pFISTA appear insensitive to the step size.

128 citations

Journal ArticleDOI
TL;DR: Experimental results on simulated and real magnetic resonance spectroscopy data show that the proposed approach can successfully recover full signals from very limited samples and is robust to the estimated tensor rank.
Abstract: Signals are generally modeled as a superposition of exponential functions in spectroscopy of chemistry, biology, and medical imaging. For fast data acquisition or other inevitable reasons, however, only a small amount of samples may be acquired, and thus, how to recover the full signal becomes an active research topic, but existing approaches cannot efficiently recover $N$ -dimensional exponential signals with $N\geq 3$ . In this paper, we study the problem of recovering $N$ -dimensional (particularly $N\geq 3$ ) exponential signals from partial observations, and formulate this problem as a low-rank tensor completion problem with exponential factor vectors. The full signal is reconstructed by simultaneously exploiting the CANDECOMP/PARAFAC tensor structure and the exponential structure of the associated factor vectors. The latter is promoted by minimizing an objective function involving the nuclear norm of Hankel matrices. Experimental results on simulated and real magnetic resonance spectroscopy data show that the proposed approach can successfully recover full signals from very limited samples and is robust to the estimated tensor rank.

94 citations

Journal ArticleDOI
TL;DR: Wang et al. as discussed by the authors proposed the first deep learning model for multi-contrast CS-MRI reconstruction, which achieved information sharing through feature sharing units, which significantly reduced the number of model parameters.
Abstract: Compressed sensing (CS) theory can accelerate multi-contrast magnetic resonance imaging (MRI) by sampling fewer measurements within each contrast. However, conventional optimization-based reconstruction models suffer several limitations, including a strict assumption of shared sparse support, time-consuming optimization, and “shallow” models with difficulties in encoding the patterns contained in massive MRI data. In this paper, we propose the first deep learning model for multi-contrast CS-MRI reconstruction. We achieve information sharing through feature sharing units, which significantly reduces the number of model parameters. The feature sharing unit combines with a data fidelity unit to comprise an inference block, which are then cascaded with dense connections, allowing for efficient information transmission across different depths of the network. Experiments on various multi-contrast MRI datasets show that the proposed model outperforms both state-of-the-art single-contrast and multi-contrast MRI methods in accuracy and efficiency. We demonstrate that improved reconstruction quality can bring benefits to subsequent medical image analysis. Furthermore, the robustness of the proposed model to misregistration shows its potential in real MRI applications.

83 citations

References
More filters
Journal ArticleDOI
Xiaobo Qu1, Di Guo1, Bende Ning1, Yingkun Hou, Yulan Lin1, Shuhui Cai1, Zhong Chen1 
TL;DR: Simulation results on phantom and in vivo data indicate that the proposed patch-based directional wavelets method outperforms conventional compressed sensing MRI methods in preserving the edges and suppressing the noise.

240 citations


"Image reconstruction of compressed ..." refers background or methods or result in this paper

  • ...Both methods significantly improve the image reconstruction over the predefined basis method (Ning et al., 2013; Qu et al., 2012; Ravishankar and Bresler, 2011)....

    [...]

  • ...For example, the geometric edge of a patch has been applied to train the adaptively sparse representations (Ning et al., 2013; Qu et al., 2012)....

    [...]

  • ...…on K-SVD decomposition, wavelet tree-structured MRI (WaTMRI) (Chen and Huang, 2014), which enforces the sparsity based on quadtree structures of wavelet coefficients, and PBDW (Qu et al., 2012), which is a patch-based directional wavelet transform that makes use of geometric information in patches....

    [...]

  • ...The overlapping factor is defined as: 2c lρ= (Qu et al., 2012), where ρ is the aforementioned patch size....

    [...]

  • ...The image reconstruction may become unsatisfactory when the data are highly undersampled because of the insufficiently sparse representations (Qu et al., 2012; Ravishankar and Bresler, 2011)....

    [...]

Journal ArticleDOI
TL;DR: An image processing scheme based on reordering of its patches is proposed, which enables good recovery of the clean image by applying relatively simple one-dimensional smoothing operations to the reordered set of pixels.
Abstract: We propose an image processing scheme based on reordering of its patches. For a given corrupted image, we extract all patches with overlaps, refer to these as coordinates in high-dimensional space, and order them such that they are chained in the “shortest possible path,” essentially solving the traveling salesman problem. The obtained ordering applied to the corrupted image implies a permutation of the image pixels to what should be a regular signal. This enables us to obtain good recovery of the clean image by applying relatively simple one-dimensional smoothing operations (such as filtering or interpolation) to the reordered set of pixels. We explore the use of the proposed approach to image denoising and inpainting, and show promising results in both cases.

182 citations

Journal ArticleDOI
Xiaobo Qu1, Weiru Zhang1, Di Guo1, Congbo Cai1, Shuhui Cai1, Zhong Chen1 
TL;DR: Simulation results demonstrate that contourlet-based CS-MRI can better reconstruct the curves and edges than traditional wavelet- based methods, especially at low k-space sampling rate.
Abstract: Reducing the acquisition time is important for clinical magnetic resonance imaging (MRI). Compressed sensing has recently emerged as a theoretical foundation for the reconstruction of magnetic resonance images from undersampled k-space measurements, assuming those images are sparse in a certain transform domain. However, most real-world signals are compressible rather than exactly sparse. For example, the commonly used two-dimensional wavelet for compressed sensing MRI (CS-MRI) does not sparsely represent curves and edges. In this article, we introduce a geometric image transform, the contourlet, to overcome this shortage. In addition, the improved redundancy provided by the contourlet can successfully suppress the pseudo-Gibbs phenomenon, a tiresome artefact produced by undersampling of k-space, around the singularities of images. For numerical calculation, a simple but effective iterative thresholding algorithm is employed to solve l 1 norm optimization for CS-MRI. Considering the recovered information ...

156 citations


"Image reconstruction of compressed ..." refers background in this paper

  • ...In CS-MRI, finding an optimally sparse representation for magnetic resonance (MR) images is important because the reconstruction error is usually lower if the image representation is sparser (Qu et al., 2012; Qu et al., 2014; Qu et al., 2010; Ravishankar and Bresler, 2011)....

    [...]

Journal ArticleDOI
TL;DR: An improved image reconstruction method from undersampled k‐space data, low‐dimensional‐structure self‐learning and thresholding (LOST), which utilizes the structure from the underlying image to improve image reconstruction for accelerated coronary MRI acquisitions is presented.
Abstract: An improved image reconstruction method from undersampled k-space data, low-dimensional-structure self-learning and thresholding (LOST), which utilizes the structure from the underlying image is presented. A low-resolution image from the fully sampled k-space center is reconstructed to learn image patches of similar anatomical characteristics. These patches are arranged into "similarity clusters," which are subsequently processed for dealiasing and artifact removal, using underlying low-dimensional properties. The efficacy of the proposed method in scan time reduction was assessed in a pilot coronary MRI study. Initially, in a retrospective study on 10 healthy adult subjects, we evaluated retrospective undersampling and reconstruction using LOST, wavelet-based l(1)-norm minimization, and total variation compressed sensing. Quantitative measures of vessel sharpness and mean square error, and qualitative image scores were used to compare reconstruction for rates of 2, 3, and 4. Subsequently, in a prospective study, coronary MRI data were acquired using these rates, and LOST-reconstructed images were compared with an accelerated data acquisition using uniform undersampling and sensitivity encoding reconstruction. Subjective image quality and sharpness data indicate that LOST outperforms the alternative techniques for all rates. The prospective LOST yields images with superior quality compared with sensitivity encoding or l(1)-minimization compressed sensing. The proposed LOST technique greatly improves image reconstruction for accelerated coronary MRI acquisitions.

150 citations


"Image reconstruction of compressed ..." refers methods in this paper

  • ...…methods have attracted considerable interest in CS-MRI because adaptively sparse representations can be trained with easy manipulations on patches (Akcakaya et al., 2011; Akcakaya et al., 2014; Maggioni et al., 2013; Ning et al., 2013; Qu et al., 2012; Qu et al., 2014; Ravishankar and Bresler,…...

    [...]

Journal ArticleDOI
TL;DR: A novel technique that employs a patch-based 3-D spatiotemporal dictionary for sparse representations of dynamic image sequence in the CS framework that is able to accelerate cardiac cine imaging and outperforms the existing state-of-the-art CS methods at high accelerations.
Abstract: In dynamic cardiac cine magnetic resonance imaging, the spatiotemporal resolution is limited by the low imaging speed. Compressed sensing (CS) theory has been applied to improve the imaging speed and thus the spatiotemporal resolution. In this paper, we propose a novel technique that employs a patch-based 3-D spatiotemporal dictionary for sparse representations of dynamic image sequence in the CS framework. Specifically, the dynamic image sequence is divided into overlapping patches along both the spatial and temporal directions. The dictionary is used to provide flexible sparse expressions for these patches. The underlying optimization problem is solved by variable splitting and the alternating direction method with multiplier. Experimental results based on in vivo cardiac data demonstrate that the proposed method is able to accelerate cardiac cine imaging by a factor up to 8 and outperforms the existing state-of-the-art CS methods at high accelerations. The method is expected to be useful in dynamic imaging with a higher spatiotemporal resolution.

125 citations


"Image reconstruction of compressed ..." refers background in this paper

  • ...…CS-MRI because adaptively sparse representations can be trained with easy manipulations on patches (Akcakaya et al., 2011; Akcakaya et al., 2014; Maggioni et al., 2013; Ning et al., 2013; Qu et al., 2012; Qu et al., 2014; Ravishankar and Bresler, 2011; Wang and Ying, 2014; Yue et al., 4 / 27 2014)....

    [...]