Accelerating compressed sensing reconstruction of subsampled radial k-space data using geometrically-derived density compensation

Exploiting the sparsity of MR signals, Compressed Sensing MR imaging (CS-MRI) is one of the most promising approaches to reconstruct a MR image with good quality from highly under-sampled k-space data. The group sparse method, which exploits additional sparse representation of the spatial group structure, can promote the overall sparsity degree, thereby leading to better reconstruction performance. In this work, an efficient superpixel/group assignment method, simple linear iterative clustering (SLIC), is incorporated to CS-MRI studies. A variable splitting strategy and classic alternating direct method is employed to solve the group sparse problem. The results indicate that the proposed method is capable of achieving significant improvements in reconstruction accuracy when compared with the state-of-the-art reconstruction methods.

Download Full-text

Quantitative Evaluation of Temporal Regularizers in Compressed Sensing Dynamic Contrast Enhanced MRI of the Breast

International Journal of Biomedical Imaging ◽

10.1155/2017/7835749 ◽

2017 ◽

Vol 2017 ◽

pp. 1-11 ◽

Cited By ~ 4

Author(s):

Dong Wang ◽

Lori R. Arlinghaus ◽

Thomas E. Yankeelov ◽

Xiaoping Yang ◽

David S. Smith

Keyword(s):

Compressed Sensing ◽

Volume Fraction ◽

Extracellular Volume ◽

Pharmacokinetic Parameters ◽

Transfer Constant ◽

Dce Mri ◽

Dynamic Contrast Enhanced ◽

Contrast Enhanced ◽

Space Data

Purpose. Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) is used in cancer imaging to probe tumor vascular properties. Compressed sensing (CS) theory makes it possible to recover MR images from randomly undersampled k-space data using nonlinear recovery schemes. The purpose of this paper is to quantitatively evaluate common temporal sparsity-promoting regularizers for CS DCE-MRI of the breast. Methods. We considered five ubiquitous temporal regularizers on 4.5x retrospectively undersampled Cartesian in vivo breast DCE-MRI data: Fourier transform (FT), Haar wavelet transform (WT), total variation (TV), second-order total generalized variation (TGVα2), and nuclear norm (NN). We measured the signal-to-error ratio (SER) of the reconstructed images, the error in tumor mean, and concordance correlation coefficients (CCCs) of the derived pharmacokinetic parameters Ktrans (volume transfer constant) and ve (extravascular-extracellular volume fraction) across a population of random sampling schemes. Results. NN produced the lowest image error (SER: 29.1), while TV/TGVα2 produced the most accurate Ktrans (CCC: 0.974/0.974) and ve (CCC: 0.916/0.917). WT produced the highest image error (SER: 21.8), while FT produced the least accurate Ktrans (CCC: 0.842) and ve (CCC: 0.799). Conclusion. TV/TGVα2 should be used as temporal constraints for CS DCE-MRI of the breast.

Download Full-text

Joint reconstruction framework of compressed sensing and nonlinear parallel imaging for dynamic cardiac magnetic resonance imaging

BMC Medical Imaging ◽

10.1186/s12880-021-00685-2 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Zhanqi Hu ◽

Cailei Zhao ◽

Xia Zhao ◽

Lingyu Kong ◽

Jun Yang ◽

...

Keyword(s):

Compressed Sensing ◽

Parallel Imaging ◽

Imaging Technique ◽

Temporal Variations ◽

Cine Mri ◽

Reconstruction Process ◽

Parallel Imaging Technique ◽

In Vivo Experiments ◽

Space Data

AbstractCompressed Sensing (CS) and parallel imaging are two promising techniques that accelerate the MRI acquisition process. Combining these two techniques is of great interest due to the complementary information used in each. In this study, we proposed a novel reconstruction framework that effectively combined compressed sensing and nonlinear parallel imaging technique for dynamic cardiac imaging. Specifically, the proposed method decouples the reconstruction process into two sequential steps: In the first step, a series of aliased dynamic images were reconstructed from the highly undersampled k-space data using compressed sensing; In the second step, nonlinear parallel imaging technique, i.e. nonlinear GRAPPA, was utilized to reconstruct the original dynamic images from the reconstructed k-space data obtained from the first step. In addition, we also proposed a tailored k-space down-sampling scheme that satisfies both the incoherent undersampling requirement for CS and the structured undersampling requirement for nonlinear parallel imaging. The proposed method was validated using four in vivo experiments of dynamic cardiac cine MRI with retrospective undersampling. Experimental results showed that the proposed method is superior at reducing aliasing artifacts and preserving the spatial details and temporal variations, compared with the competing k-t FOCUSS and k-t FOCUSS with sensitivity encoding methods, with the same numbers of measurements.

Download Full-text

Joint Reconstruction Framework of Compressed Sensing and Nonlinear Parallel Imaging for Dynamic Cardiac Magnetic Resonance Imaging

10.21203/rs.3.rs-731446/v1 ◽

2021 ◽

Author(s):

Zhanqi Hu ◽

Cailei Zhao ◽

Xia Zhao ◽

Lingyu Kong ◽

Jun Yang ◽

...

Keyword(s):

Compressed Sensing ◽

Parallel Imaging ◽

Dynamic Imaging ◽

Cine Mri ◽

Reconstruction Process ◽

Joint Reconstruction ◽

Cardiac Cine ◽

Nonlinear Technique ◽

Space Data

Abstract Compressed Sensing (CS) and parallel imaging are two promising techniques that accelerate the MRI acquisition process. Combining these two techniques is of great interest due to the complementary information used in each. In this study, we propose a new reconstruction framework for dynamic cardiac imaging that takes advantage of both CS-based dynamic imaging and one nonlinear parallel imaging technique. The method decouples the reconstruction process into two sequential steps: use CS to reconstruct a series of aliased dynamic images from the highly undersampled k-space data; use nonlinear GRAPPA method, one nonlinear technique of parallel imaging, to reconstruct the original dynamic images from the k-space data that has been reconstructed by CS. The sampling scheme of the proposed method is designed to simultaneously satisfy the incoherent undersampling requirement for CS and the structured undersampling requirement for nonlinear parallel imaging. Four in vivo experiments of dynamic cardiac cine MRI were carried out with retrospective undersampling to evaluate the performance of the proposed method. Experiments show the proposed method of dynamic cardiac cine MRI is superior at reducing aliasing artifacts and preserving the spatial details and temporal variations, when compared with k-t FOCUSS and k-t FOCUSS with sensitivity encoding, using the same numbers of measurements. The proposed joint reconstruction framework effectively combines the CS method and one nonlinear technique of parallel imaging, and improves the image quality of dynamic cardiac cine MRI reconstruction when comparing to the state-of-the-art methods.

Download Full-text

Compressed Sensing-Based MRI Reconstruction Using Complex Double-Density Dual-Tree DWT

International Journal of Biomedical Imaging ◽

10.1155/2013/907501 ◽

2013 ◽

Vol 2013 ◽

pp. 1-12 ◽

Cited By ~ 20

Author(s):

Zangen Zhu ◽

Khan Wahid ◽

Paul Babyn ◽

Ran Yang

Keyword(s):

Wavelet Transform ◽

Compressed Sensing ◽

Structural Similarity ◽

Sampling Theorem ◽

Acquisition Time ◽

Discrete Wavelet ◽

Signal Acquisition ◽

Mathematical Framework ◽

Reconstruction Method ◽

Space Data

Undersamplingk-space data is an efficient way to speed up the magnetic resonance imaging (MRI) process. As a newly developed mathematical framework of signal sampling and recovery, compressed sensing (CS) allows signal acquisition using fewer samples than what is specified by Nyquist-Shannon sampling theorem whenever the signal is sparse. As a result, CS has great potential in reducing data acquisition time in MRI. In traditional compressed sensing MRI methods, an image is reconstructed by enforcing its sparse representation with respect to a basis, usually wavelet transform or total variation. In this paper, we propose an improved compressed sensing-based reconstruction method using the complex double-density dual-tree discrete wavelet transform. Our experiments demonstrate that this method can reduce aliasing artifacts and achieve higher peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) index.

Download Full-text

Post mortem validation of DSI compressed sensing with optical imaging

10.1101/2021.02.11.430672 ◽

2021 ◽

Author(s):

Robert Jones ◽

Chiara Maffei ◽

Jean Augustinack ◽

Bruce Fischl ◽

Hui Wang ◽

...

Keyword(s):

Compressed Sensing ◽

Ex Vivo ◽

Ground Truth ◽

Acceleration Factor ◽

Training Data ◽

Acquisition Time ◽

Human Brain Tissue ◽

Diffusion Spectrum Imaging ◽

Reconstruction Methods ◽

Space Data

AbstractCompressed sensing (CS) has been used to enhance the feasibility of diffusion spectrum imaging (DSI) by reducing the required acquisition time. CS applied to DSI (CS-DSI) attempts to reconstruct diffusion probability density functions (PDFs) from significantly undersampled q-space data. Dictionary-based CS-DSI using L2-regularized algorithms is an intriguing approach that has demonstrated high fidelity reconstructions, fast computation times and inter-subject generalizability when tested on in vivo data. CS-DSI reconstruction fidelity is typically evaluated using the fully sampled data as ground truth. However, it is difficult to gauge how great an error with respect to the fully sampled PDF we can tolerate, without knowing whether that error also translates to substantial loss of accuracy with respect to the true fiber orientations. Here, we obtain direct measurements of axonal orientations in ex vivo human brain tissue at microscopic resolution with polarization-sensitive optical coherence tomography (PSOCT). We employ dictionary-based CS reconstruction methods to DSI data from the same samples, acquired at high max b-value (40000 s/mm2) and with high spatial resolution. We compare the diffusion orientation estimates from both CS and fully sampled DSI to the ground-truth orientations from PSOCT. This allows us to investigate the conditions under which CS reconstruction preserves the accuracy of diffusion orientation estimates with respect to PSOCT. We find that, for a CS acceleration factor of R=3, CS-DSI preserves the accuracy of the fully sampled DSI data. That acceleration is sufficient to make the acquisition time of DSI comparable to that of state-of-the-art single- or multi-shell acquisitions. We also show that, as the acceleration factor increases further, different CS reconstruction methods degrade in different ways. Finally, we find that the signal-to-noise (SNR) of the training data used to construct the dictionary can have an impact on the accuracy of the CS-DSI, but that there is substantial robustness to loss of SNR in the test data.

Download Full-text

Compressed Sensing MRI Reconstruction from Highly Undersampledk-Space Data Using Nonsubsampled Shearlet Transform Sparsity Prior

Mathematical Problems in Engineering ◽

10.1155/2015/615439 ◽

2015 ◽

Vol 2015 ◽

pp. 1-18 ◽

Cited By ~ 6

Author(s):

Min Yuan ◽

Bingxin Yang ◽

Yide Ma ◽

Jiuwen Zhang ◽

Runpu Zhang ◽

...

Keyword(s):

Compressed Sensing ◽

Directional Sensitivity ◽

Reconstruction Method ◽

Approximation Properties ◽

Mr Images ◽

Shearlet Transform ◽

Nonsubsampled Shearlet Transform ◽

Reconstruction Methods ◽

Mri Reconstruction ◽

Space Data

Compressed sensing has shown great potential in speeding up MR imaging by undersamplingk-space data. Generally sparsity is used as a priori knowledge to improve the quality of reconstructed image. Compressed sensing MR image (CS-MRI) reconstruction methods have employed widely used sparsifying transforms such as wavelet or total variation, which are not preeminent in dealing with MR images containing distributed discontinuities and cannot provide a sufficient sparse representation and the decomposition at any direction. In this paper, we propose a novel CS-MRI reconstruction method from highly undersampledk-space data using nonsubsampled shearlet transform (NSST) sparsity prior. In particular, we have implemented a flexible decomposition with an arbitrary even number of directional subbands at each level using NSST for MR images. The highly directional sensitivity of NSST and its optimal approximation properties lead to improvement in CS-MRI reconstruction applications. The experimental results demonstrate that the proposed method results in the high quality reconstruction, which is highly effective at preserving the intrinsic anisotropic features of MRI meanwhile suppressing the artifacts and added noise. The objective evaluation indices outperform all compared CS-MRI methods. In summary, NSST with even number directional decomposition is very competitive in CS-MRI applications as sparsity prior in terms of performance and computational efficiency.

Download Full-text

Two-Layer Tight Frame Sparsifying Model for Compressed Sensing Magnetic Resonance Imaging

BioMed Research International ◽

10.1155/2016/2860643 ◽

2016 ◽

Vol 2016 ◽

pp. 1-7 ◽

Cited By ~ 1

Author(s):

Shanshan Wang ◽

Jianbo Liu ◽

Xi Peng ◽

Pei Dong ◽

Qiegen Liu ◽

...

Keyword(s):

Magnetic Resonance Imaging ◽

Magnetic Resonance ◽

Compressed Sensing ◽

Adaptive Learning ◽

Tight Frame ◽

Resonance Imaging ◽

Acceleration Rate ◽

Space Data ◽

Mr Reconstruction

Compressed sensing magnetic resonance imaging (CSMRI) employs image sparsity to reconstruct MR images from incoherently undersampledK-space data. Existing CSMRI approaches have exploited analysis transform, synthesis dictionary, and their variants to trigger image sparsity. Nevertheless, the accuracy, efficiency, or acceleration rate of existing CSMRI methods can still be improved due to either lack of adaptability, high complexity of the training, or insufficient sparsity promotion. To properly balance the three factors, this paper proposes a two-layer tight frame sparsifying (TRIMS) model for CSMRI by sparsifying the image with a product of a fixed tight frame and an adaptively learned tight frame. The two-layer sparsifying and adaptive learning nature of TRIMS has enabled accurate MR reconstruction from highly undersampled data with efficiency. To solve the reconstruction problem, a three-level Bregman numerical algorithm is developed. The proposed approach has been compared to three state-of-the-art methods over scanned physical phantom and in vivo MR datasets and encouraging performances have been achieved.

Download Full-text

Reference-Driven Compressed Sensing MR Image Reconstruction Using Deep Convolutional Neural Networks without Pre-Training

Sensors ◽

10.3390/s20010308 ◽

2020 ◽

Vol 20 (1) ◽

pp. 308 ◽

Cited By ~ 2

Author(s):

Di Zhao ◽

Feng Zhao ◽

Yongjin Gan

Keyword(s):

Deep Learning ◽

Image Reconstruction ◽

Compressed Sensing ◽

Training Dataset ◽

Reconstruction Method ◽

Training Procedure ◽

Deep Convolutional Neural Networks ◽

Mr Image ◽

Space Data ◽

Mr Image Reconstruction

Deep learning has proven itself to be able to reduce the scanning time of Magnetic Resonance Imaging (MRI) and to improve the image reconstruction quality since it was introduced into Compressed Sensing MRI (CS-MRI). However, the requirement of using large, high-quality, and patient-based datasets for network training procedures is always a challenge in clinical applications. In this paper, we propose a novel deep learning based compressed sensing MR image reconstruction method that does not require any pre-training procedure or training dataset, thereby largely reducing clinician dependence on patient-based datasets. The proposed method is based on the Deep Image Prior (DIP) framework and uses a high-resolution reference MR image as the input of the convolutional neural network in order to induce the structural prior in the learning procedure. This reference-driven strategy improves the efficiency and effect of network learning. We then add the k-space data correction step to enforce the consistency of the k-space data with the measurements, which further improve the image reconstruction accuracy. Experiments on in vivo MR datasets showed that the proposed method can achieve more accurate reconstruction results from undersampled k-space data.

Download Full-text

Compressed-Sensing Magnetic Resonance Image Reconstruction Using an Iterative Convolutional Neural Network Approach

Applied Sciences ◽

10.3390/app10061902 ◽

2020 ◽

Vol 10 (6) ◽

pp. 1902

Author(s):

Fumio Hashimoto ◽

Kibo Ote ◽

Takenori Oida ◽

Atsushi Teramoto ◽

Yasuomi Ouchi

Keyword(s):

Magnetic Resonance ◽

Image Quality ◽

Compressed Sensing ◽

Signal To Noise Ratio ◽

A Priori ◽

Similarity Index ◽

Structural Similarity ◽

Neural Network Approach ◽

Priori Information ◽

Space Data

Convolutional neural networks (CNNs) demonstrate excellent performance when employed to reconstruct the images obtained by compressed-sensing magnetic resonance imaging (CS-MRI). Our study aimed to enhance image quality by developing a novel iterative reconstruction approach that utilizes image-based CNNs and k-space correction to preserve original k-space data. In the proposed method, CNNs represent a priori information concerning image spaces. First, the CNNs are trained to map zero-filling images onto corresponding full-sampled images. Then, they recover the zero-filled part of the k-space data. Subsequently, k-space corrections, which involve the replacement of unfilled regions by original k-space data, are implemented to preserve the original k-space data. The above-mentioned processes are used iteratively. The performance of the proposed method was validated using a T2-weighted brain-image dataset, and experiments were conducted with several sampling masks. Finally, the proposed method was compared with other noniterative approaches to demonstrate its effectiveness. The aliasing artifacts in the reconstructed images obtained using the proposed approach were reduced compared to those using other state-of-the-art techniques. In addition, the quantitative results obtained in the form of the peak signal-to-noise ratio and structural similarity index demonstrated the effectiveness of the proposed method. The proposed CS-MRI method enhanced MR image quality with high-throughput examinations.

Download Full-text