☆ 4.7 Article

Radial magnetic resonance image reconstruction with a deep unrolled projected fast iterative soft-thresholding network

COMPUTERS IN BIOLOGY AND MEDICINE (2024)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Artificial Intelligence

A Sparse Model-Inspired Deep Thresholding Network for Exponential Signal Reconstruction--Application in Fast Biological Spectroscopy

Zi Wang et al.

Summary: In this work, we propose a DL architecture called MoDern for spectra reconstruction from undersampled data by combining the advantages of the sparse model-based optimization method and data-driven DL. Extensive experiments on synthetic and biological data demonstrate that MoDern achieves more robust, high-fidelity, and ultrafast reconstruction compared to existing methods. Remarkably, MoDern has a small number of network parameters and generalizes well to biological data in various scenarios. Furthermore, we extend MoDern to a user-friendly cloud computing platform (XCloud-MoDern), contributing a promising strategy for the further development of biological applications.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Exponential Signal Reconstruction With Deep Hankel Matrix Factorization

Yihui Huang et al.

Summary: Exponential function is a common form of temporal signals, and acquiring this signal quickly is an important problem in signal processing. In this study, we propose a deep learning method that mimics the iterative process in the model-based exponentials' reconstruction method, and the neural network structure is designed accordingly. Experimental results demonstrate that this method achieves more accurate and reliable data acquisition and signal reconstruction compared to other methods.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

Uncertainty-aware physics-driven deep learning network for free-breathing liver fat and R2 quantification using self-gated stack-of-radial MRI

Shu-Fu Shih et al.

Summary: Purpose: To develop a deep learning-based method for rapid liver proton-density fat fraction (PDFF) and R-2* quantification with built-in uncertainty estimation using self-gated free-breathing stack-of-radial MRI. Methods: This work developed an uncertainty-aware physics-driven deep learning network (UP-Net) to (1) suppress radial streaking artifacts because of undersampling after self-gating, (2) calculate accurate quantitative maps, and (3) provide pixel-wise uncertainty maps. UP-Net was trained and tested using free-breathing multi-echo stack-of-radial MRI data from 105 subjects. Results: UP-Net rapidly calculates accurate liver PDFF and R-2* maps from self-gated free-breathing stack-of-radial MRI, and the pixel-wise uncertainty maps from UP-Net predict quantification errors in the liver.

MAGNETIC RESONANCE IN MEDICINE (2023)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

HFIST-Net: High-throughput fast iterative shrinkage thresholding network for accelerating MR image reconstruction

Chenghu Geng et al.

Summary: This paper proposes a High-Throughput Fast Iterative Shrinkage Thresholding Network (HFIST-Net) for reconstructing MR images from sparse measurements. The results show that this method can reconstruct more accurate MR image details from highly undersampled k-space data while maintaining fast computational speed.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2023)

添加到收藏夹

Article Biology

Undersampled MRI reconstruction based on spectral graph wavelet transform

Jun Lang et al.

Summary: This paper introduces a spectral graph wavelet transform (SGWT) for sparsely representing magnetic resonance images. The SGWT extends the traditional wavelet transform to signals defined on a weighted graph, using only the connectivity information encoded in the edge weights. A fast computing algorithm based on Chebyshev polynomials is presented for this SGWT. The proposed method out-performs several state-of-the-art sparsify transforms in terms of suppressing artifacts and achieving lower reconstruction errors.

COMPUTERS IN BIOLOGY AND MEDICINE (2023)

添加到收藏夹

Article Engineering, Electrical & Electronic

Physics-Driven Synthetic Data Learning for Biomedical Magnetic Resonance: The imaging physics-based data synthesis paradigm for artificial intelligence

Qinqin Yang et al.

Summary: Deep learning has driven innovation in computational imaging, but it often lacks sufficient training data. This article reviews imaging physics-based data synthesis (IPADS), an emerging paradigm that can provide large amounts of training data in biomedical magnetic resonance (MR), even without or with minimal real data. IPADS generates signals based on the physical law of MR, making learning more scalable, explainable, and privacy-preserving. The article discusses key components of IPADS learning, including signal generation models, basic DL network structures, enhanced data generation, and learning methods. Representative applications in fast imaging, ultrafast signal reconstruction, and accurate parameter quantification demonstrate the great potential of IPADS. Finally, open questions and future work are discussed.

IEEE SIGNAL PROCESSING MAGAZINE (2023)

添加到收藏夹

Article Biochemical Research Methods

A convergence analysis for projected fast iterative soft-thresholding algorithm under radial sampling MRI

Biao Qu et al.

Summary: Radial sampling is a fast MRI technique that can be further accelerated with undersampling. This study derived a theoretical convergence condition for a sparse reconstruction model and proposed an optimal step size based on this condition, allowing for fast convergence in radial MRI.

JOURNAL OF MAGNETIC RESONANCE (2023)

添加到收藏夹

Article Biophysics

4D Golden-Angle Radial MRI at Subsecond Temporal Resolution

Li Feng

Summary: This paper proposes a highly accelerated 4D dynamic MRI framework with subsecond temporal resolution to reduce intraframe motion blurring. The method combines radial sampling and tailored reconstruction. The proposed approach enables highly-accelerated 4D dynamic imaging at subsecond temporal resolution, and it has been successfully tested in abdominal motion phantom and dynamic contrast-enhanced MRI.

NMR IN BIOMEDICINE (2023)

添加到收藏夹

Article Biophysics

GRASPNET: Fast spatiotemporal deep learning reconstruction of golden-angle radial data for free-breathing dynamic contrast-enhanced magnetic resonance imaging

Ramin Jafari et al.

Summary: The study developed a deep learning technique called GRASPnet for fast reconstruction of dynamic contrast-enhanced MRI. GRASPnet reduced the reconstruction time to a few seconds using 2D or 3D convolutional kernels and performed well in quantitative analysis.

NMR IN BIOMEDICINE (2023)

添加到收藏夹

Article Engineering, Biomedical

Spatiotemporal Flexible Sparse Reconstruction for Rapid Dynamic Contrast-Enhanced MRI

Yuhan Hu et al.

Summary: In this paper, a new parallel CS reconstruction model for DCE-MRI is proposed to improve reconstruction quality by adjusting the importance of time and space sparsity. The results demonstrate that the proposed method achieves the lowest reconstruction error and highest image structural similarity at high acceleration rates.

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING (2022)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

NC-PDNet: A Density-Compensated Unrolled Network for 2D and 3D Non-Cartesian MRI Reconstruction

Zaccharie Ramzi et al.

Summary: This study explores the potential of deep learning in non-Cartesian acquisition settings and validates the performance of the NC-PDNet, a density-compensated unrolled neural network. The experiments demonstrate that the NC-PDNet outperforms baseline models both visually and quantitatively in various settings.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2022)

添加到收藏夹

Article Biology

ReconResNet: Regularised residual learning for MR image reconstruction of Undersampled Cartesian and Radial data

Soumick Chatterjee et al.

Summary: This study proposes a deep learning-based framework for MR image reconstruction, which can effectively reconstruct highly undersampled images without artifact. The framework shows robustness to different sampling patterns and preserves brain pathology during training.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

添加到收藏夹

Article Biology

CSR-PERT: Joint framework for MRI and HARDI data reconstruction using perturbed radial trajectory estimated from compressively sensed measurements

Ashutosh Vaish et al.

Summary: Radial sampling is an important signal acquisition strategy in MRI due to its better motion artifact immunity and less severe aliasing compared to Cartesian sampling. However, gradient delays lead to miscentered radial trajectories, degrading image reconstruction quality. In this study, a joint framework called CSR-PERT is proposed to estimate and utilize these perturbed radial trajectories for image reconstruction from compressively sensed MRI and HARDI data. Experimental results demonstrate that the proposed method performs better than existing state-of-the-art methods at high acceleration factors and exhibits robustness in various scenarios.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

添加到收藏夹

Article Biology

HIWDNet: A hybrid image-wavelet domain network for fast magnetic resonance image reconstruction

Chuan Tong et al.

Summary: In this paper, a hybrid image-wavelet domain reconstruction network (HIWDNet) is proposed for fast MRI reconstruction by integrating different modules for structure reconstruction and artifact removal in the image domain and wavelet domain. Experimental results demonstrate that HIWDNet achieves better reconstruction performance compared to other methods on different datasets.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

添加到收藏夹

Article Biophysics

Rapid reconstruction of highly undersampled, non-Cartesian real-time cinek-space data using a perceptual complex neural network (PCNN)

Daming Shen et al.

Summary: The study developed a neural network for rapid reconstruction of real-time cardiac MRI data, faster than GPU-accelerated CS reconstruction, without significant loss in image quality or accuracy in LV functional parameters.

NMR IN BIOMEDICINE (2021)

添加到收藏夹

Article Biology

MR image reconstruction using densely connected residual convolutional networks

Amir Aghabiglou et al.

Summary: MRI image reconstruction techniques based on deep learning have shown great potential in reducing MRI acquisition time and improving performance compared to analytical methods. Despite challenges in training large networks, novel methodologies have enhanced the capability for real-time clinical-grade MR image reconstruction. The efficiency of deep networks can be improved by using short connections between layers, with studies showing significant improvements in reconstruction performance by introducing densely connected residual blocks in MRI reconstruction settings.

COMPUTERS IN BIOLOGY AND MEDICINE (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

FISTA-Net: Learning a Fast Iterative Shrinkage Thresholding Network for Inverse Problems in Imaging

Jinxi Xiang et al.

Summary: FISTA-Net is a model-based deep learning network that optimizes parameters for different imaging tasks without tuning, outperforming existing methods and exhibiting good generalization ability under different noise levels.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A guaranteed convergence analysis for the projected fast iterative soft-thresholding algorithm in parallel MRI

Xinlin Zhang et al.

Summary: Sparse sampling and parallel imaging techniques are effective approaches to alleviate the lengthy MRI data acquisition problem. Promising data recoveries can be obtained from a few MRI samples with the help of sparse reconstruction models. In this work, the guaranteed convergence analysis of the parallel imaging version pFISTA for solving SENSE and SPIRiT reconstruction models is provided, along with recommended step size values for fast and promising reconstructions.

MEDICAL IMAGE ANALYSIS (2021)

添加到收藏夹

Article Engineering, Biomedical

Ground-truth-free deep learning for artefacts reduction in 2D radial cardiac cine MRI using a synthetically generated dataset

D. Chen et al.

Summary: By leveraging a transfer-learning approach using 2D spatio-temporal profiles as training data, a CNN method can be successfully applied to cardiac cine MRI image reconstruction, showing comparable or even superior performance compared to CNNs trained on actual cine MR images. This method effectively overcomes challenges related to data quality and quantity limitations in fast dynamic processes.

PHYSICS IN MEDICINE AND BIOLOGY (2021)

添加到收藏夹

Article Chemistry, Multidisciplinary

Accelerated Nuclear Magnetic Resonance Spectroscopy with Deep Learning

Xiaobo Qu et al.

ANGEWANDTE CHEMIE-INTERNATIONAL EDITION (2020)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

k-Space Deep Learning for Accelerated MRI

Yoseob Han et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2020)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

Reconstruction of undersampled 3D non-Cartesian image-based navigators for coronary MRA using an unrolled deep learning model

Mario O. Malave et al.

MAGNETIC RESONANCE IN MEDICINE (2020)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Accelerating Non-Cartesian MRI Reconstruction Convergence Using k-Space Preconditioning

Frank Ong et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Accelerating Cartesian MRI by domain-transform manifold learning in phase-encoding direction

Taejoon Eo et al.

MEDICAL IMAGE ANALYSIS (2020)

添加到收藏夹

Article Biochemical Research Methods

pFISTA-SENSE-ResNet for parallel MRI reconstruction

Tieyuan Lu et al.

JOURNAL OF MAGNETIC RESONANCE (2020)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

Real-time cardiovascular MR with spatio-temporal artifact suppression using deep learning-proof of concept in congenital heart disease

Andreas Hauptmann et al.

MAGNETIC RESONANCE IN MEDICINE (2019)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

Rapid dynamic contrast-enhanced MRI for small animals at 7T using 3D ultra-short echo time and golden-angle radial sparse parallel MRI

Jin Zhang et al.

MAGNETIC RESONANCE IN MEDICINE (2019)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

Technical Note: Sequential combination of parallel imaging and dynamic artificial sparsity framework for rapid free-breathing golden-angle radial dynamic MRI: K-T ARTS-GROWL

Zhifeng Chen et al.

MEDICAL PHYSICS (2018)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

An improved non-Cartesian partially parallel imaging by exploiting artificial sparsity

Zhifeng Chen et al.

MAGNETIC RESONANCE IN MEDICINE (2017)

添加到收藏夹

Article Mathematical & Computational Biology

A Feasibility Study of Geometric-Decomposition Coil Compression in MRI Radial Acquisitions

Jing Wang et al.

COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE (2017)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Projected Iterative Soft-Thresholding Algorithm for Tight Frames in Compressed Sensing Magnetic Resonance Imaging

Yunsong Liu et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2016)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Augmented Lagrangian with Variable Splitting for Faster Non-Cartesian L1-SPIRiT MR Image Reconstruction

Daniel S. Weller et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2014)

添加到收藏夹

Review Radiology, Nuclear Medicine & Medical Imaging

Non-Cartesian Parallel Imaging Reconstruction

Katherine L. Wright et al.

JOURNAL OF MAGNETIC RESONANCE IMAGING (2014)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

Golden-Angle Radial Sparse Parallel MRI: Combination of Compressed Sensing, Parallel Imaging, and Golden-Angle Radial Sampling for Fast and Flexible Dynamic Volumetric MRI

Li Feng et al.

MAGNETIC RESONANCE IN MEDICINE (2014)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

ESPIRiT-An Eigenvalue Approach to Autocalibrating Parallel MRI: Where SENSE Meets GRAPPA

Martin Uecker et al.

MAGNETIC RESONANCE IN MEDICINE (2014)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

GRAPPA Operator for Wider Radial Bands (GROWL) with Optimally Regularized Self-Calibration

Wei Lin et al.

MAGNETIC RESONANCE IN MEDICINE (2010)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems

Amir Beck et al.

SIAM JOURNAL ON IMAGING SCIENCES (2009)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

A software channel compression technique for faster reconstruction with many channels

Feng Huang et al.

MAGNETIC RESONANCE IMAGING (2008)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

Sparse MRI: The application of compressed sensing for rapid MR imaging

Michael Lustig et al.

MAGNETIC RESONANCE IN MEDICINE (2007)

添加到收藏夹

Article Biochemical Research Methods

On NUFFT-based gridding for non-Cartesian MRI

Jeffrey A. Fessler

JOURNAL OF MAGNETIC RESONANCE (2007)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.