1
|
Wang G, Zhang X, Guo L. Magnetic resonance image reconstruction based on image decomposition constrained by total variation and tight frame. J Appl Clin Med Phys 2024; 25:e14402. [PMID: 38783594 PMCID: PMC11302825 DOI: 10.1002/acm2.14402] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/28/2023] [Revised: 03/30/2024] [Accepted: 04/25/2024] [Indexed: 05/25/2024] Open
Abstract
OBJECTIVES Magnetic resonance imaging (MRI) is a commonly used tool in clinical medicine, but it suffers from the disadvantage of slow imaging speed. To address this, we propose a novel MRI reconstruction algorithm based on image decomposition to realize accurate image reconstruction with undersampled k-space data. METHODS In our algorithm, the MR images to be recovered are split into cartoon and texture components utilizing image decomposition theory. Different sparse transform constraints are applied to each component based on their morphological structure characteristics. The total variation transform constraint is used for the smooth cartoon component, while the L0 norm constraint of tight frame redundant transform is used for the oscillatory texture component. Finally, an alternating iterative minimization approach is adopted to complete the reconstruction. RESULTS Numerous numerical experiments are conducted on several MR images and the results consistently show that, compared with the existing classical compressed sensing algorithm, our algorithm significantly improves the peak signal-to-noise ratio of the reconstructed images and preserves more image details. CONCLUSIONS Our algorithm harnesses the sparse characteristics of different image components to reconstruct MR images accurately with highly undersampled data. It can greatly accelerate MRI speed and be extended to other imaging reconstruction fields.
Collapse
Affiliation(s)
- Guohe Wang
- School of Medical TechnologyTianjin Medical UniversityTianjinChina
| | - Xi Zhang
- School of Medical TechnologyTianjin Medical UniversityTianjinChina
| | - Li Guo
- School of Medical TechnologyTianjin Medical UniversityTianjinChina
| |
Collapse
|
2
|
Ekanayake M, Pawar K, Harandi M, Egan G, Chen Z. McSTRA: A multi-branch cascaded swin transformer for point spread function-guided robust MRI reconstruction. Comput Biol Med 2024; 168:107775. [PMID: 38061154 DOI: 10.1016/j.compbiomed.2023.107775] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2023] [Revised: 11/23/2023] [Accepted: 11/27/2023] [Indexed: 01/10/2024]
Abstract
Deep learning MRI reconstruction methods are often based on Convolutional neural network (CNN) models; however, they are limited in capturing global correlations among image features due to the intrinsic locality of the convolution operation. Conversely, the recent vision transformer models (ViT) are capable of capturing global correlations by applying self-attention operations on image patches. Nevertheless, the existing transformer models for MRI reconstruction rarely leverage the physics of MRI. In this paper, we propose a novel physics-based transformer model titled, the Multi-branch Cascaded Swin Transformers (McSTRA) for robust MRI reconstruction. McSTRA combines several interconnected MRI physics-related concepts with the Swin transformers: it exploits global MRI features via the shifted window self-attention mechanism; it extracts MRI features belonging to different spectral components via a multi-branch setup; it iterates between intermediate de-aliasing and data consistency via a cascaded network with intermediate loss computations; furthermore, we propose a point spread function-guided positional embedding generation mechanism for the Swin transformers which exploit the spread of the aliasing artifacts for effective reconstruction. With the combination of all these components, McSTRA outperforms the state-of-the-art methods while demonstrating robustness in adversarial conditions such as higher accelerations, noisy data, different undersampling protocols, out-of-distribution data, and abnormalities in anatomy.
Collapse
Affiliation(s)
- Mevan Ekanayake
- Monash Biomedical Imaging, Monash University, Australia; Department of Electrical and Computer Systems Engineering, Monash University, Australia.
| | - Kamlesh Pawar
- Monash Biomedical Imaging, Monash University, Australia
| | - Mehrtash Harandi
- Department of Electrical and Computer Systems Engineering, Monash University, Australia
| | - Gary Egan
- Monash Biomedical Imaging, Monash University, Australia; School of Psychological Sciences, Monash University, Australia
| | - Zhaolin Chen
- Monash Biomedical Imaging, Monash University, Australia; Department of Data Science and AI, Monash University, Australia
| |
Collapse
|
3
|
Yi Q, Fang F, Zhang G, Zeng T. Frequency Learning via Multi-Scale Fourier Transformer for MRI Reconstruction. IEEE J Biomed Health Inform 2023; 27:5506-5517. [PMID: 37656654 DOI: 10.1109/jbhi.2023.3311189] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/03/2023]
Abstract
Since Magnetic Resonance Imaging (MRI) requires a long acquisition time, various methods were proposed to reduce the time, but they ignored the frequency information and non-local similarity, so that they failed to reconstruct images with a clear structure. In this article, we propose Frequency Learning via Multi-scale Fourier Transformer for MRI Reconstruction (FMTNet), which focuses on repairing the low-frequency and high-frequency information. Specifically, FMTNet is composed of a high-frequency learning branch (HFLB) and a low-frequency learning branch (LFLB). Meanwhile, we propose a Multi-scale Fourier Transformer (MFT) as the basic module to learn the non-local information. Unlike normal Transformers, MFT adopts Fourier convolution to replace self-attention to efficiently learn global information. Moreover, we further introduce a multi-scale learning and cross-scale linear fusion strategy in MFT to interact information between features of different scales and strengthen the representation of features. Compared with normal Transformers, the proposed MFT occupies fewer computing resources. Based on MFT, we design a Residual Multi-scale Fourier Transformer module as the main component of HFLB and LFLB. We conduct several experiments under different acceleration rates and different sampling patterns on different datasets, and the experiment results show that our method is superior to the previous state-of-the-art method.
Collapse
|
4
|
Wang S, Lv J, He Z, Liang D, Chen Y, Zhang M, Liu Q. Denoising auto-encoding priors in undecimated wavelet domain for MR image reconstruction. Neurocomputing 2021. [DOI: 10.1016/j.neucom.2020.09.086] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
|
5
|
Sun L, Wu Y, Fan Z, Ding X, Huang Y, Paisley J. A deep error correction network for compressed sensing MRI. BMC Biomed Eng 2020; 2:4. [PMID: 32903379 PMCID: PMC7422575 DOI: 10.1186/s42490-020-0037-5] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2019] [Accepted: 01/30/2020] [Indexed: 01/10/2023] Open
Abstract
BACKGROUND CS-MRI (compressed sensing for magnetic resonance imaging) exploits image sparsity properties to reconstruct MRI from very few Fourier k-space measurements. Due to imperfect modelings in the inverse imaging, state-of-the-art CS-MRI methods tend to leave structural reconstruction errors. Compensating such errors in the reconstruction could help further improve the reconstruction quality. RESULTS In this work, we propose a DECN (deep error correction network) for CS-MRI. The DECN model consists of three parts, which we refer to as modules: a guide, or template, module, an error correction module, and a data fidelity module. Existing CS-MRI algorithms can serve as the template module for guiding the reconstruction. Using this template as a guide, the error correction module learns a CNN (convolutional neural network) to map the k-space data in a way that adjusts for the reconstruction error of the template image. We propose a deep error correction network. Our experimental results show the proposed DECN CS-MRI reconstruction framework can considerably improve upon existing inversion algorithms by supplementing with an error-correcting CNN. CONCLUSIONS In the proposed a deep error correction framework, any off-the-shelf CS-MRI algorithm can be used as template generation. Then a deep neural network is used to compensate reconstruction errors. The promising experimental results validate the effectiveness and utility of the proposed framework.
Collapse
Affiliation(s)
- Liyan Sun
- Fujian Key Laboratory of Sensing and Computing for Smart City, Xiamen University, Xiamen, China
| | - Yawen Wu
- Fujian Key Laboratory of Sensing and Computing for Smart City, Xiamen University, Xiamen, China
| | - Zhiwen Fan
- Fujian Key Laboratory of Sensing and Computing for Smart City, Xiamen University, Xiamen, China
| | - Xinghao Ding
- Fujian Key Laboratory of Sensing and Computing for Smart City, Xiamen University, Xiamen, China
| | - Yue Huang
- Fujian Key Laboratory of Sensing and Computing for Smart City, Xiamen University, Xiamen, China
| | - John Paisley
- Department of Electrical Engineering, Columbia University, New York, USA
| |
Collapse
|
6
|
Luo Y, Ling J, Gong Y, Long J. A cosparse analysis model with combined redundant systems for MRI reconstruction. Med Phys 2019; 47:457-466. [PMID: 31742722 DOI: 10.1002/mp.13931] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2018] [Revised: 10/31/2019] [Accepted: 11/06/2019] [Indexed: 11/07/2022] Open
Abstract
PURPOSE Magnetic resonance imaging (MRI) is widely used due to its noninvasive and nonionizing properties. However, MRI requires a long scanning time. In this paper, our goal is to reconstruct a high-quality MR image from its sampled k-space data to accelerate the data acquisition in MRI. METHODS We propose a cosparse analysis model with combined redundant systems to fully exploit the sparsity of MR images. Two fixed redundant systems are used to characterize different structures, namely, the wavelet tight frame and Gabor frame. An alternating iteration scheme is used for reconstruction with simple implementation and good performance. RESULTS The proposed method is tested on two MR images under three sampling patterns with sampling ratios ranging from 10% to 60%. The results show that the proposed method outperforms other state-of-the-art MRI reconstruction methods in terms of both subjective visual quality and objective quantitative measurement. For instance, for brain images under random sampling with a ratio of 10%, compared to the other three methods, the proposed method improves the peak signal-to-noise ratio (PSNR) by more than 9 dB. CONCLUSIONS To better characterize different sparsities of different structures of MRI, a cosparse analysis model combining the wavelet tight frame and Gabor frame is proposed. A partial ℓ 2 norm regularization is leveraged to obtain the optimal solution in a lower dimension. Compared to other state-of-the-art MRI reconstruction methods, the proposed method improves the reconstruction quality of MRI, especially highly undersampled MRI.
Collapse
Affiliation(s)
- Yu Luo
- School of Computer Science, Guangdong University of Technology, Guangzhou, 510006, China
| | - Jie Ling
- School of Computer Science, Guangdong University of Technology, Guangzhou, 510006, China
| | - Yi Gong
- School of Computer Science, Guangdong University of Technology, Guangzhou, 510006, China
| | - Jinyi Long
- College of Information Science and Technology, Jinan University, Guangzhou, 510632, China
| |
Collapse
|
7
|
Sun L, Fan Z, Ding X, Cai C, Huang Y, Paisley J. A divide-and-conquer approach to compressed sensing MRI. Magn Reson Imaging 2019; 63:37-48. [DOI: 10.1016/j.mri.2019.06.014] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2018] [Revised: 06/19/2019] [Accepted: 06/22/2019] [Indexed: 10/26/2022]
|
8
|
Frequency-splitting dynamic MRI reconstruction using multi-scale 3D convolutional sparse coding and automatic parameter selection. Med Image Anal 2019; 53:179-196. [DOI: 10.1016/j.media.2019.02.001] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2018] [Revised: 12/08/2018] [Accepted: 02/01/2019] [Indexed: 10/27/2022]
|
9
|
Meng J, Liu C, Kim J, Kim C, Song L. Compressed Sensing With a Gaussian Scale Mixture Model for Limited View Photoacoustic Computed Tomography In Vivo. Technol Cancer Res Treat 2018; 17:1533033818808222. [PMID: 30373467 PMCID: PMC6207971 DOI: 10.1177/1533033818808222] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022] Open
Abstract
Photoacoustic computed tomography using an ultrasonic array is an attractive noninvasive imaging modality for many biomedical applications. However, the potentially long data acquisition time of array-based photoacoustic computed tomography—usually due to the required time-multiplexing for multiple laser pulses—decreases its applicability for rapid disease diagnoses and the successive monitoring of physiological functions. Compressed sensing is used to improve the imaging speed of photoacoustic computed tomography by decreasing the amount of acquired data; however, the imaging quality can be limited when fewer measurements are used, as traditional compressed sensing considers only the sparsity of the signals in the imaging process. In this work, an advanced compressed sensing reconstruction framework with a Wiener linear estimation-based Gaussian scale mixture model was developed for limited view photoacoustic computed tomography. In this method, the structure dependencies of signals in the wavelet domain were incorporated into the imaging framework through the Gaussian scale mixture model, and an operator based on the Wiener linear estimation was designed to filter the reconstruction artifacts. Phantom and human forearm imaging were performed to verify the developed method. The results demonstrated that compressed sensing with a Wiener linear estimation-based Gaussian scale mixture model more effectively suppressed the reconstruction artifacts of sparse-sampling photoacoustic computed tomography and recovered photoacoustic images with a higher contrast-to-noise ratio and edge resolution than the traditional compressed sensing method. This work may promote the development of low-cost photoacoustic computed tomography techniques with rapid data acquisition and enhance the performance of photoacoustic computed tomography in various biomedical studies.
Collapse
Affiliation(s)
- Jing Meng
- 1 School of Information Science and Engineering, Qufu Normal University, Rizhao, China
| | - Chengbo Liu
- 2 Institute of Biomedical and Health Engineering, Chinese Academy and Sciences, Shenzhen, China
| | - Jeesu Kim
- 3 Departments of Electrical Engineering and Creative IT Engineering, Pohang University of Science and Technology, Pohang, South Korea
| | - Chulhong Kim
- 3 Departments of Electrical Engineering and Creative IT Engineering, Pohang University of Science and Technology, Pohang, South Korea
| | - Liang Song
- 2 Institute of Biomedical and Health Engineering, Chinese Academy and Sciences, Shenzhen, China
| |
Collapse
|
10
|
Lai Z, Qu X, Lu H, Peng X, Guo D, Yang Y, Guo G, Chen Z. Sparse MRI reconstruction using multi-contrast image guided graph representation. Magn Reson Imaging 2017; 43:95-104. [DOI: 10.1016/j.mri.2017.07.009] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2017] [Revised: 05/22/2017] [Accepted: 07/13/2017] [Indexed: 10/19/2022]
|
11
|
High-resolution vessel wall MRI for the evaluation of intracranial atherosclerotic disease. Neuroradiology 2017; 59:1193-1202. [PMID: 28942481 DOI: 10.1007/s00234-017-1925-9] [Citation(s) in RCA: 46] [Impact Index Per Article: 6.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2017] [Accepted: 09/11/2017] [Indexed: 01/23/2023]
Abstract
High-resolution vessel wall MRI (vwMRI) of the intracranial arteries is an emerging diagnostic imaging technique with the goal of evaluating vascular pathology. vwMRI sequences have high spatial resolution and directly image the vessel wall by suppressing blood signal. With vwMRI, it is possible to identify distinct morphologic and enhancement patterns of atherosclerosis that can provide important information about stroke etiology and recurrence risk. We present a review of vwMRI research in relation to intracranial atherosclerosis, with a focus on the relationship between ischemic stroke and atherosclerotic plaque T1 post-contrast enhancement or plaque/vessel wall morphology. The goal of this review is to provide readers with the most current understanding of the reliability, incidence, and importance of specific vwMRI findings in intracranial atherosclerosis, to guide their interpretation of vwMRI research, and help inform clinical interpretation of vwMRI. We will also provide a translational perspective on the existing vwMRI literature and insight into future vwMRI research questions and objectives. With increased use of high field strength MRI, powerful gradients, and improved pulse sequences, vwMRI will become standard-of-care in the diagnosis and prognosis of patients with cerebrovascular disease, making a firm grasp of its strengths and weakness important for neuroimagers.
Collapse
|
12
|
Fast Compressed Sensing MRI Based on Complex Double-Density Dual-Tree Discrete Wavelet Transform. Int J Biomed Imaging 2017; 2017:9604178. [PMID: 28487724 PMCID: PMC5401759 DOI: 10.1155/2017/9604178] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2016] [Accepted: 02/07/2017] [Indexed: 11/18/2022] Open
Abstract
Compressed sensing (CS) has been applied to accelerate magnetic resonance imaging (MRI) for many years. Due to the lack of translation invariance of the wavelet basis, undersampled MRI reconstruction based on discrete wavelet transform may result in serious artifacts. In this paper, we propose a CS-based reconstruction scheme, which combines complex double-density dual-tree discrete wavelet transform (CDDDT-DWT) with fast iterative shrinkage/soft thresholding algorithm (FISTA) to efficiently reduce such visual artifacts. The CDDDT-DWT has the characteristics of shift invariance, high degree, and a good directional selectivity. In addition, FISTA has an excellent convergence rate, and the design of FISTA is simple. Compared with conventional CS-based reconstruction methods, the experimental results demonstrate that this novel approach achieves higher peak signal-to-noise ratio (PSNR), larger signal-to-noise ratio (SNR), better structural similarity index (SSIM), and lower relative error.
Collapse
|
13
|
de Havenon A, Chung L, Park M, Mossa-Basha M. Intracranial vessel wall MRI: a review of current indications and future applications. ACTA ACUST UNITED AC 2016. [DOI: 10.1186/s40809-016-0021-6] [Citation(s) in RCA: 23] [Impact Index Per Article: 2.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
|
14
|
Alexander MD, Yuan C, Rutman A, Tirschwell DL, Palagallo G, Gandhi D, Sekhar LN, Mossa-Basha M. High-resolution intracranial vessel wall imaging: imaging beyond the lumen. J Neurol Neurosurg Psychiatry 2016; 87:589-97. [PMID: 26746187 PMCID: PMC5504758 DOI: 10.1136/jnnp-2015-312020] [Citation(s) in RCA: 94] [Impact Index Per Article: 11.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/13/2015] [Accepted: 11/23/2015] [Indexed: 01/21/2023]
Abstract
Accurate and timely diagnosis of intracranial vasculopathies is important due to significant risk of morbidity with delayed and/or incorrect diagnosis both from the disease process as well as inappropriate therapies. Conventional vascular imaging techniques for analysis of intracranial vascular disease provide limited information since they only identify changes to the vessel lumen. New advanced MR intracranial vessel wall imaging (IVW) techniques can allow direct characterisation of the vessel wall. These techniques can advance diagnostic accuracy and may potentially improve patient outcomes by better guided treatment decisions in comparison to previously available invasive and non-invasive techniques. While neuroradiological expertise is invaluable in accurate examination interpretation, clinician familiarity with the application and findings of the various vasculopathies on IVW can help guide diagnostic and therapeutic decision-making. This review article provides a brief overview of the technical aspects of IVW and discusses the IVW findings of various intracranial vasculopathies, differentiating characteristics and indications for when this technique can be beneficial in patient management.
Collapse
Affiliation(s)
| | - Chun Yuan
- Department of Radiology, University of Washington, Seattle, Washington, USA
| | - Aaron Rutman
- Department of Radiology, University of Washington, Seattle, Washington, USA
| | - David L Tirschwell
- Department of Neurology, University of Washington, Seattle, Washington, USA
| | - Gerald Palagallo
- Department of Radiology, University of Washington, Seattle, Washington, USA
| | - Dheeraj Gandhi
- Department of Radiology, Neurology and Neurosurgery, University of Maryland, Baltimore, Maryland, USA
| | - Laligam N Sekhar
- Department of Neurological Surgery, University of Washington, Seattle, Washington, USA
| | - Mahmud Mossa-Basha
- Department of Radiology, University of Washington, Seattle, Washington, USA
| |
Collapse
|
15
|
A Novel Compressed Sensing Method for Magnetic Resonance Imaging: Exponential Wavelet Iterative Shrinkage-Thresholding Algorithm with Random Shift. Int J Biomed Imaging 2016; 2016:9416435. [PMID: 27066068 PMCID: PMC4811091 DOI: 10.1155/2016/9416435] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2015] [Accepted: 02/23/2016] [Indexed: 12/05/2022] Open
Abstract
Aim. It can help improve the hospital throughput to accelerate magnetic resonance imaging (MRI) scanning. Patients will benefit from less waiting time. Task. In the last decade, various rapid MRI techniques on the basis of compressed sensing (CS) were proposed. However, both computation time and reconstruction quality of traditional CS-MRI did not meet the requirement of clinical use. Method. In this study, a novel method was proposed with the name of exponential wavelet iterative shrinkage-thresholding algorithm with random shift (abbreviated as EWISTARS). It is composed of three successful components: (i) exponential wavelet transform, (ii) iterative shrinkage-thresholding algorithm, and (iii) random shift. Results. Experimental results validated that, compared to state-of-the-art approaches, EWISTARS obtained the least mean absolute error, the least mean-squared error, and the highest peak signal-to-noise ratio. Conclusion. EWISTARS is superior to state-of-the-art approaches.
Collapse
|
16
|
Zhang Y, Dong Z, Phillips P, Wang S, Ji G, Yang J. Exponential Wavelet Iterative Shrinkage Thresholding Algorithm for compressed sensing magnetic resonance imaging. Inf Sci (N Y) 2015. [DOI: 10.1016/j.ins.2015.06.017] [Citation(s) in RCA: 76] [Impact Index Per Article: 8.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
|
17
|
Yang Y, Liu F, Jin Z, Crozier S. Aliasing Artefact Suppression in Compressed Sensing MRI for Random Phase-Encode Undersampling. IEEE Trans Biomed Eng 2015; 62:2215-23. [DOI: 10.1109/tbme.2015.2419372] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
|