1
|
Hewlett M, Petrov I, Johnson PM, Drangova M. Deep-learning-based motion correction using multichannel MRI data: a study using simulated artifacts in the fastMRI dataset. NMR IN BIOMEDICINE 2024:e5179. [PMID: 38808752 DOI: 10.1002/nbm.5179] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/21/2023] [Revised: 04/21/2024] [Accepted: 04/29/2024] [Indexed: 05/30/2024]
Abstract
Deep learning presents a generalizable solution for motion correction requiring no pulse sequence modifications or additional hardware, but previous networks have all been applied to coil-combined data. Multichannel MRI data provide a degree of spatial encoding that may be useful for motion correction. We hypothesize that incorporating deep learning for motion correction prior to coil combination will improve results. A conditional generative adversarial network was trained using simulated rigid motion artifacts in brain images acquired at multiple sites with multiple contrasts (not limited to healthy subjects). We compared the performance of deep-learning-based motion correction on individual channel images (single-channel model) with that performed after coil combination (channel-combined model). We also investigate simultaneous motion correction of all channel data from an image volume (multichannel model). The single-channel model significantly (p < 0.0001) improved mean absolute error, with an average 50.9% improvement compared with the uncorrected images. This was significantly (p < 0.0001) better than the 36.3% improvement achieved by the channel-combined model (conventional approach). The multichannel model provided no significant improvement in quantitative measures of image quality compared with the uncorrected images. Results were independent of the presence of pathology, and generalizable to a new center unseen during training. Performing motion correction on single-channel images prior to coil combination provided an improvement in performance compared with conventional deep-learning-based motion correction. Improved deep learning methods for retrospective correction of motion-affected MR images could reduce the need for repeat scans if applied in a clinical setting.
Collapse
Affiliation(s)
- Miriam Hewlett
- Robarts Research Institute, The University of Western Ontario, London, Ontario, Canada
- Department of Medical Biophysics, The University of Western Ontario, London, Ontario, Canada
| | - Ivailo Petrov
- Robarts Research Institute, The University of Western Ontario, London, Ontario, Canada
| | - Patricia M Johnson
- Department of Radiology, New York Medicine School of Medicine, New York, New York, USA
| | - Maria Drangova
- Robarts Research Institute, The University of Western Ontario, London, Ontario, Canada
- Department of Medical Biophysics, The University of Western Ontario, London, Ontario, Canada
| |
Collapse
|
2
|
Bao Q, Liu X, Xu J, Xia L, Otikovs M, Xie H, Liu K, Zhang Z, Zhou X, Liu C. Unsupervised deep learning model for correcting Nyquist ghosts of single-shot spatiotemporal encoding. Magn Reson Med 2024; 91:1368-1383. [PMID: 38073072 DOI: 10.1002/mrm.29925] [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: 04/15/2023] [Revised: 10/20/2023] [Accepted: 10/25/2023] [Indexed: 02/03/2024]
Abstract
PURPOSE To design an unsupervised deep learning (DL) model for correcting Nyquist ghosts of single-shot spatiotemporal encoding (SPEN) and evaluate the model for real MRI applications. METHODS The proposed method consists of three main components: (1) an unsupervised network that combines Residual Encoder and Restricted Subspace Mapping (RERSM-net) and is trained to generate a phase-difference map based on the even and odd SPEN images; (2) a spin physical forward model to obtain the corrected image with the learned phase difference map; and (3) cycle-consistency loss that is explored for training the RERSM-net. RESULTS The proposed RERSM-net could effectively generate smooth phase difference maps and correct Nyquist ghosts of single-shot SPEN. Both simulation and real in vivo MRI experiments demonstrated that our method outperforms the state-of-the-art SPEN Nyquist ghost correction method. Furthermore, the ablation experiments of generating phase-difference maps show the advantages of the proposed unsupervised model. CONCLUSION The proposed method can effectively correct Nyquist ghosts for the single-shot SPEN sequence.
Collapse
Affiliation(s)
- Qingjia Bao
- Key Laboratory of Magnetic Resonance in Biological Systems, Innovation Academy for Precision Measurement Science and Technology, Wuhan, China
| | - Xinjie Liu
- Key Laboratory of Magnetic Resonance in Biological Systems, Innovation Academy for Precision Measurement Science and Technology, Wuhan, China
- University of Chinese Academy of Sciences, Beijing, China
| | - Jingyun Xu
- School of Information Engineering, Wuhan University of Technology, Wuhan, China
| | - Liyang Xia
- School of Information Engineering, Wuhan University of Technology, Wuhan, China
| | | | - Han Xie
- Key Laboratory of Magnetic Resonance in Biological Systems, Innovation Academy for Precision Measurement Science and Technology, Wuhan, China
| | - Kewen Liu
- School of Information Engineering, Wuhan University of Technology, Wuhan, China
| | - Zhi Zhang
- Key Laboratory of Magnetic Resonance in Biological Systems, Innovation Academy for Precision Measurement Science and Technology, Wuhan, China
| | - Xin Zhou
- Key Laboratory of Magnetic Resonance in Biological Systems, Innovation Academy for Precision Measurement Science and Technology, Wuhan, China
- University of Chinese Academy of Sciences, Beijing, China
- Optics Valley Laboratory, Wuhan, China
| | - Chaoyang Liu
- Key Laboratory of Magnetic Resonance in Biological Systems, Innovation Academy for Precision Measurement Science and Technology, Wuhan, China
- University of Chinese Academy of Sciences, Beijing, China
- Optics Valley Laboratory, Wuhan, China
| |
Collapse
|
3
|
Yang T, Li Y, Ye Z, Yao S, Li Q, Yuan Y, Song B. Diffusion Weighted Imaging of the Abdomen and Pelvis: Recent Technical Advances and Clinical Applications. Acad Radiol 2023; 30:470-482. [PMID: 36038417 DOI: 10.1016/j.acra.2022.07.018] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2022] [Revised: 07/20/2022] [Accepted: 07/23/2022] [Indexed: 01/25/2023]
Abstract
Diffusion weighted imaging (DWI) serves as one of the most important functional magnetic resonance imaging techniques in abdominal and pelvic imaging. It is designed to reflect the diffusion of water molecules and is particularly sensitive to the malignancies. Yet, the limitations of image distortion and artifacts in single-shot DWI may hamper its widespread use in clinical practice. With recent technical advances in DWI, such as simultaneous multi-slice excitation, computed or reduced field-of-view techniques, as well as advanced shimming methods, it is possible to achieve shorter acquisition time, better image quality, and higher robustness in abdominopelvic DWI. This review discussed the recent advances of each DWI approach, and highlighted its future perspectives in abdominal and pelvic imaging, hoping to familiarize physicians and radiologists with the technical improvements in this field and provide future research directions.
Collapse
Affiliation(s)
- Ting Yang
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, China
| | - Ying Li
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, China
| | - Zheng Ye
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, China
| | - Shan Yao
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, China
| | - Qing Li
- MR Collaborations, Siemens Healthcare, Shanghai, China
| | - Yuan Yuan
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, China
| | - Bin Song
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, China; Department of Radiology, Sanya People's Hospital, Sanya, Hainan, China.
| |
Collapse
|
4
|
Ramos-Llordén G, Lobos RA, Kim TH, Tian Q, Witzel T, Lee HH, Scholz A, Keil B, Yendiki A, Bilgiç B, Haldar JP, Huang SY. High-fidelity, high-spatial-resolution diffusion magnetic resonance imaging of ex vivo whole human brain at ultra-high gradient strength with structured low-rank echo-planar imaging ghost correction. NMR IN BIOMEDICINE 2023; 36:e4831. [PMID: 36106429 PMCID: PMC9883835 DOI: 10.1002/nbm.4831] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/08/2022] [Revised: 08/20/2022] [Accepted: 09/11/2022] [Indexed: 06/15/2023]
Abstract
Diffusion magnetic resonance imaging (dMRI) of whole ex vivo human brain specimens enables three-dimensional (3D) mapping of structural connectivity at the mesoscopic scale, providing detailed evaluation of fiber architecture and tissue microstructure at a spatial resolution that is difficult to access in vivo. To account for the short T2 and low diffusivity of fixed tissue, ex vivo dMRI is often acquired using strong diffusion-sensitizing gradients and multishot/segmented 3D echo-planar imaging (EPI) sequences to achieve high spatial resolution. However, the combination of strong diffusion-sensitizing gradients and multishot/segmented EPI readout can result in pronounced ghosting artifacts incurred by nonlinear spatiotemporal variations in the magnetic field produced by eddy currents. Such ghosting artifacts cannot be corrected with conventional correction solutions and pose a significant roadblock to leveraging human MRI scanners with ultrahigh gradients for ex vivo whole-brain dMRI. Here, we show that ghosting-correction approaches that correct for either polarity-related ghosting or shot-to-shot variations in a separate manner are suboptimal for 3D multishot diffusion-weighted EPI experiments in fixed human brain specimens using strong diffusion-sensitizing gradients on the 3-T Connectom MRI scanner, resulting in orientationally biased dMRI estimates. We apply a recently developed advanced k-space reconstruction method based on structured low-rank matrix (SLM) modeling that handles both polarity-related ghosting and shot-to-shot variation simultaneously, to mitigate artifacts in high-angular resolution multishot dMRI data acquired in several fixed human brain specimens at 0.7-0.8-mm isotropic spatial resolution using b-values up to 10,000 s/mm2 and gradient strengths up to 280 mT/m. We demonstrate the improved mapping of diffusion tensor imaging and fiber orientation distribution functions in key neuroanatomical areas distributed across the whole brain using SLM-based EPI ghost correction compared with alternative techniques.
Collapse
Affiliation(s)
- Gabriel Ramos-Llordén
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, Massachusetts, USA
- Department of Radiology, Harvard Medical School, Boston, Massachusetts, USA
| | - Rodrigo A. Lobos
- Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, California, USA
| | - Tae Hyung Kim
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, Massachusetts, USA
- Department of Radiology, Harvard Medical School, Boston, Massachusetts, USA
- Computer Engineering, Hongik University, Seoul, Republic of Korea
| | - Qiyuan Tian
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, Massachusetts, USA
- Department of Radiology, Harvard Medical School, Boston, Massachusetts, USA
| | | | - Hong-Hsi Lee
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, Massachusetts, USA
- Department of Radiology, Harvard Medical School, Boston, Massachusetts, USA
| | - Alina Scholz
- Institute of Medical Physics and Radiation Protection, Mittelhessen University of Applied Sciences, Giessen, Germany
| | - Boris Keil
- Institute of Medical Physics and Radiation Protection, Mittelhessen University of Applied Sciences, Giessen, Germany
- Department of Diagnostic and Interventional Radiology, University Hospital Marburg, Philipps University of Marburg, Marburg, Germany
| | - Anastasia Yendiki
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, Massachusetts, USA
- Department of Radiology, Harvard Medical School, Boston, Massachusetts, USA
| | - Berkin Bilgiç
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, Massachusetts, USA
- Department of Radiology, Harvard Medical School, Boston, Massachusetts, USA
- Harvard-MIT Division of Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
| | - Justin P. Haldar
- Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, California, USA
| | - Susie Y. Huang
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, Massachusetts, USA
- Department of Radiology, Harvard Medical School, Boston, Massachusetts, USA
- Harvard-MIT Division of Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
| |
Collapse
|
5
|
Chen Z, Pawar K, Ekanayake M, Pain C, Zhong S, Egan GF. Deep Learning for Image Enhancement and Correction in Magnetic Resonance Imaging-State-of-the-Art and Challenges. J Digit Imaging 2023; 36:204-230. [PMID: 36323914 PMCID: PMC9984670 DOI: 10.1007/s10278-022-00721-9] [Citation(s) in RCA: 18] [Impact Index Per Article: 18.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2022] [Revised: 09/09/2022] [Accepted: 10/17/2022] [Indexed: 11/06/2022] Open
Abstract
Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast for clinical diagnoses and research which underpin many recent breakthroughs in medicine and biology. The post-processing of reconstructed MR images is often automated for incorporation into MRI scanners by the manufacturers and increasingly plays a critical role in the final image quality for clinical reporting and interpretation. For image enhancement and correction, the post-processing steps include noise reduction, image artefact correction, and image resolution improvements. With the recent success of deep learning in many research fields, there is great potential to apply deep learning for MR image enhancement, and recent publications have demonstrated promising results. Motivated by the rapidly growing literature in this area, in this review paper, we provide a comprehensive overview of deep learning-based methods for post-processing MR images to enhance image quality and correct image artefacts. We aim to provide researchers in MRI or other research fields, including computer vision and image processing, a literature survey of deep learning approaches for MR image enhancement. We discuss the current limitations of the application of artificial intelligence in MRI and highlight possible directions for future developments. In the era of deep learning, we highlight the importance of a critical appraisal of the explanatory information provided and the generalizability of deep learning algorithms in medical imaging.
Collapse
Affiliation(s)
- Zhaolin Chen
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, 3168, Australia.
- Department of Data Science and AI, Monash University, Melbourne, VIC, Australia.
| | - Kamlesh Pawar
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, 3168, Australia
| | - Mevan Ekanayake
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, 3168, Australia
- Department of Electrical and Computer Systems Engineering, Monash University, Melbourne, VIC, Australia
| | - Cameron Pain
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, 3168, Australia
- Department of Electrical and Computer Systems Engineering, Monash University, Melbourne, VIC, Australia
| | - Shenjun Zhong
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, 3168, Australia
- National Imaging Facility, Brisbane, QLD, Australia
| | - Gary F Egan
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, 3168, Australia
- Turner Institute for Brain and Mental Health, Monash University, Melbourne, VIC, Australia
| |
Collapse
|
6
|
Qu X, Ren C, Yan G, Zheng D, Tang W, Wang S, Lin H, Zhang J, Jiang J. Deep-Learning-Based Ultrasound Sound-Speed Tomography Reconstruction with Tikhonov Pseudo-Inverse Priori. ULTRASOUND IN MEDICINE & BIOLOGY 2022; 48:2079-2094. [PMID: 35922265 PMCID: PMC10448397 DOI: 10.1016/j.ultrasmedbio.2022.05.033] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/22/2021] [Revised: 05/26/2022] [Accepted: 05/31/2022] [Indexed: 06/15/2023]
Abstract
Ultrasound sound-speed tomography (USST) is a promising technology for breast imaging and breast cancer detection. Its reconstruction is a complex non-linear mapping from the projection data to the sound-speed image (SSI). The traditional reconstruction methods include mainly the ray-based methods and the waveform-based methods. The ray-based methods with linear approximation have low computational cost but low reconstruction quality; the full wave-based methods with the complex non-linear model have high quality but high cost. To achieve both high quality and low cost, we introduced traditional linear approximation as prior knowledge into a deep neural network and treated the complex non-linear mapping of USST reconstruction as a combination of linear mapping and non-linear mapping. In the proposed method, the linear mapping was seamlessly implemented with a fully connected layer and initialized using the Tikhonov pseudo-inverse matrix. The non-linear mapping was implemented using a U-shape Net (U-Net). Furthermore, we proposed the Tikhonov U-shape net (TU-Net), in which the linear mapping was done before the non-linear mapping, and the U-shape Tikhonov net (UT-Net), in which the non-linear mapping was done before the linear mapping. Moreover, we conducted simulations and experiments for evaluation. In the numerical simulation, the root-mean-squared error was 6.49 and 4.29 m/s for the UT-Net and TU-Net, the peak signal-to-noise ratio was 49.01 and 52.90 dB, the structural similarity was 0.9436 and 0.9761 and the reconstruction time was 10.8 and 11.3 ms, respectively. In this study, the SSIs obtained with the proposed methods exhibited high sound-speed accuracy. Both the UT-Net and the TU-Net achieved high quality and low computational cost.
Collapse
Affiliation(s)
- Xiaolei Qu
- School of Instrumentation and Optoelectronics Engineering, Beihang University, Beijing, China
| | - Chujian Ren
- School of Instrumentation and Optoelectronics Engineering, Beihang University, Beijing, China
| | - Guo Yan
- School of Instrumentation and Optoelectronics Engineering, Beihang University, Beijing, China
| | - Dezhi Zheng
- Research Institute for Frontier Science, Beihang University, Beijing, China
| | - Wenzhong Tang
- School of Computer Science and Engineering, Beihang University, Beijing, China
| | - Shuai Wang
- Research Institute for Frontier Science, Beihang University, Beijing, China
| | - Hongxiang Lin
- Research Center for Healthcare Data Science, Zhejiang Lab, Hangzhou, China
| | - Jingya Zhang
- School of Instrumentation and Optoelectronics Engineering, Beihang University, Beijing, China
| | - Jue Jiang
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, USA.
| |
Collapse
|
7
|
Wang L, Wang C, Wang F, Chu YH, Yang Z, Wang H. EPI phase error correction with deep learning (PEC-DL) at 7 T. Magn Reson Med 2022; 88:1775-1784. [PMID: 35696532 DOI: 10.1002/mrm.29317] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2021] [Revised: 05/06/2022] [Accepted: 05/09/2022] [Indexed: 11/10/2022]
Abstract
PURPOSE The phase mismatch between odd and even echoes in EPI causes Nyquist ghost artifacts. Existing ghost correction methods often suffer from severe residual artifacts and are ineffective with k-space undersampling data. This study proposed a deep learning-based method (PEC-DL) to correct phase errors for DWI at 7 Tesla. METHODS The acquired k-space data were divided into 2 independent undersampled datasets according to their readout polarities. Then the proposed PEC-DL network reconstructed 2 ghost-free images using the undersampled data without calibration and navigator data. The network was trained with fully sampled images and applied to two- and fourfold accelerated data. Healthy volunteers and patients with Moyamoya disease were recruited to validate the efficacy of the PEC-DL method. RESULTS The PEC-DL method was capable to mitigate the ghost artifacts in DWI in healthy volunteers as well as patients with Moyamoya disease. The fourfold accelerated results showed much less distortion in the lesions of the Moyamoya patient using high b-value DWI and the corresponding ADC maps. The ghost-to-signal ratios were significantly lower in PEC-DL images compared to conventional linear phase corrections, mini-entropy, and PEC-GRAPPA algorithms. CONCLUSION The proposed method can effectively eliminate ghost artifacts for full sampled and up to fourfold accelerated EPI data without calibration and navigator data.
Collapse
Affiliation(s)
- Lili Wang
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, People's Republic of China
| | - Chengyan Wang
- Human Phenome Institute, Fudan University, Shanghai, People's Republic of China
| | - Fanwen Wang
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, People's Republic of China
| | - Ying-Hua Chu
- MR Collaboration, Siemens Healthcare Ltd., Shanghai, People's Republic of China
| | - Zidong Yang
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, People's Republic of China
| | - He Wang
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, People's Republic of China.,MR Collaboration, Siemens Healthcare Ltd., Shanghai, People's Republic of China
| |
Collapse
|
8
|
Chuang KH, Wu PH, Li Z, Fan KH, Weng JC. Deep learning network for integrated coil inhomogeneity correction and brain extraction of mixed MRI data. Sci Rep 2022; 12:8578. [PMID: 35595829 PMCID: PMC9123199 DOI: 10.1038/s41598-022-12587-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2021] [Accepted: 05/13/2022] [Indexed: 12/02/2022] Open
Abstract
Magnetic Resonance Imaging (MRI) has been widely used to acquire structural and functional information about the brain. In a group- or voxel-wise analysis, it is essential to correct the bias field of the radiofrequency coil and to extract the brain for accurate registration to the brain template. Although automatic methods have been developed, manual editing is still required, particularly for echo-planar imaging (EPI) due to its lower spatial resolution and larger geometric distortion. The needs of user interventions slow down data processing and lead to variable results between operators. Deep learning networks have been successfully used for automatic postprocessing. However, most networks are only designed for a specific processing and/or single image contrast (e.g., spin-echo or gradient-echo). This limitation markedly restricts the application and generalization of deep learning tools. To address these limitations, we developed a deep learning network based on the generative adversarial net (GAN) to automatically correct coil inhomogeneity and extract the brain from both spin- and gradient-echo EPI without user intervention. Using various quantitative indices, we show that this method achieved high similarity to the reference target and performed consistently across datasets acquired from rodents. These results highlight the potential of deep networks to integrate different postprocessing methods and adapt to different image contrasts. The use of the same network to process multimodality data would be a critical step toward a fully automatic postprocessing pipeline that could facilitate the analysis of large datasets with high consistency.
Collapse
Affiliation(s)
- Kai-Hsiang Chuang
- Queensland Brain Institute and Centre for Advanced Imaging, University of Queensland, Brisbane, Australia
| | - Pei-Huan Wu
- Department of Medical Imaging and Radiological Sciences, and Graduate Institute of Artificial Intelligence, Chang Gung University, No. 259, Wenhua 1st Rd., Guishan Dist., Taoyuan, 33302, Taiwan
| | - Zengmin Li
- Queensland Brain Institute and Centre for Advanced Imaging, University of Queensland, Brisbane, Australia
| | - Kang-Hsing Fan
- Department of Radiation Oncology, Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan
| | - Jun-Cheng Weng
- Department of Medical Imaging and Radiological Sciences, and Graduate Institute of Artificial Intelligence, Chang Gung University, No. 259, Wenhua 1st Rd., Guishan Dist., Taoyuan, 33302, Taiwan. .,Medical Imaging Research Center, Institute for Radiological Research, Chang Gung University and Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan. .,Department of Psychiatry, Chang Gung Memorial Hospital, Chiayi, Taiwan.
| |
Collapse
|
9
|
|
10
|
Torop M, Kothapalli SVVN, Sun Y, Liu J, Kahali S, Yablonskiy DA, Kamilov US. Deep learning using a biophysical model for robust and accelerated reconstruction of quantitative, artifact-free and denoised R 2 * images. Magn Reson Med 2020; 84:2932-2942. [PMID: 32767489 DOI: 10.1002/mrm.28344] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2020] [Revised: 05/12/2020] [Accepted: 05/13/2020] [Indexed: 12/12/2022]
Abstract
PURPOSE To introduce a novel deep learning method for Robust and Accelerated Reconstruction (RoAR) of quantitative and B0-inhomogeneity-corrected R 2 * maps from multi-gradient recalled echo (mGRE) MRI data. METHODS RoAR trains a convolutional neural network (CNN) to generate quantitative R 2 ∗ maps free from field inhomogeneity artifacts by adopting a self-supervised learning strategy given (a) mGRE magnitude images, (b) the biophysical model describing mGRE signal decay, and (c) preliminary-evaluated F-function accounting for contribution of macroscopic B0 field inhomogeneities. Importantly, no ground-truth R 2 * images are required and F-function is only needed during RoAR training but not application. RESULTS We show that RoAR preserves all features of R 2 * maps while offering significant improvements over existing methods in computation speed (seconds vs. hours) and reduced sensitivity to noise. Even for data with SNR = 5 RoAR produced R 2 * maps with accuracy of 22% while voxel-wise analysis accuracy was 47%. For SNR = 10 the RoAR accuracy increased to 17% vs. 24% for direct voxel-wise analysis. CONCLUSIONS RoAR is trained to recognize the macroscopic magnetic field inhomogeneities directly from the input magnitude-only mGRE data and eliminate their effect on R 2 ∗ measurements. RoAR training is based on the biophysical model and does not require ground-truth R 2 * maps. Since RoAR utilizes signal information not just from individual voxels but also accounts for spatial patterns of the signals in the images, it reduces the sensitivity of R 2 * maps to the noise in the data. These features plus high computational speed provide significant benefits for the potential usage of RoAR in clinical settings.
Collapse
Affiliation(s)
- Max Torop
- Department of Computer Science and Engineering, Washington University in St. Louis, St. Louis, MO, USA
| | | | - Yu Sun
- Department of Computer Science and Engineering, Washington University in St. Louis, St. Louis, MO, USA
| | - Jiaming Liu
- Department of Electrical and Systems Engineering, University in St. Louis, St. Louis, MO, USA
| | - Sayan Kahali
- Department of Radiology, Washington University in St. Louis, St. Louis, MO, USA
| | | | - Ulugbek S Kamilov
- Department of Computer Science and Engineering, Washington University in St. Louis, St. Louis, MO, USA.,Department of Electrical and Systems Engineering, University in St. Louis, St. Louis, MO, USA
| |
Collapse
|
11
|
Börnert P, Norris DG. A half-century of innovation in technology-preparing MRI for the 21st century. Br J Radiol 2020; 93:20200113. [PMID: 32496816 DOI: 10.1259/bjr.20200113] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/16/2022] Open
Abstract
MRI developed during the last half-century from a very basic concept to an indispensable non-ionising medical imaging technique that has found broad application in diagnostics, therapy control and far beyond. Due to its excellent soft-tissue contrast and the huge variety of accessible tissue- and physiological-parameters, MRI is often preferred to other existing modalities. In the course of its development, MRI underwent many substantial transformations. From the beginning, starting as a proof of concept, much effort was expended to develop the appropriate basic scanning technology and methodology, and to establish the many clinical contrasts (e.g., T1, T2, flow, diffusion, water/fat, etc.) that MRI is famous for today. Beyond that, additional prominent innovations to the field have been parallel imaging and compressed sensing, leading to significant scanning time reductions, and the move towards higher static magnetic field strengths, which led to increased sensitivity and improved image quality. Improvements in workflow and the use of artificial intelligence are among many current trends seen in this field, paving the way for a broad use of MRI. The 125th anniversary of the BJR is a good point to reflect on all these changes and developments and to offer some slightly speculative ideas as to what the future may bring.
Collapse
Affiliation(s)
- Peter Börnert
- Philips Research, Hamburg, Germany.,Department of Radiology, LUMC, Leiden, the Netherlands
| | - David G Norris
- Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, Netherlands.,Erwin L. Hahn Institute for Magnetic Resonance Imaging, University of Duisburg-Essen, Essen, Germany.,Magnetic Detection and Imaging, Science and Technology Faculty, University of Twente, Enschede, Netherlands
| |
Collapse
|
12
|
Lin DJ, Johnson PM, Knoll F, Lui YW. Artificial Intelligence for MR Image Reconstruction: An Overview for Clinicians. J Magn Reson Imaging 2020; 53:1015-1028. [PMID: 32048372 DOI: 10.1002/jmri.27078] [Citation(s) in RCA: 97] [Impact Index Per Article: 24.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2019] [Revised: 01/15/2020] [Accepted: 01/17/2020] [Indexed: 12/22/2022] Open
Abstract
Artificial intelligence (AI) shows tremendous promise in the field of medical imaging, with recent breakthroughs applying deep-learning models for data acquisition, classification problems, segmentation, image synthesis, and image reconstruction. With an eye towards clinical applications, we summarize the active field of deep-learning-based MR image reconstruction. We review the basic concepts of how deep-learning algorithms aid in the transformation of raw k-space data to image data, and specifically examine accelerated imaging and artifact suppression. Recent efforts in these areas show that deep-learning-based algorithms can match and, in some cases, eclipse conventional reconstruction methods in terms of image quality and computational efficiency across a host of clinical imaging applications, including musculoskeletal, abdominal, cardiac, and brain imaging. This article is an introductory overview aimed at clinical radiologists with no experience in deep-learning-based MR image reconstruction and should enable them to understand the basic concepts and current clinical applications of this rapidly growing area of research across multiple organ systems.
Collapse
Affiliation(s)
- Dana J Lin
- Department of Radiology, NYU School of Medicine/NYU Langone Health, New York, New York, USA
| | - Patricia M Johnson
- Center for Biomedical Imaging, New York University School of Medicine, New York, New York, USA
| | - Florian Knoll
- Center for Biomedical Imaging, New York University School of Medicine, New York, New York, USA
| | - Yvonne W Lui
- Department of Radiology, NYU School of Medicine/NYU Langone Health, New York, New York, USA
| |
Collapse
|
13
|
Validation of Deep Learning-Based Artifact Correction on Synthetic FLAIR Images in a Different Scanning Environment. J Clin Med 2020; 9:jcm9020364. [PMID: 32013069 PMCID: PMC7074150 DOI: 10.3390/jcm9020364] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2019] [Revised: 01/26/2020] [Accepted: 01/27/2020] [Indexed: 12/26/2022] Open
Abstract
We investigated the capability of a trained deep learning (DL) model with a convolutional neural network (CNN) in a different scanning environment in terms of ameliorating the quality of synthetic fluid-attenuated inversion recovery (FLAIR) images. The acquired data of 319 patients obtained from the retrospective review were used as test sets for the already trained DL model to correct the synthetic FLAIR images. Quantitative analyses were performed for native synthetic FLAIR and DL-FLAIR images against conventional FLAIR images. Two neuroradiologists assessed the quality and artifact degree of the native synthetic FLAIR and DL-FLAIR images. The quantitative parameters showed significant improvement on DL-FLAIR in all individual tissue segments and total intracranial tissues than on the native synthetic FLAIR (p < 0.0001). DL-FLAIR images showed improved image quality with fewer artifacts than the native synthetic FLAIR images (p < 0.0001). There was no significant difference in the preservation of the periventricular white matter hyperintensities and lesion conspicuity between the two FLAIR image sets (p = 0.217). The quality of synthetic FLAIR images was improved through artifact correction using the trained DL model on a different scan environment. DL-based correction can be a promising solution for ameliorating the quality of synthetic FLAIR images to broaden the clinical use of synthetic magnetic resonance imaging (MRI).
Collapse
|
14
|
Ravishankar S, Ye JC, Fessler JA. Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learning. PROCEEDINGS OF THE IEEE. INSTITUTE OF ELECTRICAL AND ELECTRONICS ENGINEERS 2020; 108:86-109. [PMID: 32095024 PMCID: PMC7039447 DOI: 10.1109/jproc.2019.2936204] [Citation(s) in RCA: 68] [Impact Index Per Article: 17.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/05/2023]
Abstract
The field of medical image reconstruction has seen roughly four types of methods. The first type tended to be analytical methods, such as filtered back-projection (FBP) for X-ray computed tomography (CT) and the inverse Fourier transform for magnetic resonance imaging (MRI), based on simple mathematical models for the imaging systems. These methods are typically fast, but have suboptimal properties such as poor resolution-noise trade-off for CT. A second type is iterative reconstruction methods based on more complete models for the imaging system physics and, where appropriate, models for the sensor statistics. These iterative methods improved image quality by reducing noise and artifacts. The FDA-approved methods among these have been based on relatively simple regularization models. A third type of methods has been designed to accommodate modified data acquisition methods, such as reduced sampling in MRI and CT to reduce scan time or radiation dose. These methods typically involve mathematical image models involving assumptions such as sparsity or low-rank. A fourth type of methods replaces mathematically designed models of signals and systems with data-driven or adaptive models inspired by the field of machine learning. This paper focuses on the two most recent trends in medical image reconstruction: methods based on sparsity or low-rank models, and data-driven methods based on machine learning techniques.
Collapse
Affiliation(s)
- Saiprasad Ravishankar
- Departments of Computational Mathematics, Science and Engineering, and Biomedical Engineering at Michigan State University, East Lansing, MI, 48824 USA
| | - Jong Chul Ye
- Department of Bio and Brain Engineering and Department of Mathematical Sciences at the Korea Advanced Institute of Science & Technology (KAIST), Daejeon, South Korea
| | - Jeffrey A Fessler
- Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, 48109 USA
| |
Collapse
|