1
|
Wang S, Wu R, Jia S, Diakite A, Li C, Liu Q, Zheng H, Ying L. Knowledge-driven deep learning for fast MR imaging: Undersampled MR image reconstruction from supervised to un-supervised learning. Magn Reson Med 2024; 92:496-518. [PMID: 38624162 DOI: 10.1002/mrm.30105] [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: 05/03/2023] [Revised: 03/19/2024] [Accepted: 03/20/2024] [Indexed: 04/17/2024]
Abstract
Deep learning (DL) has emerged as a leading approach in accelerating MRI. It employs deep neural networks to extract knowledge from available datasets and then applies the trained networks to reconstruct accurate images from limited measurements. Unlike natural image restoration problems, MRI involves physics-based imaging processes, unique data properties, and diverse imaging tasks. This domain knowledge needs to be integrated with data-driven approaches. Our review will introduce the significant challenges faced by such knowledge-driven DL approaches in the context of fast MRI along with several notable solutions, which include learning neural networks and addressing different imaging application scenarios. The traits and trends of these techniques have also been given which have shifted from supervised learning to semi-supervised learning, and finally, to unsupervised learning methods. In addition, MR vendors' choices of DL reconstruction have been provided along with some discussions on open questions and future directions, which are critical for the reliable imaging systems.
Collapse
Affiliation(s)
- Shanshan Wang
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Ruoyou Wu
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Sen Jia
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Alou Diakite
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
- University of Chinese Academy of Sciences, Beijing, China
| | - Cheng Li
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Qiegen Liu
- Department of Electronic Information Engineering, Nanchang University, Nanchang, China
| | - Hairong Zheng
- Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Leslie Ying
- Department of Biomedical Engineering and Department of Electrical Engineering, The State University of New York, Buffalo, New York, USA
| |
Collapse
|
2
|
López-Ales E, Menchón-Lara RM, Simmross-Wattenberg F, Rodríguez-Cayetano M, Martín-Fernández M, Alberola-López C. Multi-Device Parallel MRI Reconstruction: Efficient Partitioning for Undersampled 5D Cardiac CINE. SENSORS (BASEL, SWITZERLAND) 2024; 24:1313. [PMID: 38400470 PMCID: PMC10891760 DOI: 10.3390/s24041313] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/29/2023] [Revised: 02/04/2024] [Accepted: 02/16/2024] [Indexed: 02/25/2024]
Abstract
Cardiac CINE, a form of dynamic cardiac MRI, is indispensable in the diagnosis and treatment of heart conditions, offering detailed visualization essential for the early detection of cardiac diseases. As the demand for higher-resolution images increases, so does the volume of data requiring processing, presenting significant computational challenges that can impede the efficiency of diagnostic imaging. Our research presents an approach that takes advantage of the computational power of multiple Graphics Processing Units (GPUs) to address these challenges. GPUs are devices capable of performing large volumes of computations in a short period, and have significantly improved the cardiac MRI reconstruction process, allowing images to be produced faster. The innovation of our work resides in utilizing a multi-device system capable of processing the substantial data volumes demanded by high-resolution, five-dimensional cardiac MRI. This system surpasses the memory capacity limitations of single GPUs by partitioning large datasets into smaller, manageable segments for parallel processing, thereby preserving image integrity and accelerating reconstruction times. Utilizing OpenCL technology, our system offers adaptability and cross-platform functionality, ensuring wider applicability. The proposed multi-device approach offers an advancement in medical imaging, accelerating the reconstruction process and facilitating faster and more effective cardiac health assessment.
Collapse
Affiliation(s)
- Emilio López-Ales
- Laboratorio de Procesado de Imagen, Universidad de Valladolid, Campus Miguel Delibes sn., 47011 Valladolid, Spain; (R.-M.M.-L.); (F.S.-W.); (M.R.-C.); (M.M.-F.)
| | | | | | | | | | - Carlos Alberola-López
- Laboratorio de Procesado de Imagen, Universidad de Valladolid, Campus Miguel Delibes sn., 47011 Valladolid, Spain; (R.-M.M.-L.); (F.S.-W.); (M.R.-C.); (M.M.-F.)
| |
Collapse
|
3
|
Oscanoa JA, Ong F, Iyer SS, Li Z, Sandino CM, Ozturkler B, Ennis DB, Pilanci M, Vasanawala SS. Coil sketching for computationally efficient MR iterative reconstruction. Magn Reson Med 2024; 91:784-802. [PMID: 37848365 DOI: 10.1002/mrm.29883] [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: 04/13/2023] [Revised: 08/23/2023] [Accepted: 09/17/2023] [Indexed: 10/19/2023]
Abstract
PURPOSE Parallel imaging and compressed sensing reconstructions of large MRI datasets often have a prohibitive computational cost that bottlenecks clinical deployment, especially for three-dimensional (3D) non-Cartesian acquisitions. One common approach is to reduce the number of coil channels actively used during reconstruction as in coil compression. While effective for Cartesian imaging, coil compression inherently loses signal energy, producing shading artifacts that compromise image quality for 3D non-Cartesian imaging. We propose coil sketching, a general and versatile method for computationally-efficient iterative MR image reconstruction. THEORY AND METHODS We based our method on randomized sketching algorithms, a type of large-scale optimization algorithms well established in the fields of machine learning and big data analysis. We adapt the sketching theory to the MRI reconstruction problem via a structured sketching matrix that, similar to coil compression, considers high-energy virtual coils obtained from principal component analysis. But, unlike coil compression, it also considers random linear combinations of the remaining low-energy coils, effectively leveraging information from all coils. RESULTS First, we performed ablation experiments to validate the sketching matrix design on both Cartesian and non-Cartesian datasets. The resulting design yielded both improved computatioanal efficiency and preserved signal-to-noise ratio (SNR) as measured by the inverse g-factor. Then, we verified the efficacy of our approach on high-dimensional non-Cartesian 3D cones datasets, where coil sketching yielded up to three-fold faster reconstructions with equivalent image quality. CONCLUSION Coil sketching is a general and versatile reconstruction framework for computationally fast and memory-efficient reconstruction.
Collapse
Affiliation(s)
- Julio A Oscanoa
- Department of Bioengineering, Stanford University, Stanford, California, USA
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Frank Ong
- Department of Electrical Engineering, Stanford University, Stanford, California, USA
| | - Siddharth S Iyer
- Department of Electrical Engineering and Computer Science, Massachussetts Institute of Technology, Cambridge, Massachussetts, USA
| | - Zhitao Li
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Christopher M Sandino
- Department of Electrical Engineering, Stanford University, Stanford, California, USA
| | - Batu Ozturkler
- Department of Electrical Engineering, Stanford University, Stanford, California, USA
| | - Daniel B Ennis
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Mert Pilanci
- Department of Electrical Engineering, Stanford University, Stanford, California, USA
| | | |
Collapse
|
4
|
Dar SUH, Öztürk Ş, Özbey M, Oguz KK, Çukur T. Parallel-stream fusion of scan-specific and scan-general priors for learning deep MRI reconstruction in low-data regimes. Comput Biol Med 2023; 167:107610. [PMID: 37883853 DOI: 10.1016/j.compbiomed.2023.107610] [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: 04/10/2023] [Revised: 09/20/2023] [Accepted: 10/17/2023] [Indexed: 10/28/2023]
Abstract
Magnetic resonance imaging (MRI) is an essential diagnostic tool that suffers from prolonged scan times. Reconstruction methods can alleviate this limitation by recovering clinically usable images from accelerated acquisitions. In particular, learning-based methods promise performance leaps by employing deep neural networks as data-driven priors. A powerful approach uses scan-specific (SS) priors that leverage information regarding the underlying physical signal model for reconstruction. SS priors are learned on each individual test scan without the need for a training dataset, albeit they suffer from computationally burdening inference with nonlinear networks. An alternative approach uses scan-general (SG) priors that instead leverage information regarding the latent features of MRI images for reconstruction. SG priors are frozen at test time for efficiency, albeit they require learning from a large training dataset. Here, we introduce a novel parallel-stream fusion model (PSFNet) that synergistically fuses SS and SG priors for performant MRI reconstruction in low-data regimes, while maintaining competitive inference times to SG methods. PSFNet implements its SG prior based on a nonlinear network, yet it forms its SS prior based on a linear network to maintain efficiency. A pervasive framework for combining multiple priors in MRI reconstruction is algorithmic unrolling that uses serially alternated projections, causing error propagation under low-data regimes. To alleviate error propagation, PSFNet combines its SS and SG priors via a novel parallel-stream architecture with learnable fusion parameters. Demonstrations are performed on multi-coil brain MRI for varying amounts of training data. PSFNet outperforms SG methods in low-data regimes, and surpasses SS methods with few tens of training samples. On average across tasks, PSFNet achieves 3.1 dB higher PSNR, 2.8% higher SSIM, and 0.3 × lower RMSE than baselines. Furthermore, in both supervised and unsupervised setups, PSFNet requires an order of magnitude lower samples compared to SG methods, and enables an order of magnitude faster inference compared to SS methods. Thus, the proposed model improves deep MRI reconstruction with elevated learning and computational efficiency.
Collapse
Affiliation(s)
- Salman Ul Hassan Dar
- Department of Internal Medicine III, Heidelberg University Hospital, 69120, Heidelberg, Germany; AI Health Innovation Cluster, Heidelberg, Germany
| | - Şaban Öztürk
- Department of Electrical and Electronics Engineering, Bilkent University, Ankara 06800, Turkey; Department of Electrical-Electronics Engineering, Amasya University, Amasya 05100, Turkey
| | - Muzaffer Özbey
- Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, IL 61820, United States
| | - Kader Karli Oguz
- Department of Radiology, University of California, Davis, CA 95616, United States; Department of Radiology, Hacettepe University, Ankara, Turkey
| | - Tolga Çukur
- Department of Electrical and Electronics Engineering, Bilkent University, Ankara 06800, Turkey; Department of Radiology, Hacettepe University, Ankara, Turkey; National Magnetic Resonance Research Center (UMRAM), Bilkent University, Ankara 06800, Turkey; Neuroscience Graduate Program, Bilkent University, Ankara 06800, Turkey.
| |
Collapse
|
5
|
Vu BTD, Jones BC, Lee H, Kamona N, Deshpande RS, Wehrli FW, Rajapakse CS. Six-minute, in vivo MRI quantification of proximal femur trabecular bone 3D microstructure. Bone 2023; 177:116900. [PMID: 37714503 DOI: 10.1016/j.bone.2023.116900] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/26/2023] [Revised: 08/29/2023] [Accepted: 09/12/2023] [Indexed: 09/17/2023]
Abstract
BACKGROUND Assessment of proximal femur trabecular bone microstructure in vivo by magnetic resonance imaging has recently been validated for acquiring information independent of bone mineral density in osteoporotic patients. However, the requisite signal-to-noise ratio (SNR) and resolution for interrogation of the trabecular microstructure at this anatomical location prolongs the scan duration and renders the imaging protocol clinically infeasible. Parallel imaging and compressed sensing (PICS) techniques can reduce the scan duration of the imaging protocol without substantially compromising image quality. The present work investigates the limits of acceleration for a commonly used PICS technique, ℓ1-ESPIRiT, for the purpose of quantifying measures of trabecular bone microarchitecture. Based on a desired error tolerance, a six-minute, prospectively accelerated variant of the imaging protocol was developed and assessed for intersession reproducibility and agreement with the longer reference scan. PURPOSE To investigate the limits of acceleration for MRI-based trabecular bone quantification by parallel imaging and compressed sensing reconstruction, and to develop a prototypical imaging protocol for assessing the proximal femur microstructure in a clinically practical scan time. METHODS Healthy participants (n = 11) were scanned by a 3D balanced steady-state free precession (bSSFP) sequence satisfying the Nyquist criterion with a scan duration of about 18 min. The raw data were retrospectively undersampled and reconstructed to mimic various acceleration factors ranging from 2 to 6. Trabecular volumes-of-interest in four major femoral regions (greater trochanter, intertrochanteric region, femoral neck, and femoral head) were analyzed and six relevant measures of trabecular bone microarchitecture (bone volume fraction, surface-to-curve ratio, erosion index, elastic modulus, trabecular thickness, plates-to-rods ratio) were obtained for images of all accelerations. To assess agreement, median percent error and intraclass correlation coefficients (ICCs) were computed using the fully-sampled data as reference. Based on this analysis, a prospectively 3-fold accelerated sequence with a duration of about 6 min was developed and the analysis was repeated. RESULTS A prospective acceleration factor of 3 demonstrated comparable performance in reproducibility and absolute agreement to the fully-sampled scan. The median CoV over all image-derived metrics was generally <6 % and ICCs >0.70. Also, measurements from prospectively 3-fold accelerated scans demonstrated in general median percent errors of <7 % and ICCs >0.70. CONCLUSION The present work proposes a method to make in vivo quantitative assessment of proximal femur trabecular microstructure with a clinically practical scan duration of about 6 min.
Collapse
Affiliation(s)
- Brian-Tinh Duc Vu
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 1 Founders Building, 3400 Spruce St, Philadelphia, PA 19104, United States of America; Department of Bioengineering, School of Engineering and Applied Sciences, University of Pennsylvania, 210 South 33(rd) St, Philadelphia, PA 19104, United States of America.
| | - Brandon C Jones
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 1 Founders Building, 3400 Spruce St, Philadelphia, PA 19104, United States of America; Department of Bioengineering, School of Engineering and Applied Sciences, University of Pennsylvania, 210 South 33(rd) St, Philadelphia, PA 19104, United States of America
| | - Hyunyeol Lee
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 1 Founders Building, 3400 Spruce St, Philadelphia, PA 19104, United States of America; School of Electronics Engineering, Kyungpook National University, 80 Daehakro, Bukgu, Daegu 41566, South Korea
| | - Nada Kamona
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 1 Founders Building, 3400 Spruce St, Philadelphia, PA 19104, United States of America; Department of Bioengineering, School of Engineering and Applied Sciences, University of Pennsylvania, 210 South 33(rd) St, Philadelphia, PA 19104, United States of America
| | - Rajiv S Deshpande
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 1 Founders Building, 3400 Spruce St, Philadelphia, PA 19104, United States of America; Department of Bioengineering, School of Engineering and Applied Sciences, University of Pennsylvania, 210 South 33(rd) St, Philadelphia, PA 19104, United States of America
| | - Felix W Wehrli
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 1 Founders Building, 3400 Spruce St, Philadelphia, PA 19104, United States of America
| | - Chamith S Rajapakse
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 1 Founders Building, 3400 Spruce St, Philadelphia, PA 19104, United States of America; Department of Orthopaedic Surgery, Perelman School of Medicine, University of Pennsylvania, 3400 Spruce St, Philadelphia, PA 19104, United States of America
| |
Collapse
|
6
|
Pan Z, Ma X, Dai E, Auerbach EJ, Guo H, Uğurbil K, Wu X. Reconstruction for 7T high-resolution whole-brain diffusion MRI using two-stage N/2 ghost correction and L1-SPIRiT without single-band reference. Magn Reson Med 2023; 89:1915-1930. [PMID: 36594439 PMCID: PMC9992311 DOI: 10.1002/mrm.29573] [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: 08/01/2022] [Revised: 11/28/2022] [Accepted: 12/19/2022] [Indexed: 01/04/2023]
Abstract
PURPOSE To combine a new two-stage N/2 ghost correction and an adapted L1-SPIRiT method for reconstruction of 7T highly accelerated whole-brain diffusion MRI (dMRI) using only autocalibration scans (ACS) without the need of additional single-band reference (SBref) scans. METHODS The proposed ghost correction consisted of a 3-line reference approach in stage 1 and the reference-free entropy method in stage 2. The adapted L1-SPIRiT method was formulated within the 3D k-space framework. Its efficacy was examined by acquiring two dMRI data sets at 1.05-mm isotropic resolutions with a total acceleration of 6 or 9 (i.e., 2-fold or 3-fold slice and 3-fold in-plane acceleration). Diffusion analysis was performed to derive DTI metrics and estimate fiber orientation distribution functions (fODFs). The results were compared with those of 3D k-space GRAPPA using only ACS, all in reference to 3D k-space GRAPPA using both ACS and SBref (serving as a reference). RESULTS The proposed ghost correction eliminated artifacts more robustly than conventional approaches. Our adapted L1-SPIRiT method outperformed 3D k-space GRAPPA when using only ACS, improving image quality to what was achievable with 3D k-space GRAPPA using both ACS and SBref scans. The improvement in image quality further resulted in an improvement in estimation performances for DTI and fODFs. CONCLUSION The combination of our new ghost correction and adapted L1-SPIRiT method can reliably reconstruct 7T highly accelerated whole-brain dMRI without the need of SBref scans, increasing acquisition efficiency and reducing motion sensitivity.
Collapse
Affiliation(s)
- Ziyi Pan
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Xiaodong Ma
- Center for Magnetic Resonance Research, Radiology, Medical School, University of Minnesota, Minneapolis, MN, United States
| | - Erpeng Dai
- Department of Radiology, Stanford University, Stanford, CA, United States
| | - Edward J. Auerbach
- Center for Magnetic Resonance Research, Radiology, Medical School, University of Minnesota, Minneapolis, MN, United States
| | - Hua Guo
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Kâmil Uğurbil
- Center for Magnetic Resonance Research, Radiology, Medical School, University of Minnesota, Minneapolis, MN, United States
| | - Xiaoping Wu
- Center for Magnetic Resonance Research, Radiology, Medical School, University of Minnesota, Minneapolis, MN, United States
| |
Collapse
|
7
|
Zhang J, Spincemaille P, Zhang H, Nguyen TD, Li C, Li J, Kovanlikaya I, Sabuncu MR, Wang Y. LARO: Learned acquisition and reconstruction optimization to accelerate quantitative susceptibility mapping. Neuroimage 2023; 268:119886. [PMID: 36669747 PMCID: PMC10021353 DOI: 10.1016/j.neuroimage.2023.119886] [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: 10/31/2022] [Revised: 12/12/2022] [Accepted: 01/16/2023] [Indexed: 01/19/2023] Open
Abstract
Quantitative susceptibility mapping (QSM) involves acquisition and reconstruction of a series of images at multi-echo time points to estimate tissue field, which prolongs scan time and requires specific reconstruction technique. In this paper, we present our new framework, called Learned Acquisition and Reconstruction Optimization (LARO), which aims to accelerate the multi-echo gradient echo (mGRE) pulse sequence for QSM. Our approach involves optimizing a Cartesian multi-echo k-space sampling pattern with a deep reconstruction network. Next, this optimized sampling pattern was implemented in an mGRE sequence using Cartesian fan-beam k-space segmenting and ordering for prospective scans. Furthermore, we propose to insert a recurrent temporal feature fusion module into the reconstruction network to capture signal redundancies along echo time. Our ablation studies show that both the optimized sampling pattern and proposed reconstruction strategy help improve the quality of the multi-echo image reconstructions. Generalization experiments show that LARO is robust on the test data with new pathologies and different sequence parameters. Our code is available at https://github.com/Jinwei1209/LARO-QSM.git.
Collapse
Affiliation(s)
- Jinwei Zhang
- Department of Biomedical Engineering, Cornell University, Ithaca, NY, USA; Department of Radiology, Weill Medical College of Cornell University, New York, NY, USA
| | - Pascal Spincemaille
- Department of Radiology, Weill Medical College of Cornell University, New York, NY, USA
| | - Hang Zhang
- Department of Radiology, Weill Medical College of Cornell University, New York, NY, USA; Department of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA
| | - Thanh D Nguyen
- Department of Radiology, Weill Medical College of Cornell University, New York, NY, USA
| | - Chao Li
- Department of Radiology, Weill Medical College of Cornell University, New York, NY, USA; Department of Applied Physics, Cornell University, Ithaca, NY, USA
| | - Jiahao Li
- Department of Biomedical Engineering, Cornell University, Ithaca, NY, USA; Department of Radiology, Weill Medical College of Cornell University, New York, NY, USA
| | - Ilhami Kovanlikaya
- Department of Radiology, Weill Medical College of Cornell University, New York, NY, USA
| | - Mert R Sabuncu
- Department of Radiology, Weill Medical College of Cornell University, New York, NY, USA; Department of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA
| | - Yi Wang
- Department of Biomedical Engineering, Cornell University, Ithaca, NY, USA; Department of Radiology, Weill Medical College of Cornell University, New York, NY, USA.
| |
Collapse
|
8
|
Wang Y, Pang Y, Tong C. DSMENet: Detail and Structure Mutually Enhancing Network for under-sampled MRI reconstruction. Comput Biol Med 2023; 154:106204. [PMID: 36716684 DOI: 10.1016/j.compbiomed.2022.106204] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2022] [Revised: 09/21/2022] [Accepted: 10/09/2022] [Indexed: 02/01/2023]
Abstract
Reconstructing zero-filled MR images (ZF) from partial k-space by convolutional neural networks (CNN) is an important way to accelerate MRI. However, due to the lack of attention to different components in ZF, it is challenging to learn the mapping from ZF to targets effectively. To ameliorate this issue, we propose a Detail and Structure Mutually Enhancing Network (DSMENet), which benefits from the complementary of the Structure Reconstruction UNet (SRUN) and the Detail Feature Refinement Module (DFRM). The SRUN learns structure-dominated information at multiple scales. And the DRFM enriches detail-dominated information from coarse to fine. The bidirectional alternate connections then exchange information between them. Moreover, the Detail Representation Construction Module (DRCM) extracts valuable initial detail representation for DFRM. And the Detail Guided Fusion Module (DGFM) facilitates the deep fusion of these complementary information. With the help of them, various components in ZF can be applied with discriminative attentions and mutually enhanced. In addition, the performance can be further improved by the Deep Enhanced Restoration (DER), a strategy based on recursion and constrain. Extensive experiments on fastMRI and CC-359 datasets demonstrate that DSMENet has robustness in terms of various body parts, under-sampling rates, and masks. Furthermore, DSMENet can achieve promising performance on qualitative and quantitative results, especially the competitive NMSE of 0.0268, PSNE of 33.7, and SSIM of 0.7808 on fastMRI 4 × single-coil knee leaderboard.
Collapse
Affiliation(s)
- Yueze Wang
- TJK-BIIT Lab, School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China.
| | - Yanwei Pang
- TJK-BIIT Lab, School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China.
| | - Chuan Tong
- TJK-BIIT Lab, School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China.
| |
Collapse
|
9
|
Lyu J, Li Y, Yan F, Chen W, Wang C, Li R. Multi-channel GAN-based calibration-free diffusion-weighted liver imaging with simultaneous coil sensitivity estimation and reconstruction. Front Oncol 2023; 13:1095637. [PMID: 36845688 PMCID: PMC9945270 DOI: 10.3389/fonc.2023.1095637] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/11/2022] [Accepted: 01/09/2023] [Indexed: 02/10/2023] Open
Abstract
Introduction Diffusion-weighted imaging (DWI) with parallel reconstruction may suffer from a mismatch between the coil calibration scan and imaging scan due to motions, especially for abdominal imaging. Methods This study aimed to construct an iterative multichannel generative adversarial network (iMCGAN)-based framework for simultaneous sensitivity map estimation and calibration-free image reconstruction. The study included 106 healthy volunteers and 10 patients with tumors. Results The performance of iMCGAN was evaluated in healthy participants and patients and compared with the SAKE, ALOHA-net, and DeepcomplexMRI reconstructions. The peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), root mean squared error (RMSE), and histograms of apparent diffusion coefficient (ADC) maps were calculated for assessing image qualities. The proposed iMCGAN outperformed the other methods in terms of the PSNR (iMCGAN: 41.82 ± 2.14; SAKE: 17.38 ± 1.78; ALOHA-net: 20.43 ± 2.11 and DeepcomplexMRI: 39.78 ± 2.78) for b = 800 DWI with an acceleration factor of 4. Besides, the ghosting artifacts in the SENSE due to the mismatch between the DW image and the sensitivity maps were avoided using the iMCGAN model. Discussion The current model iteratively refined the sensitivity maps and the reconstructed images without additional acquisitions. Thus, the quality of the reconstructed image was improved, and the aliasing artifact was alleviated when motions occurred during the imaging procedure.
Collapse
Affiliation(s)
- Jun Lyu
- School of Computer and Control Engineering, Yantai University, Yantai, Shandong, China
| | - Yan Li
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China,College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Fuhua Yan
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China,College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Weibo Chen
- Philips Healthcare (China), Shanghai, China
| | - Chengyan Wang
- Human Phenome Institute, Fudan University, Shanghai, China,*Correspondence: Chengyan Wang, ; Ruokun Li,
| | - Ruokun Li
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China,College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine, Shanghai, China,*Correspondence: Chengyan Wang, ; Ruokun Li,
| |
Collapse
|
10
|
Munoz C, Fotaki A, Botnar RM, Prieto C. Latest Advances in Image Acceleration: All Dimensions are Fair Game. J Magn Reson Imaging 2023; 57:387-402. [PMID: 36205716 PMCID: PMC10092100 DOI: 10.1002/jmri.28462] [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: 06/16/2022] [Revised: 09/20/2022] [Accepted: 09/22/2022] [Indexed: 01/20/2023] Open
Abstract
Magnetic resonance imaging (MRI) is a versatile modality that can generate high-resolution images with a variety of tissue contrasts. However, MRI is a slow technique and requires long acquisition times, which increase with higher temporal and spatial resolution and/or when multiple contrasts and large volumetric coverage is required. In order to speedup MR data acquisition, several approaches have been introduced in the literature. Most of these techniques acquire less data than required and exploit intrinsic redundancies in the MR images to recover the information that was not sampled. This article presents a review of MR acquisition and reconstruction methods that have exploited redundancies in the temporal, spatial, and contrast/parametric dimensions to accelerate image data acquisition, focusing on cardiac and abdominal MR imaging applications. The review describes how each of these dimensions has been separately exploited for speeding up MR acquisition to then discuss more advanced techniques where multiple dimensions are exploited together for further reducing scan times. Finally, future directions for multidimensional image acceleration and remaining technical challenges are discussed. EVIDENCE LEVEL: 5 TECHNICAL EFFICACY: 1.
Collapse
Affiliation(s)
- Camila Munoz
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
| | - Anastasia Fotaki
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
| | - René M Botnar
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK.,Escuela de Ingeniería, Pontificia Universidad Católica de Chile, Santiago, Chile.,Millenium Institute for Intelligent Healthcare Engineering iHEALTH, Santiago, Chile
| | - Claudia Prieto
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK.,Escuela de Ingeniería, Pontificia Universidad Católica de Chile, Santiago, Chile.,Millenium Institute for Intelligent Healthcare Engineering iHEALTH, Santiago, Chile
| |
Collapse
|
11
|
Wave-Encoded Model-Based Deep Learning for Highly Accelerated Imaging with Joint Reconstruction. BIOENGINEERING (BASEL, SWITZERLAND) 2022; 9:bioengineering9120736. [PMID: 36550942 PMCID: PMC9774601 DOI: 10.3390/bioengineering9120736] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/09/2022] [Revised: 11/21/2022] [Accepted: 11/25/2022] [Indexed: 12/03/2022]
Abstract
A recently introduced model-based deep learning (MoDL) technique successfully incorporates convolutional neural network (CNN)-based regularizers into physics-based parallel imaging reconstruction using a small number of network parameters. Wave-controlled aliasing in parallel imaging (CAIPI) is an emerging parallel imaging method that accelerates imaging acquisition by employing sinusoidal gradients in the phase- and slice/partition-encoding directions during the readout to take better advantage of 3D coil sensitivity profiles. We propose wave-encoded MoDL (wave-MoDL) combining the wave-encoding strategy with unrolled network constraints for highly accelerated 3D imaging while enforcing data consistency. We extend wave-MoDL to reconstruct multicontrast data with CAIPI sampling patterns to leverage similarity between multiple images to improve the reconstruction quality. We further exploit this to enable rapid quantitative imaging using an interleaved look-locker acquisition sequence with T2 preparation pulse (3D-QALAS). Wave-MoDL enables a 40 s MPRAGE acquisition at 1 mm resolution at 16-fold acceleration. For quantitative imaging, wave-MoDL permits a 1:50 min acquisition for T1, T2, and proton density mapping at 1 mm resolution at 12-fold acceleration, from which contrast-weighted images can be synthesized as well. In conclusion, wave-MoDL allows rapid MR acquisition and high-fidelity image reconstruction and may facilitate clinical and neuroscientific applications by incorporating unrolled neural networks into wave-CAIPI reconstruction.
Collapse
|
12
|
Ryu K, Alkan C, Vasanawala SS. Improving high frequency image features of deep learning reconstructions via k-space refinement with null-space kernel. Magn Reson Med 2022; 88:1263-1272. [PMID: 35426470 PMCID: PMC9246879 DOI: 10.1002/mrm.29261] [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: 12/15/2021] [Revised: 03/20/2022] [Accepted: 03/21/2022] [Indexed: 11/12/2022]
Abstract
PURPOSE Deep learning (DL) based reconstruction using unrolled neural networks has shown great potential in accelerating MRI. However, one of the major drawbacks is the loss of high-frequency details and textures in the output. The purpose of the study is to propose a novel refinement method that uses null-space kernel to refine k-space and improve blurred image details and textures. METHODS The proposed method constrains the output of the DL to comply to the linear neighborhood relationship calibrated in the auto-calibration lines. To demonstrate efficacy, we tested our refinement method on the DL reconstruction under a variety of conditions (i.e., dataset, unrolled neural networks, and under-sampling scheme). Specifically, the method was tested on three large-scale public datasets (knee and brain) from fastMRI's multi-coil track. RESULTS The proposed scheme visually reduces the structural error in the k-space domain, enhance the homogeneity of the k-space intensity. Consequently, reconstructed image shows sharper images with enhanced details and textures. The proposed method is also successful in improving high-frequency image details (SSIM, GMSD) without sacrificing overall image error (PSNR). CONCLUSION Our findings imply that refining DL output using the proposed method may generally improve DL reconstruction as tested with various large-scale dataset and networks.
Collapse
Affiliation(s)
- Kanghyun Ryu
- Department of Radiology, Stanford University, CA, USA
| | - Cagan Alkan
- Department of Electrical Engineering, Stanford University, CA, USA
| | | |
Collapse
|
13
|
Liu X, Pang Y, Jin R, Liu Y, Wang Z. Dual-Domain Reconstruction Network with V-Net and K-Net for Fast MRI. Magn Reson Med 2022; 88:2694-2708. [PMID: 35942977 DOI: 10.1002/mrm.29400] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/23/2022] [Revised: 07/05/2022] [Accepted: 07/08/2022] [Indexed: 11/10/2022]
Abstract
PURPOSE To introduce a dual-domain reconstruction network with V-Net and K-Net for accurate MR image reconstruction from undersampled k-space data. METHODS Most state-of-the-art reconstruction methods apply U-Net or cascaded U-Nets in the image domain and/or k-space domain. Nevertheless, these methods have the following problems: (1) directly applying U-Net in the k-space domain is not optimal for extracting features; (2) classical image-domain-oriented U-Net is heavyweighted and hence inefficient when cascaded many times to yield good reconstruction accuracy; (3) classical image-domain-oriented U-Net does not make full use of information of the encoder network for extracting features in the decoder network; and (4) existing methods are ineffective in simultaneously extracting and fusing features in the image domain and its dual k-space domain. To tackle these problems, we present 3 different methods: (1) V-Net, an image-domain encoder-decoder subnetwork that is more lightweight for cascading and effective in fully utilizing features in the encoder for decoding; (2) K-Net, a k-space domain subnetwork that is more suitable for extracting hierarchical features in the k-space domain, and (3) KV-Net, a dual-domain reconstruction network in which V-Nets and K-Nets are effectively combined and cascaded. RESULTS Extensive experimental results on the fastMRI dataset demonstrate that the proposed KV-Net can reconstruct high-quality images and outperform state-of-the-art approaches with fewer parameters. CONCLUSIONS To reconstruct images effectively and efficiently from incomplete k-space data, we have presented a dual-domain KV-Net to combine K-Nets and V-Nets. The KV-Net achieves better results with 9% and 5% parameters than comparable methods (XPD-Net and i-RIM).
Collapse
Affiliation(s)
- Xiaohan Liu
- Tianjin Key Lab. of Brain Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, People's Republic of China
| | - Yanwei Pang
- Tianjin Key Lab. of Brain Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, People's Republic of China
| | - Ruiqi Jin
- Tianjin Key Lab. of Brain Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, People's Republic of China
| | - Yu Liu
- Tianjin Key Lab. of Brain Inspired Intelligence Technology, School of Electrical and Information Engineering, Tianjin University, Tianjin, People's Republic of China
| | - Zhenchang Wang
- Beijing Friendship Hospital, Capital Medical University, Beijing, People's Republic of China
| |
Collapse
|
14
|
Zhang J, Han L, Sun J, Wang Z, Xu W, Chu Y, Xia L, Jiang M. Compressed sensing based dynamic MR image reconstruction by using 3D-total generalized variation and tensor decomposition: k-t TGV-TD. BMC Med Imaging 2022; 22:101. [PMID: 35624425 PMCID: PMC9137209 DOI: 10.1186/s12880-022-00826-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/08/2021] [Accepted: 05/18/2022] [Indexed: 11/10/2022] Open
Abstract
PURPOSE Compressed Sensing Magnetic Resonance Imaging (CS-MRI) is a promising technique to accelerate dynamic cardiac MR imaging (DCMRI). For DCMRI, the CS-MRI usually exploits image signal sparsity and low-rank property to reconstruct dynamic images from the undersampled k-space data. In this paper, a novel CS algorithm is investigated to improve dynamic cardiac MR image reconstruction quality under the condition of minimizing the k-space recording. METHODS The sparse representation of 3D cardiac magnetic resonance data is implemented by synergistically integrating 3D total generalized variation (3D-TGV) algorithm and high order singular value decomposition (HOSVD) based Tensor Decomposition, termed k-t TGV-TD method. In the proposed method, the low rank structure of the 3D dynamic cardiac MR data is performed with the HOSVD method, and the localized image sparsity is achieved by the 3D-TGV method. Moreover, the Fast Composite Splitting Algorithm (FCSA) method, combining the variable splitting with operator splitting techniques, is employed to solve the low-rank and sparse problem. Two different cardiac MR datasets (cardiac perfusion and cine MR datasets) are used to evaluate the performance of the proposed method. RESULTS Compared with the state-of-art methods, such as k-t SLR, 3D-TGV, HOSVD based tensor decomposition and low-rank plus sparse method, the proposed k-t TGV-TD method can offer improved reconstruction accuracy in terms of higher peak SNR (PSNR) and structural similarity index (SSIM). The proposed k-t TGV-TD method can achieve significantly better and stable reconstruction results than state-of-the-art methods in terms of both PSNR and SSIM, especially for cardiac perfusion MR dataset. CONCLUSIONS This work proved that the k-t TGV-TD method was an effective sparse representation way for DCMRI, which was capable of significantly improving the reconstruction accuracy with different acceleration factors.
Collapse
Affiliation(s)
- Jucheng Zhang
- Department of Clinical Engineering, The Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, 310019, People's Republic of China
| | - Lulu Han
- School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou, 310018, People's Republic of China.,Zhejiang Aerospace HengJia Data Technology Co., Ltd., Jiaxing, People's Republic of China
| | - Jianzhong Sun
- Department of Radiology, The Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, 310027, People's Republic of China
| | - Zhikang Wang
- Department of Clinical Engineering, The Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, 310019, People's Republic of China
| | - Wenlong Xu
- Department of Biomedical Engineering, China Jiliang University, Hangzhou, 310018, People's Republic of China
| | - Yonghua Chu
- Department of Clinical Engineering, The Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, 310019, People's Republic of China
| | - Ling Xia
- Department of Biomedical Engineering, Zhejiang University, Hangzhou, 310027, People's Republic of China
| | - Mingfeng Jiang
- School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou, 310018, People's Republic of China.
| |
Collapse
|
15
|
Sun C, Robinson A, Wang Y, Bilchick KC, Kramer CM, Weller D, Salerno M, Epstein FH. A Slice-Low-Rank Plus Sparse (slice-L + S) Reconstruction Method for k-t Undersampled Multiband First-Pass Myocardial Perfusion MRI. Magn Reson Med 2022; 88:1140-1155. [PMID: 35608225 PMCID: PMC9325064 DOI: 10.1002/mrm.29281] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2021] [Revised: 03/14/2022] [Accepted: 04/11/2022] [Indexed: 11/19/2022]
Abstract
Purpose The synergistic use of k‐t undersampling and multiband (MB) imaging has the potential to provide extended slice coverage and high spatial resolution for first‐pass perfusion MRI. The low‐rank plus sparse (L + S) model has shown excellent performance for accelerating single‐band (SB) perfusion MRI. Methods A MB data consistency method employing ESPIRiT maps and through‐plane coil information was developed. This data consistency method was combined with the temporal L + S constraint to form the slice‐L + S method. Slice‐L + S was compared to SB L + S and the sequential operations of split slice‐GRAPPA and SB L + S (seq‐SG‐L + S) using synthetic data formed from multislice SB images. Prospectively k‐t undersampled MB data were also acquired and reconstructed using seq‐SG‐L + S and slice‐L + S. Results Using synthetic data with total acceleration rates of 6–12, slice‐L + S outperformed SB L + S and seq‐SG‐L + S (N = 7 subjects) with respect to normalized RMSE and the structural similarity index (P < 0.05 for both). For the specific case with MB factor = 3 and rate 3 undersampling, or for SB imaging with rate 9 undersampling (N = 7 subjects), the normalized RMSE values were 0.037 ± 0.007, 0.042 ± 0.005, and 0.031 ± 0.004; and the structural similarity index values were 0.88 ± 0.03, 0.85 ± 0.03, and 0.89 ± 0.02 for SB L + S, seq‐SG‐L + S, and slice‐L + S, respectively (P < 0.05 for both). For prospectively undersampled MB data, slice‐L + S provided better image quality than seq‐SG‐L + S for rate 6 (N = 7) and rate 9 acceleration (N = 7) as scored by blinded experts. Conclusion Slice‐L + S outperformed SB‐L + S and seq‐SG‐L + S and provides 9 slice coverage of the left ventricle with a spatial resolution of 1.5 mm × 1.5 mm with good image quality.
Collapse
Affiliation(s)
- Changyu Sun
- Department of Biomedical Engineering, University of Virginia, Charlottesville, Virginia.,Department of Biomedical, Biological and Chemical Engineering, University of Missouri, Columbia, Missouri.,Department of Radiology, University of Missouri, Columbia, Missouri
| | - Austin Robinson
- Department of Medicine, University of Virginia Health System, Charlottesville, Virginia
| | - Yu Wang
- Department of Biomedical Engineering, University of Virginia, Charlottesville, Virginia
| | - Kenneth C Bilchick
- Department of Medicine, University of Virginia Health System, Charlottesville, Virginia
| | - Christopher M Kramer
- Department of Medicine, University of Virginia Health System, Charlottesville, Virginia.,Department of Radiology, University of Virginia Health System, Charlottesville, Virginia
| | - Daniel Weller
- Department of Biomedical Engineering, University of Virginia, Charlottesville, Virginia.,Department of Radiology, University of Virginia Health System, Charlottesville, Virginia.,Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, Virginia
| | - Michael Salerno
- Department of Biomedical Engineering, University of Virginia, Charlottesville, Virginia.,Department of Medicine, University of Virginia Health System, Charlottesville, Virginia.,Department of Radiology, University of Virginia Health System, Charlottesville, Virginia
| | - Frederick H Epstein
- Department of Biomedical Engineering, University of Virginia, Charlottesville, Virginia.,Department of Radiology, University of Virginia Health System, Charlottesville, Virginia
| |
Collapse
|
16
|
Temporospatial characterization of ventricular wall motion with real-time cardiac magnetic resonance imaging in health and disease. Sci Rep 2022; 12:4070. [PMID: 35260729 PMCID: PMC8904443 DOI: 10.1038/s41598-022-08094-3] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2021] [Accepted: 02/21/2022] [Indexed: 11/11/2022] Open
Abstract
Cardiac magnetic resonance imaging (MRI) has been largely dependent on retrospective cine for data acquisition. Real-time imaging, although inferior in image quality to retrospective cine, is more informative about motion dynamics. We herein developed a real-time cardiac MRI approach to temporospatial characterization of left ventricle (LV) and right ventricle (RV) wall motion. This approach provided two temporospatial indices, temporal periodicity and spatial coherence, for quantitative assessment of ventricular function. In a cardiac MRI study, we prospectively investigated temporospatial characterization in reference to standard volumetric measurements with retrospective cine. The temporospatial indices were found to be effective for evaluating the difference of ventricular performance between the healthy volunteers and the heart failure (HF) patients (LV temporal periodicity 0.24 ± 0.037 vs. 0.14 ± 0.021; RV temporal periodicity 0.18 ± 0.030 vs. 0.10 ± 0.014; LV spatial coherence 0.52 ± 0.039 vs. 0.38 ± 0.040; RV spatial coherence 0.50 ± 0.036 vs. 0.35 ± 0.035; all in arbitrary unit). The HF patients and healthy volunteers were well differentiated in the scatter plots of spatial coherence and temporal periodicity while they were mixed in those of end-systolic volume (ESV) and ejection fraction (EF) from volumetric measurements. This study demonstrated the potential of real-time cardiac MRI for intricate analysis of ventricular function beyond retrospective cine.
Collapse
|
17
|
Tian Q, Li Z, Fan Q, Polimeni JR, Bilgic B, Salat DH, Huang SY. SDnDTI: Self-supervised deep learning-based denoising for diffusion tensor MRI. Neuroimage 2022; 253:119033. [PMID: 35240299 DOI: 10.1016/j.neuroimage.2022.119033] [Citation(s) in RCA: 26] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/09/2021] [Revised: 02/15/2022] [Accepted: 02/21/2022] [Indexed: 12/12/2022] Open
Abstract
Diffusion tensor magnetic resonance imaging (DTI) is a widely adopted neuroimaging method for the in vivo mapping of brain tissue microstructure and white matter tracts. Nonetheless, the noise in the diffusion-weighted images (DWIs) decreases the accuracy and precision of DTI derived microstructural parameters and leads to prolonged acquisition time for achieving improved signal-to-noise ratio (SNR). Deep learning-based image denoising using convolutional neural networks (CNNs) has superior performance but often requires additional high-SNR data for supervising the training of CNNs, which reduces the feasibility of supervised learning-based denoising in practice. In this work, we develop a self-supervised deep learning-based method entitled "SDnDTI" for denoising DTI data, which does not require additional high-SNR data for training. Specifically, SDnDTI divides multi-directional DTI data into many subsets of six DWI volumes and transforms DWIs from each subset to along the same diffusion-encoding directions through the diffusion tensor model, generating multiple repetitions of DWIs with identical image contrasts but different noise observations. SDnDTI removes noise by first denoising each repetition of DWIs using a deep 3-dimensional CNN with the average of all repetitions with higher SNR as the training target, following the same approach as normal supervised learning based denoising methods, and then averaging CNN-denoised images for achieving higher SNR. The denoising efficacy of SDnDTI is demonstrated in terms of the similarity of output images and resultant DTI metrics compared to the ground truth generated using substantially more DWI volumes on two datasets with different spatial resolutions, b-values and numbers of input DWI volumes provided by the Human Connectome Project (HCP) and the Lifespan HCP in Aging. The SDnDTI results preserve image sharpness and textural details and substantially improve upon those from the raw data. The results of SDnDTI are comparable to those from supervised learning-based denoising and outperform those from state-of-the-art conventional denoising algorithms including BM4D, AONLM and MPPCA. By leveraging domain knowledge of diffusion MRI physics, SDnDTI makes it easier to use CNN-based denoising methods in practice and has the potential to benefit a wider range of research and clinical applications that require accelerated DTI acquisition and high-quality DTI data for mapping of tissue microstructure, fiber tracts and structural connectivity in the living human brain.
Collapse
Affiliation(s)
- Qiyuan Tian
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, 149 13th Street, Charlestown, MA 02129, United States; Department of Radiology, Harvard Medical School, Boston, MA, United States.
| | - Ziyu Li
- Department of Biomedical Engineering, Tsinghua University, Beijing, PR China
| | - Qiuyun Fan
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, 149 13th Street, Charlestown, MA 02129, United States; Department of Radiology, Harvard Medical School, Boston, MA, United States
| | - Jonathan R Polimeni
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, 149 13th Street, Charlestown, MA 02129, United States; Department of Radiology, Harvard Medical School, Boston, MA, United States; Harvard-MIT Division of Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge, MA, United States
| | - Berkin Bilgic
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, 149 13th Street, Charlestown, MA 02129, United States; Department of Radiology, Harvard Medical School, Boston, MA, United States; Harvard-MIT Division of Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge, MA, United States
| | - David H Salat
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, 149 13th Street, Charlestown, MA 02129, United States; Department of Radiology, Harvard Medical School, Boston, MA, United States
| | - Susie Y Huang
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, 149 13th Street, Charlestown, MA 02129, United States; Department of Radiology, Harvard Medical School, Boston, MA, United States; Harvard-MIT Division of Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge, MA, United States
| |
Collapse
|
18
|
Ilicak E, Saritas EU, Çukur T. Automated Parameter Selection for Accelerated MRI Reconstruction via Low-Rank Modeling of Local k-Space Neighborhoods. Z Med Phys 2022:S0939-3889(22)00008-3. [PMID: 35216887 DOI: 10.1016/j.zemedi.2022.02.002] [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: 09/23/2021] [Revised: 01/04/2022] [Accepted: 02/01/2022] [Indexed: 11/26/2022]
Abstract
PURPOSE Image quality in accelerated MRI rests on careful selection of various reconstruction parameters. A common yet tedious and error-prone practice is to hand-tune each parameter to attain visually appealing reconstructions. Here, we propose a parameter tuning strategy to automate hybrid parallel imaging (PI) - compressed sensing (CS) reconstructions via low-rank modeling of local k-space neighborhoods (LORAKS) supplemented with sparsity regularization in wavelet and total variation (TV) domains. METHODS For low-rank regularization, we leverage a soft-thresholding operation based on singular values for matrix rank selection in LORAKS. For sparsity regularization, we employ Stein's unbiased risk estimate criterion to select the wavelet regularization parameter and local standard deviation of reconstructions to select the TV regularization parameter. Comprehensive demonstrations are presented on a numerical brain phantom and in vivo brain and knee acquisitions. Quantitative assessments are performed via PSNR, SSIM and NMSE metrics. RESULTS The proposed hybrid PI-CS method improves reconstruction quality compared to PI-only techniques, and it achieves on par image quality to reconstructions with brute-force optimization of reconstruction parameters. These results are prominent across several different datasets and the range of examined acceleration rates. CONCLUSION A data-driven parameter tuning strategy to automate hybrid PI-CS reconstructions is presented. The proposed method achieves reliable reconstructions of accelerated multi-coil MRI datasets without the need for exhaustive hand-tuning of reconstruction parameters.
Collapse
Affiliation(s)
- Efe Ilicak
- Computer Assisted Clinical Medicine, Mannheim Institute for Intelligent Systems in Medicine, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany; National Magnetic Resonance Research Center (UMRAM), Bilkent University, Ankara, Turkey.
| | - Emine Ulku Saritas
- National Magnetic Resonance Research Center (UMRAM), Bilkent University, Ankara, Turkey; Department of Electrical and Electronics Engineering, Bilkent University, Ankara, Turkey; Neuroscience Program, Bilkent University, Ankara, Turkey
| | - Tolga Çukur
- National Magnetic Resonance Research Center (UMRAM), Bilkent University, Ankara, Turkey; Department of Electrical and Electronics Engineering, Bilkent University, Ankara, Turkey; Neuroscience Program, Bilkent University, Ankara, Turkey
| |
Collapse
|
19
|
Byanju R, Klein S, Cristobal-Huerta A, Hernandez-Tamames JA, Poot DH. Time efficiency analysis for undersampled quantitative MRI acquisitions. Med Image Anal 2022; 78:102390. [DOI: 10.1016/j.media.2022.102390] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2021] [Revised: 11/12/2021] [Accepted: 02/10/2022] [Indexed: 10/19/2022]
|
20
|
Pan T, Duan J, Wang J, Liu Y. Iterative self-consistent parallel magnetic resonance imaging reconstruction based on nonlocal low-rank regularization. Magn Reson Imaging 2022; 88:62-75. [DOI: 10.1016/j.mri.2022.01.012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/06/2021] [Revised: 12/14/2021] [Accepted: 01/26/2022] [Indexed: 10/19/2022]
|
21
|
Zibetti MVW, Knoll F, Regatte RR. Alternating Learning Approach for Variational Networks and Undersampling Pattern in Parallel MRI Applications. IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 2022; 8:449-461. [PMID: 35795003 PMCID: PMC9252023 DOI: 10.1109/tci.2022.3176129] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/23/2023]
Abstract
This work proposes an alternating learning approach to learn the sampling pattern (SP) and the parameters of variational networks (VN) in accelerated parallel magnetic resonance imaging (MRI). We investigate four variations of the learning approach, that alternates between improving the SP, using bias-accelerated subset selection, and improving parameters of the VN, using ADAM. The variations include the use of monotone or non-monotone alternating steps and systematic reduction of learning rates. The algorithms learn an effective pair to be used in future scans, including an SP that captures fewer k-space samples in which the generated undersampling artifacts are removed by the VN reconstruction. The quality of the VNs and SPs obtained by the proposed approaches is compared against different methods, including other kinds of joint learning methods and state-of-art reconstructions, on two different datasets at various acceleration factors (AF). We observed improvements visually and in three different figures of merit commonly used in deep learning (RMSE, SSIM, and HFEN) on AFs from 2 to 20 with brain and knee joint datasets when compared to the other approaches. The improvements ranged from 1% to 62% over the next best approach tested with VNs. The proposed approach has shown stable performance, obtaining similar learned SPs under different initial training conditions. We observe that the improvement is not only due to the learned sampling density, it is also due to the learned position of samples in k-space. The proposed approach was able to learn effective pairs of SPs and reconstruction VNs, improving 3D Cartesian accelerated parallel MRI applications.
Collapse
Affiliation(s)
- Marcelo V W Zibetti
- Department of Radiology of the New York University Grossman School of Medicine, New York, NY 10016 USA
| | - Florian Knoll
- Department of Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander University of Erlangen-Nurnberg, Erlangen, Germany
| | - Ravinder R Regatte
- Department of Radiology of the New York University Grossman School of Medicine, New York, NY 10016 USA
| |
Collapse
|
22
|
Reduced Acquisition Time per Bed Position for PET/MRI Using 68Ga-RM2 or 68Ga-PSMA-11 in Patients With Prostate Cancer: A Retrospective Analysis. AJR Am J Roentgenol 2021; 218:333-340. [PMID: 34406051 DOI: 10.2214/ajr.21.25961] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
Abstract
BACKGROUND. Growing clinical adoption of PET/MRI for prostate cancer (PC) evaluation has increased interest in reducing PET/MRI scanning times. Reducing acquisition time per bed position below current times of at least 5 minutes would allow shorter examination lengths. OBJECTIVE. The purpose of this study was to evaluate the effect of different reduced PET acquisition times in patients with PC who underwent 68Ga-PSMA-11 or 68Ga-RM2 PET/MRI using highly sensitive silicon photomultiplier-based PET detectors. METHODS. This study involved retrospective review of men with PC who underwent PET/MRI as part of one of two prospective trials. Fifty men (mean [± SD] age, 69.9 ± 6.8 years) who underwent 68Ga-RM2 PET/MRI and 50 men (mean age, 66.6 ± 5.7 years) who underwent 68Ga-PSMA-11 PET/MRI were included. PET/MRI used a time-of-flight-enabled system with silicon photomultiplier-based detectors. The acquisition time was 4 minutes per bed position. PET data were reconstructed using acquisition times of 30 seconds, 1 minute, 2 minutes, 3 minutes, and 4 minutes. Three readers independently assessed image quality for each reconstruction using a 5-point Likert scale (with 1 denoting nondiagnostic and 5 indicating excellent quality). One reader measured SUVmax for up to six lesions per patient. Two readers independently assessed lesion conspicuity using a a 3-point Likert scale (with 1 indicating that lesions were not visualized and 3 denoting that they were definitely visualized). RESULTS. Mean image quality across readers at 30 seconds, 1 minutes, 2 minutes, 3 minutes, and 4 minutes was, for 68Ga-RM2 PET/MRI, from 1.0 ± 0.2 to 1.7 ± 0.7, 2.0 ± 0.3 to 2.6 ± 0.8, 3.1 ± 0.5 to 3.9 ± 0.8, 4.6 ± 0.6 to 4.7 ± 0.6, and 4.8 ± 0.4 to 4.8 ± 0.5, respectively, and for 68Ga-PSMA-11 PET/MRI it was from 1.2 ± 0.4 to 1.8 ± 0.6, 2.2 ± 0.4 to 2.8 ± 0.7, 3.6 ± 0.6 to 4.1± 0.8, 4.8 ± 0.4 to 4.9 ± 0.4, and 4.9 ± 0.3 to 5.0 ± 0.2, respectively. The mean lesion SUVmax for 68Ga-RM2 PET/MRI was 11.1 ± 12.4, 10.2 ± 11.7, 9.6 ± 11.3, 9.5 ± 11.6, and 9.4 ± 11.6, respectively, and for 68Ga-PSMA-11 PET/MRI it was 14.7 ± 8.2, 12.9 ± 7.4, 12.1 ± 7.8, 11.7 ± 7.9, and 11.6 ± 7.9, respectively. Mean lesion conspicuity (reader 1/reader 2) was, for 68Ga-RM2 PET/MRI, 2.4 ± 0.5/2.7 ± 0.5, 2.9 ± 0.3/2.9 ± 0.3, 3.0 ± 0.0/3.0 ± 0.0, 3.0 ± 0.0/3.0 ± 0.0, and 3.0 ± 0.0/3.0 ± 0.0, respectively, and for 68Ga-PSMA-11 PET/MRI it was 2.6 ± 0.5/2.8 ± 0.4, 3.0 ± 0.2/2.9 ± 0.3, 3.0 ± 0.1/3.0 ± 0.2, 3.0 ± 0.0/3.0 ± 0.0, and 3.0 ± 0.0/3.0 ± 0.0, respectively. CONCLUSION. Our data support routine 3-minute acquisitions, which provided results very similar to those for 4-minute acquisitions. Two-minute acquisitions, although they lowered quality somewhat, provided acceptable performance and warrant consideration. CLINICAL IMPACT. When PC is evaluated using modern PET/MRI equipment, time per bed position may be reduced compared with historically used times. TRIAL REGISTRATION. ClinicalTrials.gov NCT02624518 and NCT02678351.
Collapse
|
23
|
Hu Z, Zhao C, Zhao X, Kong L, Yang J, Wang X, Liao J, Zhou Y. Joint reconstruction framework of compressed sensing and nonlinear parallel imaging for dynamic cardiac magnetic resonance imaging. BMC Med Imaging 2021; 21:182. [PMID: 34852771 PMCID: PMC8638482 DOI: 10.1186/s12880-021-00685-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2021] [Accepted: 10/06/2021] [Indexed: 02/08/2023] Open
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 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.
Collapse
Affiliation(s)
- Zhanqi Hu
- grid.452787.b0000 0004 1806 5224Shenzhen Children’s Hospital, Shenzhen, 518038 Guangdong China
| | - Cailei Zhao
- grid.452787.b0000 0004 1806 5224Shenzhen Children’s Hospital, Shenzhen, 518038 Guangdong China
| | - Xia Zhao
- grid.452787.b0000 0004 1806 5224Shenzhen Children’s Hospital, Shenzhen, 518038 Guangdong China
| | - Lingyu Kong
- grid.452787.b0000 0004 1806 5224Shenzhen Children’s Hospital, Shenzhen, 518038 Guangdong China
| | - Jun Yang
- grid.410726.60000 0004 1797 8419Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, Shenzhen, 518055 Guangdong China
| | - Xiaoyan Wang
- grid.464483.90000 0004 1799 4419School of Physics and Electronic Engineering, Yuxi Normal University, Yuxi, 653100 Yunnan China
| | - Jianxiang Liao
- grid.452787.b0000 0004 1806 5224Shenzhen Children’s Hospital, Shenzhen, 518038 Guangdong China
| | - Yihang Zhou
- grid.414329.90000 0004 1764 7097Hong Kong Sanatorium and Hospital, 5 A Kung Ngam Village Road, Shau Kei Wan, Hong Kong, China
| |
Collapse
|
24
|
Deep learning based multiplexed sensitivity-encoding (DL-MUSE) for high-resolution multi-shot DWI. Neuroimage 2021; 244:118632. [PMID: 34627977 DOI: 10.1016/j.neuroimage.2021.118632] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2021] [Revised: 09/27/2021] [Accepted: 10/01/2021] [Indexed: 11/22/2022] Open
Abstract
PURPOSE A phase correction method for high-resolution multi-shot (MSH) diffusion weighted imaging (DWI) is proposed. The efficacy and generalization capability of the method were validated on both healthy volunteers and patients. THEORY AND METHODS Conventionally, inter-shot phase variations for MSH echo-planar imaging (EPI) DWI are corrected by model-based algorithms. However, many acquisition imperfections are hard to measure accurately for conventional model-based methods, making the phase estimation and artifacts suppression unreliable. We propose a deep learning multiplexed sensitivity-encoding (DL-MUSE) framework to improve the phase estimations based on convolutional neural network (CNN) reconstruction. Aliasing-free single-shot (SSH) DW images, which have been used routinely in clinical settings, were used for training before the aliasing correction of MSH-DWI images. A dual-channel U-net comprising multiple convolutional layers was used for the phase estimation of MSH-EPI. The network was trained on a dataset containing 30 healthy volunteers and tested on another dataset of 52 healthy subjects and 15 patients with lesions or tumors with different shot numbers (4, 6 and 8). To further validate the generalization capability of our network, we acquired a dataset with different numbers of shots, TEs, partial Fourier factors, resolutions, ETLs, FOVs, coil numbers, and image orientations from two sites. We also compared the reconstruction performance of our proposed method with that of the conventional MUSE and SSH-EPI qualitatively and quantitatively. RESULTS Our results show that DL-MUSE is capable of correcting inter-shot phase errors with high and robust performance. Compared to conventional model-based MUSE, our method, by applying deep learning-based phase corrections, showed reduced distortion, noise level, and signal loss in high b-value DWIs. The improvements of image quality become more evident as the shot number increases from 4 to 8, especially in those central regions of the images, where g-factor artifacts are severe. Furthermore, the proposed method could provide the information about the orientation of the white matter with better consistency and achieve finer fibers delineation compared to the SSH-EPI method. Besides, the experiments on volunteers and patients from two different sites demonstrated the generalizability of our proposed method preliminarily. CONCLUSION A deep learning-based reconstruction algorithm for MSH-EPI images, which helps improve image quality greatly, was proposed. Results from healthy volunteers and tumor patients demonstrated the feasibility and generalization performances of our method for high-resolution MSH-EPI DWI, which can be used for routine clinical applications as well as neuroimaging research.
Collapse
|
25
|
Jia S, Qiu Z, Zhang L, Wang H, Yang G, Liu X, Liang D, Zheng H. Aliasing-free reduced field-of-view parallel imaging. Magn Reson Med 2021; 87:1574-1582. [PMID: 34752654 DOI: 10.1002/mrm.29046] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2021] [Revised: 09/20/2021] [Accepted: 09/27/2021] [Indexed: 11/12/2022]
Abstract
PURPOSE To reconstruct aliasing-free full field-of-view (FOV) images for reduced FOV (rFOV) parallel imaging (PI) with Cartesian and Wave sampling, which suffers from aliasing artifacts using existing PI methods. THEORY AND METHODS The sensitivity encoding method (SENSE) was extended to the Soft-SENSE models supporting multiple-set coil sensitivity maps (CSM) and point spread functions (PSF) for Cartesian and Wave sampled rFOV PI, respectively. The multiple-set CSM and PSF were created from full FOV CSM and PSF according to the image folding process induced by rFOV sampling. The Soft-SENSE reconstructions could be solved by the same algorithms for the conventional full FOV SENSE reconstruction. RESULTS Soft-SENSE using multiple-set full FOV CSM and PSF successfully reconstruct aliasing-free full FOV image from rFOV PI data with Cartesian and Wave sampling. The proposed rFOV PI enables flexible control of the aliasing and achieves comparable geometry factors as the standard full FOV PI with the same net acceleration factor. Reduced FOV PI improves the computational efficiency of iterative compressed sensing (CS) and PI reconstruction, especially for high-resolution volumetric imaging, thanks to the reduced fast Fourier transform (FFT) size. Moreover, rFOV PI reconstruction provides a potential alternative to the phase oversampling for the FOV aliasing problem. CONCLUSION The proposed Soft-SENSE using full FOV CSM and PSF could reconstruct aliasing-free full FOV image for rFOV PI, and make it a viable solution enabling more flexible PI acceleration and effectively improving the computational efficiency of iterative CSPI reconstruction.
Collapse
Affiliation(s)
- Sen Jia
- Paul C. Lauterbur Research Centre for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China
| | - Zhilang Qiu
- Paul C. Lauterbur Research Centre for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China.,Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, Shenzhen, Guangdong, China
| | - Lei Zhang
- Paul C. Lauterbur Research Centre for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China
| | - Haifeng Wang
- Paul C. Lauterbur Research Centre for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China
| | - Gang Yang
- Jinling Hospital, Medical School of Nanjing University, Nanjing, Jiangsu, China
| | - Xin Liu
- Paul C. Lauterbur Research Centre for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China
| | - Dong Liang
- Paul C. Lauterbur Research Centre for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China.,Research Centre of Medical AI, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China
| | - Hairong Zheng
- Paul C. Lauterbur Research Centre for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China
| |
Collapse
|
26
|
Koolstra K, Remis R. Learning a preconditioner to accelerate compressed sensing reconstructions in MRI. Magn Reson Med 2021; 87:2063-2073. [PMID: 34752655 PMCID: PMC9299023 DOI: 10.1002/mrm.29073] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2021] [Revised: 10/13/2021] [Accepted: 10/20/2021] [Indexed: 01/07/2023]
Abstract
Purpose To learn a preconditioner that accelerates parallel imaging (PI) and compressed sensing (CS) reconstructions. Methods A convolutional neural network (CNN) with residual connections was used to train a preconditioning operator. Training and validation data were simulated using 50% brain images and 50% white Gaussian noise images. Each multichannel training example contains a simulated sampling mask, complex coil sensitivity maps, and two regularization parameter maps. The trained model was integrated in the preconditioned conjugate gradient (PCG) method as part of the split Bregman CS method. The acceleration performance was compared with that of a circulant PI‐CS preconditioner for varying undersampling factors, number of coil elements and anatomies. Results The learned preconditioner reduces the number of PCG iterations by a factor of 4, yielding a similar acceleration as an efficient circulant preconditioner. The method generalizes well to different sampling schemes, coil configurations and anatomies. Conclusion It is possible to learn adaptable preconditioners for PI and CS reconstructions that meet the performance of state‐of‐the‐art preconditioners. Further acceleration could be achieved by optimizing the network architecture and the training set. Such a preconditioner could also be integrated in fully learned reconstruction methods to accelerate the training process of unrolled networks.
Collapse
Affiliation(s)
- Kirsten Koolstra
- Division of Image Processing, Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands
| | - Rob Remis
- Circuits & Systems Group, Electrical Engineering, Mathematics and Computer Science Faculty, Delft University of Technology, Delft, The Netherlands
| |
Collapse
|
27
|
Cheng J, Cui ZX, Huang W, Ke Z, Ying L, Wang H, Zhu Y, Liang D. Learning Data Consistency and its Application to Dynamic MR Imaging. IEEE TRANSACTIONS ON MEDICAL IMAGING 2021; 40:3140-3153. [PMID: 34252025 DOI: 10.1109/tmi.2021.3096232] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/13/2023]
Abstract
Magnetic resonance (MR) image reconstruction from undersampled k-space data can be formulated as a minimization problem involving data consistency and image prior. Existing deep learning (DL)-based methods for MR reconstruction employ deep networks to exploit the prior information and integrate the prior knowledge into the reconstruction under the explicit constraint of data consistency, without considering the real distribution of the noise. In this work, we propose a new DL-based approach termed Learned DC that implicitly learns the data consistency with deep networks, corresponding to the actual probability distribution of system noise. The data consistency term and the prior knowledge are both embedded in the weights of the networks, which provides an utterly implicit manner of learning reconstruction model. We evaluated the proposed approach with highly undersampled dynamic data, including the dynamic cardiac cine data with up to 24-fold acceleration and dynamic rectum data with the acceleration factor equal to the number of phases. Experimental results demonstrate the superior performance of the Learned DC both quantitatively and qualitatively than the state-of-the-art.
Collapse
|
28
|
Mani A, Santini T, Puppala R, Dahl M, Venkatesh S, Walker E, DeHaven M, Isitan C, Ibrahim TS, Wang L, Zhang T, Gong E, Barrios-Martinez J, Yeh FC, Krafty R, Mettenburg JM, Xia Z. Applying Deep Learning to Accelerated Clinical Brain Magnetic Resonance Imaging for Multiple Sclerosis. Front Neurol 2021; 12:685276. [PMID: 34646227 PMCID: PMC8504490 DOI: 10.3389/fneur.2021.685276] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2021] [Accepted: 08/24/2021] [Indexed: 11/14/2022] Open
Abstract
Background: Magnetic resonance (MR) scans are routine clinical procedures for monitoring people with multiple sclerosis (PwMS). Patient discomfort, timely scheduling, and financial burden motivate the need to accelerate MR scan time. We examined the clinical application of a deep learning (DL) model in restoring the image quality of accelerated routine clinical brain MR scans for PwMS. Methods: We acquired fast 3D T1w BRAVO and fast 3D T2w FLAIR MRI sequences (half the phase encodes and half the number of slices) in parallel to conventional parameters. Using a subset of the scans, we trained a DL model to generate images from fast scans with quality similar to the conventional scans and then applied the model to the remaining scans. We calculated clinically relevant T1w volumetrics (normalized whole brain, thalamic, gray matter, and white matter volume) for all scans and T2 lesion volume in a sub-analysis. We performed paired t-tests comparing conventional, fast, and fast with DL for these volumetrics, and fit repeated measures mixed-effects models to test for differences in correlations between volumetrics and clinically relevant patient-reported outcomes (PRO). Results: We found statistically significant but small differences between conventional and fast scans with DL for all T1w volumetrics. There was no difference in the extent to which the key T1w volumetrics correlated with clinically relevant PROs of MS symptom burden and neurological disability. Conclusion: A deep learning model that improves the image quality of the accelerated routine clinical brain MR scans has the potential to inform clinically relevant outcomes in MS.
Collapse
Affiliation(s)
- Ashika Mani
- Department of Biostatistics, University of Pittsburgh, Pittsburgh, PA, United States
| | - Tales Santini
- Department of Bioengineering, University of Pittsburgh, Pittsburgh, PA, United States
| | - Radhika Puppala
- Department of Neurology, University of Pittsburgh, Pittsburgh, PA, United States
| | - Megan Dahl
- Department of Neurology, University of Pittsburgh, Pittsburgh, PA, United States
| | - Shruthi Venkatesh
- Department of Neurology, University of Pittsburgh, Pittsburgh, PA, United States
| | - Elizabeth Walker
- Department of Neurology, University of Pittsburgh, Pittsburgh, PA, United States
| | - Megan DeHaven
- Department of Neurology, University of Pittsburgh, Pittsburgh, PA, United States
| | - Cigdem Isitan
- Department of Neurology, University of Pittsburgh, Pittsburgh, PA, United States
| | - Tamer S Ibrahim
- Department of Bioengineering, University of Pittsburgh, Pittsburgh, PA, United States
| | - Long Wang
- Subtle Medical Inc., Menlo Park, CA, United States
| | - Tao Zhang
- Subtle Medical Inc., Menlo Park, CA, United States
| | - Enhao Gong
- Subtle Medical Inc., Menlo Park, CA, United States
| | | | - Fang-Cheng Yeh
- Department of Neurological Surgery, University of Pittsburgh, Pittsburgh, PA, United States
| | - Robert Krafty
- Department of Biostatistics and Bioinformatics, Emory University, Atlanta, GA, United States
| | - Joseph M Mettenburg
- Department of Radiology, University of Pittsburgh, Pittsburgh, PA, United States
| | - Zongqi Xia
- Department of Bioengineering, University of Pittsburgh, Pittsburgh, PA, United States.,Department of Neurology, University of Pittsburgh, Pittsburgh, PA, United States
| |
Collapse
|
29
|
Dwork N, O'Connor D, Baron CA, Johnson EMI, Kerr AB, Pauly JM, Larson PEZ. Utilizing the Wavelet Transform's Structure in Compressed Sensing. SIGNAL, IMAGE AND VIDEO PROCESSING 2021; 15:1407-1414. [PMID: 34531930 PMCID: PMC8439112 DOI: 10.1007/s11760-021-01872-y] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/17/2020] [Revised: 01/11/2021] [Accepted: 02/08/2021] [Indexed: 06/13/2023]
Abstract
Compressed sensing has empowered quality image reconstruction with fewer data samples than previously thought possible. These techniques rely on a sparsifying linear transformation. The Daubechies wavelet transform is commonly used for this purpose. In this work, we take advantage of the structure of this wavelet transform and identify an affine transformation that increases the sparsity of the result. After inclusion of this affine transformation, we modify the resulting optimization problem to comply with the form of the Basis Pursuit Denoising problem. Finally, we show theoretically that this yields a lower bound on the error of the reconstruction and present results where solving this modified problem yields images of higher quality for the same sampling patterns using both magnetic resonance and optical images.
Collapse
Affiliation(s)
- Nicholas Dwork
- University of California, San Francisco, Department of Radiology and Biomedical Imaging
| | - Daniel O'Connor
- Department of Mathematics and Statistics, University of San Francisco
| | | | | | - Adam B Kerr
- Stanford University, Center for Cognitive and Neurobiological Imaging
| | - John M Pauly
- Stanford University, Department of Electrical Engineering
| | - Peder E Z Larson
- University of California, San Francisco, Department of Radiology and Biomedical Imaging
| |
Collapse
|
30
|
Klauser A, Strasser B, Thapa B, Lazeyras F, Andronesi O. Achieving high-resolution 1H-MRSI of the human brain with compressed-sensing and low-rank reconstruction at 7 Tesla. JOURNAL OF MAGNETIC RESONANCE (SAN DIEGO, CALIF. : 1997) 2021; 331:107048. [PMID: 34438355 PMCID: PMC8717865 DOI: 10.1016/j.jmr.2021.107048] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/05/2021] [Revised: 06/29/2021] [Accepted: 08/08/2021] [Indexed: 06/02/2023]
Abstract
Low sensitivity MR techniques such as magnetic resonance spectroscopic imaging (MRSI) greatly benefit from the gain in signal-to-noise provided by ultra-high field MR. High-resolution and whole-slab brain MRSI remains however very challenging due to lengthy acquisition, low signal, lipid contamination and field inhomogeneity. In this study, we propose an acquisition-reconstruction scheme that combines 1H free-induction-decay (FID)-MRSI sequence, short TR acquisition, compressed sensing acceleration and low-rank modeling with total-generalized-variation constraint to achieve metabolite imaging in two and three dimensions at 7 Tesla. The resulting images and volumes reveal highly detailed distributions that are specific to each metabolite and follow the underlying brain anatomy. The MRSI method was validated in a high-resolution phantom containing fine metabolite structures, and in five healthy volunteers. This new application of compressed sensing acceleration paves the way for high-resolution MRSI in clinical setting with acquisition times of 5 min for 2D MRSI at 2.5 mm and of 20 min for 3D MRSI at 3.3 mm isotropic.
Collapse
Affiliation(s)
- Antoine Klauser
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States; Department of Radiology and Medical Informatics, University of Geneva, Switzerland; Center for Biomedical Imaging (CIBM), Geneva, Switzerland.
| | - Bernhard Strasser
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States
| | - Bijaya Thapa
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States
| | - Francois Lazeyras
- Department of Radiology and Medical Informatics, University of Geneva, Switzerland; Center for Biomedical Imaging (CIBM), Geneva, Switzerland
| | - Ovidiu Andronesi
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States
| |
Collapse
|
31
|
Zibetti MVW, Herman GT, Regatte RR. Fast data-driven learning of parallel MRI sampling patterns for large scale problems. Sci Rep 2021; 11:19312. [PMID: 34588478 PMCID: PMC8481566 DOI: 10.1038/s41598-021-97995-w] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2021] [Accepted: 09/01/2021] [Indexed: 12/14/2022] Open
Abstract
In this study, a fast data-driven optimization approach, named bias-accelerated subset selection (BASS), is proposed for learning efficacious sampling patterns (SPs) with the purpose of reducing scan time in large-dimensional parallel MRI. BASS is applicable when Cartesian fully-sampled k-space measurements of specific anatomy are available for training and the reconstruction method for undersampled measurements is specified; such information is used to define the efficacy of any SP for recovering the values at the non-sampled k-space points. BASS produces a sequence of SPs with the aim of finding one of a specified size with (near) optimal efficacy. BASS was tested with five reconstruction methods for parallel MRI based on low-rankness and sparsity that allow a free choice of the SP. Three datasets were used for testing, two of high-resolution brain images ([Formula: see text]-weighted images and, respectively, [Formula: see text]-weighted images) and another of knee images for quantitative mapping of the cartilage. The proposed approach has low computational cost and fast convergence; in the tested cases it obtained SPs up to 50 times faster than the currently best greedy approach. Reconstruction quality increased by up to 45% over that provided by variable density and Poisson disk SPs, for the same scan time. Optionally, the scan time can be nearly halved without loss of reconstruction quality. Quantitative MRI and prospective accelerated MRI results show improvements. Compared with greedy approaches, BASS rapidly learns effective SPs for various reconstruction methods, using larger SPs and larger datasets; enabling better selection of sampling-reconstruction pairs for specific MRI problems.
Collapse
Affiliation(s)
- Marcelo V W Zibetti
- Center for Biomedical Imaging, Department of Radiology, New York University School of Medicine, New York, NY, 10016, USA.
| | - Gabor T Herman
- Center for Biomedical Imaging, Department of Radiology, New York University School of Medicine, New York, NY, 10016, USA
- Department of Computer Science, The Graduate Center, City University of New York, New York, NY, 10016, USA
| | - Ravinder R Regatte
- Center for Biomedical Imaging, Department of Radiology, New York University School of Medicine, New York, NY, 10016, USA
| |
Collapse
|
32
|
Park S, Park J. Global and local constrained parallel MRI reconstruction by exploiting dual sparsity and self-consistency. Biomed Signal Process Control 2021. [DOI: 10.1016/j.bspc.2021.102922] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
33
|
A deep cascade of ensemble of dual domain networks with gradient-based T1 assistance and perceptual refinement for fast MRI reconstruction. Comput Med Imaging Graph 2021; 91:101942. [PMID: 34087612 DOI: 10.1016/j.compmedimag.2021.101942] [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: 09/29/2020] [Revised: 05/03/2021] [Accepted: 05/14/2021] [Indexed: 11/23/2022]
Abstract
Deep learning networks have shown promising results in fast magnetic resonance imaging (MRI) reconstruction. In our work, we develop deep networks to further improve the quantitative and the perceptual quality of reconstruction. To begin with, we propose reconsynergynet (RSN), a network that combines the complementary benefits of independently operating on both the image and the Fourier domain. For a single-coil acquisition, we introduce deep cascade RSN (DC-RSN), a cascade of RSN blocks interleaved with data fidelity (DF) units. Secondly, we improve the structure recovery of DC-RSN for T2 weighted Imaging (T2WI) through assistance of T1 weighted imaging (T1WI), a sequence with short acquisition time. T1 assistance is provided to DC-RSN through a gradient of log feature (GOLF) fusion. Furthermore, we propose perceptual refinement network (PRN) to refine the reconstructions for better visual information fidelity (VIF), a metric highly correlated to radiologist's opinion on the image quality. Lastly, for multi-coil acquisition, we propose variable splitting RSN (VS-RSN), a deep cascade of blocks, each block containing RSN, multi-coil DF unit, and a weighted average module. We extensively validate our models DC-RSN and VS-RSN for single-coil and multi-coil acquisitions and report the state-of-the-art performance. We obtain a SSIM of 0.768, 0.923, and 0.878 for knee single-coil-4x, multi-coil-4x, and multi-coil-8x in fastMRI, respectively. We also conduct experiments to demonstrate the efficacy of GOLF based T1 assistance and PRN.
Collapse
|
34
|
Compressed sensing regularized calibrationless parallel magnetic resonance imaging via deep learning. Biomed Signal Process Control 2021. [DOI: 10.1016/j.bspc.2020.102399] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
35
|
Tian Q, Zaretskaya N, Fan Q, Ngamsombat C, Bilgic B, Polimeni JR, Huang SY. Improved cortical surface reconstruction using sub-millimeter resolution MPRAGE by image denoising. Neuroimage 2021; 233:117946. [PMID: 33711484 PMCID: PMC8421085 DOI: 10.1016/j.neuroimage.2021.117946] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2020] [Revised: 02/28/2021] [Accepted: 03/03/2021] [Indexed: 11/24/2022] Open
Abstract
Automatic cerebral cortical surface reconstruction is a useful tool for cortical anatomy quantification, analysis and visualization. Recently, the Human Connectome Project and several studies have shown the advantages of using T1-weighted magnetic resonance (MR) images with sub-millimeter isotropic spatial resolution instead of the standard 1-mm isotropic resolution for improved accuracy of cortical surface positioning and thickness estimation. Nonetheless, sub-millimeter resolution images are noisy by nature and require averaging multiple repetitions to increase the signal-to-noise ratio for precisely delineating the cortical boundary. The prolonged acquisition time and potential motion artifacts pose significant barriers to the wide adoption of cortical surface reconstruction at sub-millimeter resolution for a broad range of neuroscientific and clinical applications. We address this challenge by evaluating the cortical surface reconstruction resulting from denoised single-repetition sub-millimeter T1-weighted images. We systematically characterized the effects of image denoising on empirical data acquired at 0.6 mm isotropic resolution using three classical denoising methods, including denoising convolutional neural network (DnCNN), block-matching and 4-dimensional filtering (BM4D) and adaptive optimized non-local means (AONLM). The denoised single-repetition images were found to be highly similar to 6-repetition averaged images, with a low whole-brain averaged mean absolute difference of ~0.016, high whole-brain averaged peak signal-to-noise ratio of ~33.5 dB and structural similarity index of ~0.92, and minimal gray matter–white matter contrast loss (2% to 9%). The whole-brain mean absolute discrepancies in gray matter–white matter surface placement, gray matter–cerebrospinal fluid surface placement and cortical thickness estimation were lower than 165 μm, 155 μm and 145 μm—sufficiently accurate for most applications. These discrepancies were approximately one third to half of those from 1-mm isotropic resolution data. The denoising performance was equivalent to averaging ~2.5 repetitions of the data in terms of image similarity, and 1.6–2.2 repetitions in terms of the cortical surface placement accuracy. The scan-rescan variability of the cortical surface positioning and thickness estimation was lower than 170 μm. Our unique dataset and systematic characterization support the use of denoising methods for improved cortical surface reconstruction at sub-millimeter resolution.
Collapse
Affiliation(s)
- Qiyuan Tian
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Charlestown, MA, United States; Harvard Medical School, Boston, MA, United States.
| | - Natalia Zaretskaya
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Charlestown, MA, United States; Harvard Medical School, Boston, MA, United States; Institute of Psychology, University of Graz, Graz, Austria; BioTechMed-Graz, Austria
| | - Qiuyun Fan
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Charlestown, MA, United States; Harvard Medical School, Boston, MA, United States
| | - Chanon Ngamsombat
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Charlestown, MA, United States; Department of Radiology, Faculty of Medicine, Siriraj Hospital, Mahidol University, Thailand
| | - Berkin Bilgic
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Charlestown, MA, United States; Harvard Medical School, Boston, MA, United States; Harvard-MIT Division of Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge, MA, United States
| | - Jonathan R Polimeni
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Charlestown, MA, United States; Harvard Medical School, Boston, MA, United States; Harvard-MIT Division of Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge, MA, United States
| | - Susie Y Huang
- Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Charlestown, MA, United States; Harvard Medical School, Boston, MA, United States; Harvard-MIT Division of Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge, MA, United States
| |
Collapse
|
36
|
Sanders JW, Venkatesan AM, Levitt CA, Bathala T, Kudchadker RJ, Tang C, Bruno TL, Starks C, Santiago E, Wells M, Weaver CP, Ma J, Frank SJ. Fully Balanced SSFP Without an Endorectal Coil for Postimplant QA of MRI-Assisted Radiosurgery (MARS) of Prostate Cancer: A Prospective Study. Int J Radiat Oncol Biol Phys 2021; 109:614-625. [PMID: 32980498 DOI: 10.1016/j.ijrobp.2020.09.040] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2020] [Revised: 07/29/2020] [Accepted: 09/21/2020] [Indexed: 01/23/2023]
Abstract
PURPOSE To investigate fully balanced steady-state free precession (bSSFP) with optimized acquisition protocols for magnetic resonance imaging (MRI)-based postimplant quality assessment of low-dose-rate (LDR) prostate brachytherapy without an endorectal coil (ERC). METHODS AND MATERIALS Seventeen patients at a major academic cancer center who underwent MRI-assisted radiosurgery (MARS) LDR prostate cancer brachytherapy were imaged with moderate, high, or very high spatial resolution fully bSSFP MRIs without using an ERC. Between 1 and 3 signal averages (NEX) were acquired with acceleration factors (R) between 1 and 2, with the goal of keeping scan times between 4 and 6 minutes. Acquisitions with R >1 were reconstructed with parallel imaging and compressed sensing (PICS) algorithms. Radioactive seeds were identified by 3 medical dosimetrists. Additionally, some of the MRI techniques were implemented and tested at a community hospital; 3 patients underwent MARS LDR prostate brachytherapy and were imaged without an ERC. RESULTS Increasing the in-plane spatial resolution mitigated partial volume artifacts and improved overall seed and seed marker visualization at the expense of reduced signal-to-noise ratio (SNR). The reduced SNR as a result of imaging at higher spatial resolution and without an ERC was partially compensated for by the multi-NEX acquisitions enabled by PICS. Resultant image quality was superior to the current clinical standard. All 3 dosimetrists achieved near-perfect precision and recall for seed identification in the 17 patients. The 3 postimplant MRIs acquired at the community hospital were sufficient to identify 208 out of 211 seeds implanted without reference to computed tomography (CT). CONCLUSIONS Acquiring postimplant prostate brachytherapy MRI without an ERC has several advantages including better patient tolerance, lower costs, higher clinical throughput, and widespread access to precision LDR prostate brachytherapy. This prospective study confirms that the use of an ERC can be circumvented with fully bSSFP and advanced MRI scan techniques in a major academic cancer center and community hospital, potentially enabling postimplant assessment of MARS LDR prostate brachytherapy without CT.
Collapse
Affiliation(s)
- Jeremiah W Sanders
- Department of Imaging Physics, University of Texas MD Anderson Cancer Center, Houston, Texas; Medical Physics Graduate Program, MD Anderson Cancer Center UTHealth Graduate School of Biomedical Sciences, Houston, Texas.
| | | | - Chad A Levitt
- Department of Diagnostic Radiology, University of Texas MD Anderson Cancer Center, Houston, Texas
| | | | - Rajat J Kudchadker
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Chad Tang
- Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Teresa L Bruno
- Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Christine Starks
- Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Edwin Santiago
- Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Michelle Wells
- Department of Diagnostic Radiology, University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Carl P Weaver
- Department of Diagnostic Radiology, University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Jingfei Ma
- Department of Imaging Physics, University of Texas MD Anderson Cancer Center, Houston, Texas; Medical Physics Graduate Program, MD Anderson Cancer Center UTHealth Graduate School of Biomedical Sciences, Houston, Texas
| | - Steven J Frank
- Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, Texas
| |
Collapse
|
37
|
Liu R, Zhang Y, Cheng S, Luo Z, Fan X. A Deep Framework Assembling Principled Modules for CS-MRI: Unrolling Perspective, Convergence Behaviors, and Practical Modeling. IEEE TRANSACTIONS ON MEDICAL IMAGING 2020; 39:4150-4163. [PMID: 32746155 DOI: 10.1109/tmi.2020.3014193] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
Compressed Sensing Magnetic Resonance Imaging (CS-MRI) significantly accelerates MR acquisition at a sampling rate much lower than the Nyquist criterion. A major challenge for CS-MRI lies in solving the severely ill-posed inverse problem to reconstruct aliasing-free MR images from the sparse k -space data. Conventional methods typically optimize an energy function, producing restoration of high quality, but their iterative numerical solvers unavoidably bring extremely large time consumption. Recent deep techniques provide fast restoration by either learning direct prediction to final reconstruction or plugging learned modules into the energy optimizer. Nevertheless, these data-driven predictors cannot guarantee the reconstruction following principled constraints underlying the domain knowledge so that the reliability of their reconstruction process is questionable. In this paper, we propose a deep framework assembling principled modules for CS-MRI that fuses learning strategy with the iterative solver of a conventional reconstruction energy. This framework embeds an optimal condition checking mechanism, fostering efficient and reliable reconstruction. We also apply the framework to three practical tasks, i.e., complex-valued data reconstruction, parallel imaging and reconstruction with Rician noise. Extensive experiments on both benchmark and manufacturer-testing images demonstrate that the proposed method reliably converges to the optimal solution more efficiently and accurately than the state-of-the-art in various scenarios.
Collapse
|
38
|
Yuan Z, Jiang M, Wang Y, Wei B, Li Y, Wang P, Menpes-Smith W, Niu Z, Yang G. SARA-GAN: Self-Attention and Relative Average Discriminator Based Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction. Front Neuroinform 2020; 14:611666. [PMID: 33324189 PMCID: PMC7726262 DOI: 10.3389/fninf.2020.611666] [Citation(s) in RCA: 24] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2020] [Accepted: 11/05/2020] [Indexed: 11/17/2022] Open
Abstract
Research on undersampled magnetic resonance image (MRI) reconstruction can increase the speed of MRI imaging and reduce patient suffering. In this paper, an undersampled MRI reconstruction method based on Generative Adversarial Networks with the Self-Attention mechanism and the Relative Average discriminator (SARA-GAN) is proposed. In our SARA-GAN, the relative average discriminator theory is applied to make full use of the prior knowledge, in which half of the input data of the discriminator is true and half is fake. At the same time, a self-attention mechanism is incorporated into the high-layer of the generator to build long-range dependence of the image, which can overcome the problem of limited convolution kernel size. Besides, spectral normalization is employed to stabilize the training process. Compared with three widely used GAN-based MRI reconstruction methods, i.e., DAGAN, DAWGAN, and DAWGAN-GP, the proposed method can obtain a higher peak signal-to-noise ratio (PSNR) and structural similarity index measure(SSIM), and the details of the reconstructed image are more abundant and more realistic for further clinical scrutinization and diagnostic tasks.
Collapse
Affiliation(s)
- Zhenmou Yuan
- School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou, China
| | - Mingfeng Jiang
- School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou, China
| | - Yaming Wang
- School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou, China
| | - Bo Wei
- School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou, China
| | - Yongming Li
- College of Communication Engineering, Chongqing University, Chongqing, China
| | - Pin Wang
- College of Communication Engineering, Chongqing University, Chongqing, China
| | | | - Zhangming Niu
- Aladdin Healthcare Technologies Ltd., London, United Kingdom
| | - Guang Yang
- Cardiovascular Research Centre, Royal Brompton Hospital, London, United Kingdom
- National Heart and Lung Institute, Imperial College London, London, United Kingdom
| |
Collapse
|
39
|
Park S, Torrisi S, Townsend JD, Beckett A, Feinberg DA. Highly accelerated submillimeter resolution 3D GRASE with controlled T 2 blurring in T 2 -weighted functional MRI at 7 Tesla: A feasibility study. Magn Reson Med 2020; 85:2490-2506. [PMID: 33231890 DOI: 10.1002/mrm.28589] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2020] [Revised: 10/12/2020] [Accepted: 10/20/2020] [Indexed: 11/12/2022]
Abstract
PURPOSE To achieve highly accelerated submillimeter resolution T 2 -weighted functional MRI at 7T by developing a three-dimensional gradient and spin echo imaging (GRASE) with inner-volume selection and variable flip angles (VFA). METHODS GRASE imaging has disadvantages in that (a) k-space modulation causes T 2 blurring by limiting the number of slices and (b) a VFA scheme results in partial success with substantial SNR loss. In this work, accelerated GRASE with controlled T 2 blurring is developed to improve a point spread function (PSF) and temporal signal-to-noise ratio (tSNR) with a large number of slices. To this end, the VFA scheme is designed by minimizing a trade-off between SNR and blurring for functional sensitivity, and a new GRASE-optimized random encoding, which takes into account the complex signal decays of T 2 and T 2 ∗ weightings, is proposed by achieving incoherent aliasing for constrained reconstruction. Numerical and experimental studies were performed to validate the effectiveness of the proposed method over regular and VFA GRASE (R- and V-GRASE). RESULTS The proposed method, while achieving 0.8 mm isotropic resolution, functional MRI compared to R- and V-GRASE improves the spatial extent of the excited volume up to 36 slices with 52%-68% full width at half maximum (FWHM) reduction in PSF but approximately 2- to 3-fold mean tSNR improvement, thus resulting in higher BOLD activations. CONCLUSIONS We successfully demonstrated the feasibility of the proposed method in T 2 -weighted functional MRI. The proposed method is especially promising for cortical layer-specific functional MRI.
Collapse
Affiliation(s)
- Suhyung Park
- Helen Wills Neuroscience Institute, University of California, Berkeley, CA, USA.,Department of Computer Engineering, Chonnam National University, Gwangju, Republic of Korea
| | - Salvatore Torrisi
- Helen Wills Neuroscience Institute, University of California, Berkeley, CA, USA.,Advanced MRI Technologies, Sebastopol, CA, USA
| | - Jennifer D Townsend
- Helen Wills Neuroscience Institute, University of California, Berkeley, CA, USA.,Advanced MRI Technologies, Sebastopol, CA, USA
| | - Alexander Beckett
- Helen Wills Neuroscience Institute, University of California, Berkeley, CA, USA.,Advanced MRI Technologies, Sebastopol, CA, USA
| | - David A Feinberg
- Helen Wills Neuroscience Institute, University of California, Berkeley, CA, USA.,Advanced MRI Technologies, Sebastopol, CA, USA
| |
Collapse
|
40
|
Li YY, Zhang P, Rashid S, Cheng YJ, Li W, Schapiro W, Gliganic K, Yamashita AM, Grgas M, Haag E, Cao JJ. Real-time exercise stress cardiac MRI with Fourier-series reconstruction from golden-angle radial data. Magn Reson Imaging 2020; 75:89-99. [PMID: 33098934 DOI: 10.1016/j.mri.2020.10.010] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2020] [Revised: 09/30/2020] [Accepted: 10/18/2020] [Indexed: 10/23/2022]
Abstract
Magnetic resonance imaging (MRI) can measure cardiac response to exercise stress for evaluating and managing heart patients in the practice of clinical cardiology. However, exercise stress cardiac MRI have been clinically limited by the ability of available MRI techniques to quantitatively measure fast and unstable cardiac dynamics during exercise. The presented work is to develop a new real-time MRI technique for improved quantitative performance of exercise stress cardiac MRI. This technique seeks to represent real-time cardiac images as a sparse Fourier-series along the time. With golden-angle radial acquisition, parallel imaging and compressed sensing can be integrated into a linear system of equations for resolving Fourier coefficients that are in turn used to generate real-time cardiac images from the Fourier-series representation. Fourier-series reconstruction from golden-angle radial data can effectively address data insufficiency due to MRI speed limitation, providing a real-time approach to exercise stress cardiac MRI. To demonstrate the feasibility, an exercise stress cardiac MRI experiment was run to investigate biventricular response to in-scanner biking exercise in a cohort of sixteen healthy volunteers. It was found that Fourier-series reconstruction from golden-angle radial data effectively detected exercise-induced increase in stroke volume and ejection fraction in a healthy heart. The presented work will improve the applications of exercise stress cardiac MRI in the practice of clinical cardiology.
Collapse
Affiliation(s)
- Yu Y Li
- St. Francis Hospital, DeMatteis Center for Research and Education, Cardiac Imaging, 101 Northern Blvd, Greenvale, NY 11548, USA.
| | - Pengyue Zhang
- St. Francis Hospital, DeMatteis Center for Research and Education, Cardiac Imaging, 101 Northern Blvd, Greenvale, NY 11548, USA
| | - Shams Rashid
- St. Francis Hospital, DeMatteis Center for Research and Education, Cardiac Imaging, 101 Northern Blvd, Greenvale, NY 11548, USA.
| | - Yang J Cheng
- St. Francis Hospital, DeMatteis Center for Research and Education, Cardiac Imaging, 101 Northern Blvd, Greenvale, NY 11548, USA.
| | - Wenhui Li
- St. Francis Hospital, DeMatteis Center for Research and Education, Cardiac Imaging, 101 Northern Blvd, Greenvale, NY 11548, USA
| | - William Schapiro
- St. Francis Hospital, DeMatteis Center for Research and Education, Cardiac Imaging, 101 Northern Blvd, Greenvale, NY 11548, USA.
| | - Kathleen Gliganic
- St. Francis Hospital, DeMatteis Center for Research and Education, Cardiac Imaging, 101 Northern Blvd, Greenvale, NY 11548, USA.
| | - Ann-Marie Yamashita
- St. Francis Hospital, DeMatteis Center for Research and Education, Cardiac Imaging, 101 Northern Blvd, Greenvale, NY 11548, USA.
| | - Marie Grgas
- St. Francis Hospital, DeMatteis Center for Research and Education, Cardiac Imaging, 101 Northern Blvd, Greenvale, NY 11548, USA.
| | - Elizabeth Haag
- St. Francis Hospital, DeMatteis Center for Research and Education, Cardiac Imaging, 101 Northern Blvd, Greenvale, NY 11548, USA.
| | - J Jane Cao
- St. Francis Hospital, DeMatteis Center for Research and Education, Cardiac Imaging, 101 Northern Blvd, Greenvale, NY 11548, USA.
| |
Collapse
|
41
|
Arshad M, Qureshi M, Inam O, Omer H. Transfer learning in deep neural network based under-sampled MR image reconstruction. Magn Reson Imaging 2020; 76:96-107. [PMID: 32980504 DOI: 10.1016/j.mri.2020.09.018] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2020] [Revised: 08/10/2020] [Accepted: 09/08/2020] [Indexed: 01/27/2023]
Abstract
In Magnetic Resonance Imaging (MRI), the success of deep learning-based under-sampled MR image reconstruction depends on: (i) size of the training dataset, (ii) generalization capabilities of the trained neural network. Whenever there is a mismatch between the training and testing data, there is a need to retrain the neural network from scratch with thousands of MR images obtained using the same protocol. This may not be possible in MRI as it is costly and time consuming to acquire data. In this research, a transfer learning approach i.e. end-to-end fine tuning is proposed for U-Net to address the data scarcity and generalization problems of deep learning-based MR image reconstruction. First the generalization capabilities of a pre-trained U-Net (initially trained on the human brain images of 1.5 T scanner) are assessed for: (a) MR images acquired from MRI scanners of different magnetic field strengths, (b) MR images of different anatomies and (c) MR images under-sampled by different acceleration factors. Later, end-to-end fine tuning of the pre-trained U-Net is proposed for the reconstruction of the above-mentioned MR images (i.e. (a), (b) and (c)). The results show successful reconstructions obtained from the proposed method as reflected by the Structural SIMilarity index, Root Mean Square Error, Peak Signal-to-Noise Ratio and central line profile of the reconstructed images.
Collapse
Affiliation(s)
- Madiha Arshad
- Medical Image Processing Research Group (MIPRG), Department of Electrical and Computer Engineering, COMSATS University Islamabad, Pakistan
| | - Mahmood Qureshi
- Medical Image Processing Research Group (MIPRG), Department of Electrical and Computer Engineering, COMSATS University Islamabad, Pakistan
| | - Omair Inam
- Medical Image Processing Research Group (MIPRG), Department of Electrical and Computer Engineering, COMSATS University Islamabad, Pakistan
| | - Hammad Omer
- Medical Image Processing Research Group (MIPRG), Department of Electrical and Computer Engineering, COMSATS University Islamabad, Pakistan.
| |
Collapse
|
42
|
Utzschneider M, Müller M, Gast LV, Lachner S, Behl NGR, Maier A, Uder M, Nagel AM. Towards accelerated quantitative sodium MRI at 7 T in the skeletal muscle: Comparison of anisotropic acquisition- and compressed sensing techniques. Magn Reson Imaging 2020; 75:72-88. [PMID: 32979516 DOI: 10.1016/j.mri.2020.09.019] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2020] [Revised: 08/25/2020] [Accepted: 09/14/2020] [Indexed: 12/14/2022]
Abstract
PURPOSE To compare three anisotropic acquisition schemes and three compressed sensing (CS) approaches for accelerated tissue sodium concentration (TSC) quantification using 23Na MRI at 7 T. MATERIALS AND METHODS Three anisotropic 3D-radial acquisition sequences were evaluated using simulations, phantom- and in vivo TSC measurements: An anisotropic density-adapted 3D-radial sequence (3DPR-C), a 3D acquisition-weighted density-adapted stack-of-stars sampling scheme (SOS) and a SOS approach with golden-ratio rotation (SOS-GR). Eight healthy volunteers were examined at a 7 Tesla MRI system. TSC measurements of the calf were conducted with a nominal spatial resolution of Δx = (3.0 × 3.0 × 15.0) mm3 and a field of view of (156.0 × 156.0 × 240.0) mm3 for multiple undersampling factors (USF). Three CS reconstructions were evaluated: Total variation CS (TV-CS), 3D dictionary-learning compressed sensing (3D-DLCS) and TV-CS with a block matching prior (TV-BL-CS). Results of the simulations and measurements were compared to a simulated ground truth (GT) or a fully sampled reference measurement (FS), respectively. The deviation of the mean TSC evaluated in multiple ROI (mEGT/FS) and the normalized root-mean-squared error (NRMSE) for simulations were evaluated for CS and NUFFT reconstructions. RESULTS In simulations, the SOS-GR yielded the lowest NRMSE and mEGT (< 4%) with NUFFT for an acquisition time (TA) of less than 2 min. CS further improved the results. In simulations and measurements, the best TSC quantification results were obtained with 3D-DLCS and SOS-GR (lowest NRMSE, mEGT < 2.6% in simulations, mEGT < 10.7% for phantom measurements and mEFS < 6% in vivo) with an USF = 4.1 (TA < 2 min). TV-CS showed no or only slight improvements to NUFFT. The results of TV-BL-CS were similar to 3D-DLCS. DISCUSSION The TA for TSC measurements could be reduced to less than 2 min by using adapted sequences such as SOS-GR and CS reconstruction approaches such as 3D-DLCS or TV-BL-CS, while the quantitative accuracy stays comparable to a fully sampled NUFFT reconstruction (approx. 8 min TA). In future, the lower TA could improve clinical applicability of TSC measurements.
Collapse
Affiliation(s)
- Matthias Utzschneider
- Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany; Pattern Recognition Lab, Department of Computer Science, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.
| | - Max Müller
- Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany
| | - Lena V Gast
- Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany; Institute of Medical Physics, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany
| | - Sebastian Lachner
- Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany
| | - Nicolas G R Behl
- Division of Medical Physics in Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Andreas Maier
- Pattern Recognition Lab, Department of Computer Science, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany
| | - Michael Uder
- Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany
| | - Armin M Nagel
- Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany; Division of Medical Physics in Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany; Institute of Medical Physics, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany
| |
Collapse
|
43
|
Benjamin AJV, Bano W, Mair G, Thompson G, Casado A, Di Perri C, Davies M, Marshall I. Diagnostic quality assessment of IR-prepared 3D magnetic resonance neuroimaging accelerated using compressed sensing and k-space sampling order optimization. Magn Reson Imaging 2020; 74:31-45. [PMID: 32890675 DOI: 10.1016/j.mri.2020.08.025] [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: 01/30/2020] [Revised: 07/28/2020] [Accepted: 08/30/2020] [Indexed: 10/23/2022]
Abstract
PURPOSE To evaluate the clinical diagnostic efficacy of accelerated 3D magnetic resonance (MR) neuroimaging by radiological assessment for image quality and artefacts. STUDY TYPE Prospective healthy volunteer study. SUBJECTS Eight healthy subjects. FIELD STRENGTH/SEQUENCE Inversion Recovery (IR) prepared 3D Gradient Echo (GRE) sequence on a 1.5 T GE Signa HDx scanner. ASSESSMENT Independent radiological diagnostic quality assessments of accelerated 3D MR brain datasets were carried out by four experienced neuro-radiologists who were blinded to the acceleration factor and to the subject. The radiological grading was based on a previously reported radiological scoring key that was used for image quality assessment of human brains. STATISTICAL TESTS Bland-Altman analysis. RESULTS Optimization of the k-space sampling order was important for preserving contrast in accelerated scans. Despite having lower scores than fully sampled datasets, the majority of the compressed sensing (CS) accelerated brain datasets with k-space sampling order optimization (19/24 datasets by Radiologist 1, 24/24 datasets by Radiologist 2 and 16/24 datasets by Radiologist 3) were graded to be fully diagnostic indicating that there was adequate confidence for performing gross structural assessment of the brain. CONCLUSION Optimization of k-space acquisition order improves the clinical utility of CS accelerated 3D neuroimaging. This method may be appropriate for routine radiological assessment of the brain.
Collapse
Affiliation(s)
- Arnold Julian Vinoj Benjamin
- School of Engineering, Institute for Digital Communications, The University of Edinburgh, United Kingdom; Centre for Clinical Brain Sciences, The University of Edinburgh, United Kingdom.
| | - Wajiha Bano
- School of Engineering, Institute for Digital Communications, The University of Edinburgh, United Kingdom; Centre for Clinical Brain Sciences, The University of Edinburgh, United Kingdom
| | - Grant Mair
- Centre for Clinical Brain Sciences, The University of Edinburgh, United Kingdom
| | - Gerard Thompson
- Centre for Clinical Brain Sciences, The University of Edinburgh, United Kingdom
| | - Ana Casado
- Centre for Clinical Brain Sciences, The University of Edinburgh, United Kingdom
| | - Carol Di Perri
- Centre for Clinical Brain Sciences, The University of Edinburgh, United Kingdom
| | - Michael Davies
- School of Engineering, Institute for Digital Communications, The University of Edinburgh, United Kingdom
| | - Ian Marshall
- Centre for Clinical Brain Sciences, The University of Edinburgh, United Kingdom
| |
Collapse
|
44
|
Yoon JH, Nickel MD, Peeters JM, Lee JM. Rapid Imaging: Recent Advances in Abdominal MRI for Reducing Acquisition Time and Its Clinical Applications. Korean J Radiol 2020; 20:1597-1615. [PMID: 31854148 PMCID: PMC6923214 DOI: 10.3348/kjr.2018.0931] [Citation(s) in RCA: 45] [Impact Index Per Article: 11.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/31/2018] [Accepted: 07/22/2019] [Indexed: 02/06/2023] Open
Abstract
Magnetic resonance imaging (MRI) plays an important role in abdominal imaging. The high contrast resolution offered by MRI provides better lesion detection and its capacity to provide multiparametric images facilitates lesion characterization more effectively than computed tomography. However, the relatively long acquisition time of MRI often detrimentally affects the image quality and limits its accessibility. Recent developments have addressed these drawbacks. Specifically, multiphasic acquisition of contrast-enhanced MRI, free-breathing dynamic MRI using compressed sensing technique, simultaneous multi-slice acquisition for diffusion-weighted imaging, and breath-hold three-dimensional magnetic resonance cholangiopancreatography are recent notable advances in this field. This review explores the aforementioned state-of-the-art techniques by focusing on their clinical applications and potential benefits, as well as their likely future direction.
Collapse
Affiliation(s)
- Jeong Hee Yoon
- Department of Radiology, Seoul National University Hospital, Seoul National University College of Medicine, Seoul, Korea.
| | | | | | - Jeong Min Lee
- Department of Radiology, Seoul National University Hospital, Seoul National University College of Medicine, Seoul, Korea.,Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Korea
| |
Collapse
|
45
|
El-Rewaidy H, Neisius U, Mancio J, Kucukseymen S, Rodriguez J, Paskavitz A, Menze B, Nezafat R. Deep complex convolutional network for fast reconstruction of 3D late gadolinium enhancement cardiac MRI. NMR IN BIOMEDICINE 2020; 33:e4312. [PMID: 32352197 DOI: 10.1002/nbm.4312] [Citation(s) in RCA: 18] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/05/2019] [Revised: 03/19/2020] [Accepted: 03/24/2020] [Indexed: 06/11/2023]
Abstract
Several deep-learning models have been proposed to shorten MRI scan time. Prior deep-learning models that utilize real-valued kernels have limited capability to learn rich representations of complex MRI data. In this work, we utilize a complex-valued convolutional network (ℂNet) for fast reconstruction of highly under-sampled MRI data and evaluate its ability to rapidly reconstruct 3D late gadolinium enhancement (LGE) data. ℂNet preserves the complex nature and optimal combination of real and imaginary components of MRI data throughout the reconstruction process by utilizing complex-valued convolution, novel radial batch normalization, and complex activation function layers in a U-Net architecture. A prospectively under-sampled 3D LGE cardiac MRI dataset of 219 patients (17 003 images) at acceleration rates R = 3 through R = 5 was used to evaluate ℂNet. The dataset was further retrospectively under-sampled to a maximum of R = 8 to simulate higher acceleration rates. We created three reconstructions of the 3D LGE dataset using (1) ℂNet, (2) a compressed-sensing-based low-dimensional-structure self-learning and thresholding algorithm (LOST), and (3) a real-valued U-Net (realNet) with the same number of parameters as ℂNet. LOST-reconstructed data were considered the reference for training and evaluation of all models. The reconstructed images were quantitatively evaluated using mean-squared error (MSE) and the structural similarity index measure (SSIM), and subjectively evaluated by three independent readers. Quantitatively, ℂNet-reconstructed images had significantly improved MSE and SSIM values compared with realNet (MSE, 0.077 versus 0.091; SSIM, 0.876 versus 0.733, respectively; p < 0.01). Subjective quality assessment showed that ℂNet-reconstructed image quality was similar to that of compressed sensing and significantly better than that of realNet. ℂNet reconstruction was also more than 300 times faster than compressed sensing. Retrospective under-sampled images demonstrate the potential of ℂNet at higher acceleration rates. ℂNet enables fast reconstruction of highly accelerated 3D MRI with superior performance to real-valued networks, and achieves faster reconstruction than compressed sensing.
Collapse
Affiliation(s)
- Hossam El-Rewaidy
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
- Department of Computer Science, Technical University of Munich, Munich, Germany
| | - Ulf Neisius
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
| | - Jennifer Mancio
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
| | - Selcuk Kucukseymen
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
| | - Jennifer Rodriguez
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
| | - Amanda Paskavitz
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
| | - Bjoern Menze
- Department of Computer Science, Technical University of Munich, Munich, Germany
| | - Reza Nezafat
- Department of Medicine (Cardiovascular Division), Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, Massachusetts
| |
Collapse
|
46
|
Shimron E, Webb AG, Azhari H. CORE-Deblur: Parallel MRI Reconstruction by Deblurring using compressed sensing. Magn Reson Imaging 2020; 72:25-33. [PMID: 32562743 DOI: 10.1016/j.mri.2020.06.001] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2020] [Revised: 05/11/2020] [Accepted: 06/08/2020] [Indexed: 01/22/2023]
Affiliation(s)
- Efrat Shimron
- Biomedical Engineering Department, Technion - Israel Institute of Technology, Haifa 3200003, Israel.
| | - Andrew G Webb
- C.J. Gorter Center for High Field MRI Research, Department of Radiology, Leiden University Medical Center (LUMC), Leiden, The Netherlands
| | - Haim Azhari
- Biomedical Engineering Department, Technion - Israel Institute of Technology, Haifa 3200003, Israel.
| |
Collapse
|
47
|
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
|
48
|
Hosseini SAH, Zhang C, Weingärtner S, Moeller S, Stuber M, Ugurbil K, Akçakaya M. Accelerated coronary MRI with sRAKI: A database-free self-consistent neural network k-space reconstruction for arbitrary undersampling. PLoS One 2020; 15:e0229418. [PMID: 32084235 PMCID: PMC7034900 DOI: 10.1371/journal.pone.0229418] [Citation(s) in RCA: 14] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2019] [Accepted: 02/05/2020] [Indexed: 02/01/2023] Open
Abstract
Purpose To accelerate coronary MRI acquisitions with arbitrary undersampling patterns by using a novel reconstruction algorithm that applies coil self-consistency using subject-specific neural networks. Methods Self-consistent robust artificial-neural-networks for k-space interpolation (sRAKI) performs iterative parallel imaging reconstruction by enforcing self-consistency among coils. The approach bears similarity to SPIRiT, but extends the linear convolutions in SPIRiT to nonlinear interpolation using convolutional neural networks (CNNs). These CNNs are trained individually for each scan using the scan-specific autocalibrating signal (ACS) data. Reconstruction is performed by imposing the learned self-consistency and data-consistency, which enables sRAKI to support random undersampling patterns. Fully-sampled targeted right coronary artery MRI was acquired in six healthy subjects. The data were retrospectively undersampled, and reconstructed using SPIRiT, l1-SPIRiT and sRAKI for acceleration rates of 2 to 5. Additionally, prospectively undersampled whole-heart coronary MRI was acquired to further evaluate reconstruction performance. Results sRAKI reduces noise amplification and blurring artifacts compared with SPIRiT and l1-SPIRiT, especially at high acceleration rates in targeted coronary MRI. Quantitative analysis shows that sRAKI outperforms these techniques in terms of normalized mean-squared-error (~44% and ~21% over SPIRiT and l1-SPIRiT at rate 5) and vessel sharpness (~10% and ~20% over SPIRiT and l1-SPIRiT at rate 5). Whole-heart data shows the sharpest coronary arteries when resolved using sRAKI, with 11% and 15% improvement in vessel sharpness over SPIRiT and l1-SPIRiT, respectively. Conclusion sRAKI is a database-free neural network-based reconstruction technique that may further accelerate coronary MRI with arbitrary undersampling patterns, while improving noise resilience over linear parallel imaging and image sharpness over l1 regularization techniques.
Collapse
Affiliation(s)
- Seyed Amir Hossein Hosseini
- Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, United States of America
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, United States of America
| | - Chi Zhang
- Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, United States of America
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, United States of America
| | - Sebastian Weingärtner
- Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, United States of America
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, United States of America
- Department of Imaging Physics, Delft University of Technology, Delft, Netherlands
| | - Steen Moeller
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, United States of America
| | - Matthias Stuber
- Department of Radiology, University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- Center for Biomedical Imaging (CIBM), Lausanne, Switzerland
| | - Kamil Ugurbil
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, United States of America
| | - Mehmet Akçakaya
- Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, United States of America
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, United States of America
- * E-mail:
| |
Collapse
|
49
|
Utzschneider M, Behl NGR, Lachner S, Gast LV, Maier A, Uder M, Nagel AM. Accelerated quantification of tissue sodium concentration in skeletal muscle tissue: quantitative capability of dictionary learning compressed sensing. MAGNETIC RESONANCE MATERIALS IN PHYSICS BIOLOGY AND MEDICINE 2020; 33:495-505. [DOI: 10.1007/s10334-019-00819-2] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/18/2019] [Revised: 11/22/2019] [Accepted: 12/17/2019] [Indexed: 12/11/2022]
|
50
|
Sandino CM, Cheng JY, Chen F, Mardani M, Pauly JM, Vasanawala SS. Compressed Sensing: From Research to Clinical Practice with Deep Neural Networks. IEEE SIGNAL PROCESSING MAGAZINE 2020; 37:111-127. [PMID: 33192036 PMCID: PMC7664163 DOI: 10.1109/msp.2019.2950433] [Citation(s) in RCA: 49] [Impact Index Per Article: 12.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/13/2023]
Abstract
Compressed sensing (CS) reconstruction methods leverage sparse structure in underlying signals to recover high-resolution images from highly undersampled measurements. When applied to magnetic resonance imaging (MRI), CS has the potential to dramatically shorten MRI scan times, increase diagnostic value, and improve overall patient experience. However, CS has several shortcomings which limit its clinical translation such as: 1) artifacts arising from inaccurate sparse modelling assumptions, 2) extensive parameter tuning required for each clinical application, and 3) clinically infeasible reconstruction times. Recently, CS has been extended to incorporate deep neural networks as a way of learning complex image priors from historical exam data. Commonly referred to as unrolled neural networks, these techniques have proven to be a compelling and practical approach to address the challenges of sparse CS. In this tutorial, we will review the classical compressed sensing formulation and outline steps needed to transform this formulation into a deep learning-based reconstruction framework. Supplementary open source code in Python will be used to demonstrate this approach with open databases. Further, we will discuss considerations in applying unrolled neural networks in the clinical setting.
Collapse
|