1
|
Blumenthal M, Fantinato C, Unterberg-Buchwald C, Haltmeier M, Wang X, Uecker M. Self-supervised learning for improved calibrationless radial MRI with NLINV-Net. Magn Reson Med 2024; 92:2447-2463. [PMID: 39080844 DOI: 10.1002/mrm.30234] [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: 02/09/2024] [Revised: 06/10/2024] [Accepted: 07/10/2024] [Indexed: 09/28/2024]
Abstract
PURPOSE To develop a neural network architecture for improved calibrationless reconstruction of radial data when no ground truth is available for training. METHODS NLINV-Net is a model-based neural network architecture that directly estimates images and coil sensitivities from (radial) k-space data via nonlinear inversion (NLINV). Combined with a training strategy using self-supervision via data undersampling (SSDU), it can be used for imaging problems where no ground truth reconstructions are available. We validated the method for (1) real-time cardiac imaging and (2) single-shot subspace-based quantitative T1 mapping. Furthermore, region-optimized virtual (ROVir) coils were used to suppress artifacts stemming from outside the field of view and to focus the k-space-based SSDU loss on the region of interest. NLINV-Net-based reconstructions were compared with conventional NLINV and PI-CS (parallel imaging + compressed sensing) reconstruction and the effect of the region-optimized virtual coils and the type of training loss was evaluated qualitatively. RESULTS NLINV-Net-based reconstructions contain significantly less noise than the NLINV-based counterpart. ROVir coils effectively suppress streakings which are not suppressed by the neural networks while the ROVir-based focused loss leads to visually sharper time series for the movement of the myocardial wall in cardiac real-time imaging. For quantitative imaging, T1-maps reconstructed using NLINV-Net show similar quality as PI-CS reconstructions, but NLINV-Net does not require slice-specific tuning of the regularization parameter. CONCLUSION NLINV-Net is a versatile tool for calibrationless imaging which can be used in challenging imaging scenarios where a ground truth is not available.
Collapse
Affiliation(s)
- Moritz Blumenthal
- Institute of Biomedical Imaging, Graz University of Technology, Graz, Austria
- Institute for Diagnostic and Interventional Radiology, University Medical Center Göttingen, Göttingen, Germany
| | - Chiara Fantinato
- Institute of Biomedical Imaging, Graz University of Technology, Graz, Austria
| | - Christina Unterberg-Buchwald
- Institute for Diagnostic and Interventional Radiology, University Medical Center Göttingen, Göttingen, Germany
- Clinic for Cardiology and Pneumology, University Medical Center Göttingen, Göttingen, Germany
- DZHK (German Centre for Cardiovascular Research), Partner Site Lower Saxony, Göttingen, Germany
| | - Markus Haltmeier
- Department of Mathematics, University of Innsbruck, Innsbruck, Austria
| | - Xiaoqing Wang
- Department of Radiology, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Martin Uecker
- Institute of Biomedical Imaging, Graz University of Technology, Graz, Austria
- Institute for Diagnostic and Interventional Radiology, University Medical Center Göttingen, Göttingen, Germany
- DZHK (German Centre for Cardiovascular Research), Partner Site Lower Saxony, Göttingen, Germany
- BioTechMed-Graz, Graz, Austria
| |
Collapse
|
2
|
Bartlett JJ, Davey CE, Johnston LA, Duan J. Recovering high-quality fiber orientation distributions from a reduced number of diffusion-weighted images using a model-driven deep learning architecture. Magn Reson Med 2024; 92:2193-2206. [PMID: 38852179 DOI: 10.1002/mrm.30187] [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: 10/08/2023] [Revised: 04/09/2024] [Accepted: 05/20/2024] [Indexed: 06/11/2024]
Abstract
PURPOSE The aim of this study was to develop a model-based deep learning architecture to accurately reconstruct fiber orientation distributions (FODs) from a reduced number of diffusion-weighted images (DWIs), facilitating accurate analysis with reduced acquisition times. METHODS Our proposed architecture, Spherical Deconvolution Network (SDNet), performed FOD reconstruction by mapping 30 DWIs to fully sampled FODs, which have been fit to 288 DWIs. SDNet included DWI-consistency blocks within the network architecture, and a fixel-classification penalty within the loss function. SDNet was trained on a subset of the Human Connectome Project, and its performance compared with FOD-Net, and multishell multitissue constrained spherical deconvolution. RESULTS SDNet achieved the strongest results with respect to angular correlation coefficient and sum of squared errors. When the impact of the fixel-classification penalty was increased, we observed an improvement in performance metrics reliant on segmenting the FODs into the correct number of fixels. CONCLUSION Inclusion of DWI-consistency blocks improved reconstruction performance, and the fixel-classification penalty term offered increased control over the angular separation of fixels in the reconstructed FODs.
Collapse
Affiliation(s)
- Joseph J Bartlett
- Department of Biomedical Engineering, Melbourne Brain Centre Imaging Unit, Graeme Clark Institute, The University of Melbourne, Parkville, Victoria, Australia
- School of Computer Science, University of Birmingham, Birmingham, UK
| | - Catherine E Davey
- Department of Biomedical Engineering, Melbourne Brain Centre Imaging Unit, Graeme Clark Institute, The University of Melbourne, Parkville, Victoria, Australia
| | - Leigh A Johnston
- Department of Biomedical Engineering, Melbourne Brain Centre Imaging Unit, Graeme Clark Institute, The University of Melbourne, Parkville, Victoria, Australia
| | - Jinming Duan
- School of Computer Science, University of Birmingham, Birmingham, UK
- The Alan Turing Institute, London, UK
| |
Collapse
|
3
|
Karkalousos D, Išgum I, Marquering HA, Caan MWA. ATOMMIC: An Advanced Toolbox for Multitask Medical Imaging Consistency to facilitate Artificial Intelligence applications from acquisition to analysis in Magnetic Resonance Imaging. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 256:108377. [PMID: 39180913 DOI: 10.1016/j.cmpb.2024.108377] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/19/2024] [Revised: 07/26/2024] [Accepted: 08/15/2024] [Indexed: 08/27/2024]
Abstract
BACKGROUND AND OBJECTIVES Artificial intelligence (AI) is revolutionizing Magnetic Resonance Imaging (MRI) along the acquisition and processing chain. Advanced AI frameworks have been applied in various successive tasks, such as image reconstruction, quantitative parameter map estimation, and image segmentation. However, existing frameworks are often designed to perform tasks independently of each other or are focused on specific models or single datasets, limiting generalization. This work introduces the Advanced Toolbox for Multitask Medical Imaging Consistency (ATOMMIC), a novel open-source toolbox that streamlines AI applications for accelerated MRI reconstruction and analysis. ATOMMIC implements several tasks using deep learning (DL) models and enables MultiTask Learning (MTL) to perform related tasks in an integrated manner, targeting generalization in the MRI domain. METHODS We conducted a comprehensive literature review and analyzed 12,479 GitHub repositories to assess the current landscape of AI frameworks for MRI. Subsequently, we demonstrate how ATOMMIC standardizes workflows and improves data interoperability, enabling effective benchmarking of various DL models across MRI tasks and datasets. To showcase ATOMMIC's capabilities, we evaluated twenty-five DL models on eight publicly available datasets, focusing on accelerated MRI reconstruction, segmentation, quantitative parameter map estimation, and joint accelerated MRI reconstruction and segmentation using MTL. RESULTS ATOMMIC's high-performance training and testing capabilities, utilizing multiple GPUs and mixed precision support, enable efficient benchmarking of multiple models across various tasks. The framework's modular architecture implements each task through a collection of data loaders, models, loss functions, evaluation metrics, and pre-processing transformations, facilitating seamless integration of new tasks, datasets, and models. Our findings demonstrate that ATOMMIC supports MTL for multiple MRI tasks with harmonized complex-valued and real-valued data support while maintaining active development and documentation. Task-specific evaluations demonstrate that physics-based models outperform other approaches in reconstructing highly accelerated acquisitions. These high-quality reconstruction models also show superior accuracy in estimating quantitative parameter maps. Furthermore, when combining high-performing reconstruction models with robust segmentation networks through MTL, performance is improved in both tasks. CONCLUSIONS ATOMMIC advances MRI reconstruction and analysis by leveraging MTL and ensuring consistency across tasks, models, and datasets. This comprehensive framework serves as a versatile platform for researchers to use existing AI methods and develop new approaches in medical imaging.
Collapse
Affiliation(s)
- Dimitrios Karkalousos
- Department of Biomedical Engineering & Physics, Amsterdam University Medical Center, Location University of Amsterdam, Amsterdam, The Netherlands; Department of Radiology & Nuclear Medicine, Amsterdam University Medical Center, Location University of Amsterdam, Amsterdam, The Netherlands; Amsterdam Neuroscience, Brain Imaging, Amsterdam, The Netherlands.
| | - Ivana Išgum
- Department of Biomedical Engineering & Physics, Amsterdam University Medical Center, Location University of Amsterdam, Amsterdam, The Netherlands; Department of Radiology & Nuclear Medicine, Amsterdam University Medical Center, Location University of Amsterdam, Amsterdam, The Netherlands; Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands
| | - Henk A Marquering
- Department of Biomedical Engineering & Physics, Amsterdam University Medical Center, Location University of Amsterdam, Amsterdam, The Netherlands; Department of Radiology & Nuclear Medicine, Amsterdam University Medical Center, Location University of Amsterdam, Amsterdam, The Netherlands; Amsterdam Neuroscience, Brain Imaging, Amsterdam, The Netherlands
| | - Matthan W A Caan
- Department of Biomedical Engineering & Physics, Amsterdam University Medical Center, Location University of Amsterdam, Amsterdam, The Netherlands; Amsterdam Neuroscience, Brain Imaging, Amsterdam, The Netherlands
| |
Collapse
|
4
|
Wei H, Yoon JH, Jeon SK, Choi JW, Lee J, Kim JH, Nickel MD, Song B, Duan T, Lee JM. Enhancing gadoxetic acid-enhanced liver MRI: a synergistic approach with deep learning CAIPIRINHA-VIBE and optimized fat suppression techniques. Eur Radiol 2024; 34:6712-6725. [PMID: 38492004 PMCID: PMC11399219 DOI: 10.1007/s00330-024-10693-9] [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: 09/18/2023] [Revised: 02/02/2024] [Accepted: 02/18/2024] [Indexed: 03/18/2024]
Abstract
OBJECTIVE To investigate whether a deep learning (DL) controlled aliasing in parallel imaging results in higher acceleration (CAIPIRINHA)-volumetric interpolated breath-hold examination (VIBE) technique can improve image quality, lesion conspicuity, and lesion detection compared to a standard CAIPIRINHA-VIBE technique in gadoxetic acid-enhanced liver MRI. METHODS This retrospective single-center study included 168 patients who underwent gadoxetic acid-enhanced liver MRI at 3 T using both standard CAIPIRINHA-VIBE and DL CAIPIRINHA-VIBE techniques on pre-contrast and hepatobiliary phase (HBP) images. Additionally, high-resolution (HR) DL CAIPIRINHA-VIBE was obtained with 1-mm slice thickness on the HBP. Three abdominal radiologists independently assessed the image quality and lesion conspicuity of pre-contrast and HBP images. Statistical analyses involved the Wilcoxon signed-rank test for image quality assessment and the generalized estimation equation for lesion conspicuity and detection evaluation. RESULTS DL and HR-DL CAIPIRINHA-VIBE demonstrated significantly improved overall image quality and reduced artifacts on pre-contrast and HBP images compared to standard CAIPIRINHA-VIBE (p < 0.001), with a shorter acquisition time (DL vs standard, 11 s vs 17 s). However, the former presented a more synthetic appearance (both p < 0.05). HR-DL CAIPIRINHA-VIBE showed superior lesion conspicuity to standard and DL CAIPIRINHA-VIBE on HBP images (p < 0.001). Moreover, HR-DL CAIPIRINHA-VIBE exhibited a significantly higher detection rate of small (< 2 cm) solid focal liver lesions (FLLs) on HBP images compared to standard CAIPIRINHA-VIBE (92.5% vs 87.4%; odds ratio = 1.83; p = 0.036). CONCLUSION DL and HR-DL CAIPIRINHA-VIBE achieved superior image quality compared to standard CAIPIRINHA-VIBE. Additionally, HR-DL CAIPIRINHA-VIBE improved the lesion conspicuity and detection of small solid FLLs. DL and HR-DL CAIPIRINHA-VIBE hold the potential clinical utility for gadoxetic acid-enhanced liver MRI. CLINICAL RELEVANCE STATEMENT DL and HR-DL CAIPIRINHA-VIBE hold promise as potential alternatives to standard CAIPIRINHA-VIBE in routine clinical liver MRI, improving the image quality and lesion conspicuity, enhancing the detection of small (< 2 cm) solid focal liver lesions, and reducing the acquisition time. KEY POINTS • DL and HR-DL CAIPIRINHA-VIBE demonstrated improved overall image quality and reduced artifacts on pre-contrast and HBP images compared to standard CAIPIRINHA-VIBE, in addition to a shorter acquisition time. • DL and HR-DL CAIPIRINHA-VIBE yielded a more synthetic appearance than standard CAIPIRINHA-VIBE. • HR-DL CAIPIRINHA-VIBE showed improved lesion conspicuity than standard CAIPIRINHA-VIBE on HBP images, with a higher detection of small (< 2 cm) solid focal liver lesions.
Collapse
Affiliation(s)
- Hong Wei
- Department of Radiology, Seoul National University Hospital, Seoul, 03080, Republic of Korea
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, Sichuan, China
| | - Jeong Hee Yoon
- Department of Radiology, Seoul National University Hospital, Seoul, 03080, Republic of Korea
- Department of Radiology, Seoul National University College of Medicine, Seoul, 03080, Republic of Korea
| | - Sun Kyung Jeon
- Department of Radiology, Seoul National University Hospital, Seoul, 03080, Republic of Korea
| | - Jae Won Choi
- Department of Radiology, Seoul National University College of Medicine, Seoul, 03080, Republic of Korea
- Department of Radiology, Armed Forces Yangju Hospital, Yangju, 482863, Republic of Korea
| | - Jihyuk Lee
- Department of Radiology, Seoul National University Hospital, Seoul, 03080, Republic of Korea
| | - Jae Hyun Kim
- Department of Radiology, Seoul National University Hospital, Seoul, 03080, Republic of Korea
| | - Marcel Dominik Nickel
- MR Application Predevelopment, Siemens Healthcare GmbH, Henkestr. 127, 91052, Erlangen, Germany
| | - Bin Song
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, Sichuan, China
- Department of Radiology, Sanya People's Hospital, Sanya, 572000, Hainan, China
| | - Ting Duan
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, Sichuan, China
| | - Jeong Min Lee
- Department of Radiology, Seoul National University Hospital, Seoul, 03080, Republic of Korea.
- Department of Radiology, Seoul National University College of Medicine, Seoul, 03080, Republic of Korea.
| |
Collapse
|
5
|
Dubljevic N, Moore S, Lauzon ML, Souza R, Frayne R. Effect of MR head coil geometry on deep-learning-based MR image reconstruction. Magn Reson Med 2024; 92:1404-1420. [PMID: 38647191 DOI: 10.1002/mrm.30130] [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: 09/30/2023] [Revised: 04/02/2024] [Accepted: 04/07/2024] [Indexed: 04/25/2024]
Abstract
PURPOSE To investigate whether parallel imaging-imposed geometric coil constraints can be relaxed when using a deep learning (DL)-based image reconstruction method as opposed to a traditional non-DL method. THEORY AND METHODS Traditional and DL-based MR image reconstruction approaches operate in fundamentally different ways: Traditional methods solve a system of equations derived from the image data whereas DL methods use data/target pairs to learn a generalizable reconstruction model. Two sets of head coil profiles were evaluated: (1) 8-channel and (2) 32-channel geometries. A DL model was compared to conjugate gradient SENSE (CG-SENSE) and L1-wavelet compressed sensing (CS) through quantitative metrics and visual assessment as coil overlap was increased. RESULTS Results were generally consistent between experiments. As coil overlap increased, there was a significant (p < 0.001) decrease in performance in most cases for all methods. The decrease was most pronounced for CG-SENSE, and the DL models significantly outperformed (p < 0.001) their non-DL counterparts in all scenarios. CS showed improved robustness to coil overlap and signal-to-noise ratio (SNR) versus CG-SENSE, but had quantitatively and visually poorer reconstructions characterized by blurriness as compared to DL. DL showed virtually no change in performance across SNR and very small changes across coil overlap. CONCLUSION The DL image reconstruction method produced images that were robust to coil overlap and of higher quality than CG-SENSE and CS. This suggests that geometric coil design constraints can be relaxed when using DL reconstruction methods.
Collapse
Affiliation(s)
- Natalia Dubljevic
- Department of Biomedical Engineering, University of Calgary, Calgary, Alberta, Canada
- Seaman Family MR Research Centre, Foothills Medical Centre, Calgary, Alberta, Canada
- Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada
| | - Stephen Moore
- Seaman Family MR Research Centre, Foothills Medical Centre, Calgary, Alberta, Canada
- Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada
- O'Brien Centre for the Health Sciences, Cumming School of Medicine, Calgary, Alberta, Canada
| | - Michel Louis Lauzon
- Seaman Family MR Research Centre, Foothills Medical Centre, Calgary, Alberta, Canada
- Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada
- Radiology and Clinical Neuroscience, University of Calgary, Calgary, Alberta, Canada
| | - Roberto Souza
- Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada
- Department of Electrical and Software Engineering, University of Calgary, Calgary, Alberta, Canada
| | - Richard Frayne
- Department of Biomedical Engineering, University of Calgary, Calgary, Alberta, Canada
- Seaman Family MR Research Centre, Foothills Medical Centre, Calgary, Alberta, Canada
- Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada
- Radiology and Clinical Neuroscience, University of Calgary, Calgary, Alberta, Canada
| |
Collapse
|
6
|
Fujita N, Yokosawa S, Shirai T, Terada Y. Numerical and Clinical Evaluation of the Robustness of Open-source Networks for Parallel MR Imaging Reconstruction. Magn Reson Med Sci 2024; 23:460-478. [PMID: 37518672 PMCID: PMC11447470 DOI: 10.2463/mrms.mp.2023-0031] [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] [Indexed: 08/01/2023] Open
Abstract
PURPOSE Deep neural networks (DNNs) for MRI reconstruction often require large datasets for training. Still, in clinical settings, the domains of datasets are diverse, and how robust DNNs are to domain differences between training and testing datasets has been an open question. Here, we numerically and clinically evaluate the generalization of the reconstruction networks across various domains under clinically practical conditions and provide practical guidance on what points to consider when selecting models for clinical application. METHODS We compare the reconstruction performance between four network models: U-Net, the deep cascade of convolutional neural networks (DC-CNNs), Hybrid Cascade, and variational network (VarNet). We used the public multicoil dataset fastMRI for training and testing and performed a single-domain test, where the domains of the dataset used for training and testing were the same, and cross-domain tests, where the source and target domains were different. We conducted a single-domain test (Experiment 1) and cross-domain tests (Experiments 2-4), focusing on six factors (the number of images, sampling pattern, acceleration factor, noise level, contrast, and anatomical structure) both numerically and clinically. RESULTS U-Net had lower performance than the three model-based networks and was less robust to domain shifts between training and testing datasets. VarNet had the highest performance and robustness among the three model-based networks, followed by Hybrid Cascade and DC-CNN. Especially, VarNet showed high performance even with a limited number of training images (200 images/10 cases). U-Net was more robust to domain shifts concerning noise level than the other model-based networks. Hybrid Cascade showed slightly better performance and robustness than DC-CNN, except for robustness to noise-level domain shifts. The results of the clinical evaluations generally agreed with the results of the quantitative metrics. CONCLUSION In this study, we numerically and clinically evaluated the robustness of the publicly available networks using the multicoil data. Therefore, this study provided practical guidance for clinical applications.
Collapse
Affiliation(s)
- Naoto Fujita
- Institute of Applied Physics, University of Tsukuba
| | - Suguru Yokosawa
- FUJIFILM Corporation, Medical Systems Research & Development Center
| | - Toru Shirai
- FUJIFILM Corporation, Medical Systems Research & Development Center
| | | |
Collapse
|
7
|
Shen G, Li M, Farris CW, Anderson S, Zhang X. Learning to reconstruct accelerated MRI through K-space cold diffusion without noise. Sci Rep 2024; 14:21877. [PMID: 39300170 DOI: 10.1038/s41598-024-72820-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/21/2024] [Accepted: 09/10/2024] [Indexed: 09/22/2024] Open
Abstract
Deep learning-based MRI reconstruction models have achieved superior performance these days. Most recently, diffusion models have shown remarkable performance in image generation, in-painting, super-resolution, image editing and more. As a generalized diffusion model, cold diffusion further broadens the scope and considers models built around arbitrary image transformations such as blurring, down-sampling, etc. In this paper, we propose a k-space cold diffusion model that performs image degradation and restoration in k-space without the need for Gaussian noise. We provide comparisons with multiple deep learning-based MRI reconstruction models and perform tests on a well-known large open-source MRI dataset. Our results show that this novel way of performing degradation can generate high-quality reconstruction images for accelerated MRI.
Collapse
Affiliation(s)
- Guoyao Shen
- Department of Mechanical Engineering, Boston University, Boston, MA, 02215, USA
- The Photonics Center, Boston University, Boston, MA, 02215, USA
| | - Mengyu Li
- Department of Mechanical Engineering, Boston University, Boston, MA, 02215, USA
- The Photonics Center, Boston University, Boston, MA, 02215, USA
| | - Chad W Farris
- Department of Radiology, Boston Medical Center, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, 02118, USA
| | - Stephan Anderson
- The Photonics Center, Boston University, Boston, MA, 02215, USA
- Department of Radiology, Boston Medical Center, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, 02118, USA
| | - Xin Zhang
- Department of Mechanical Engineering, Boston University, Boston, MA, 02215, USA.
- The Photonics Center, Boston University, Boston, MA, 02215, USA.
| |
Collapse
|
8
|
Li B, Xie R, Sun Z, Shao X, Lian Y, Guo H, You R, You Z, Zhao X. Nonlinear metamaterials enhanced surface coil array for parallel magnetic resonance imaging. Nat Commun 2024; 15:7949. [PMID: 39261525 PMCID: PMC11390956 DOI: 10.1038/s41467-024-52423-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2023] [Accepted: 09/05/2024] [Indexed: 09/13/2024] Open
Abstract
Magnetic resonance imaging (MRI) is a crucial medical imaging modality, with parallel MRI accelerating scans but often reducing the signal-to-noise ratio (SNR). Recent advances in metamaterials have shown considerable potential in enhancing the SNR of MRI and consequently improving the quality of parallel MRI. In this study, we present a nonlinear metamaterial comprising nonlinear meta-atoms designed to selectively enhance the radio-frequency reception field in MRI, while minimizing interference with the radio-frequency transmission field. We develop an electromagnetic field-circuit joint simulation process for analyzing and optimizing the nonlinear response. Experimental validation confirms that nonlinear metamaterial integration in a surface coil array delivers a 3-fold SNR increase for parallel MRI compared to using the surface coil array alone. This research advances our understanding of such metamaterials and demonstrates their potential for practical utilization in MRI and clinical settings, thereby promising substantial enhancements in imaging capabilities.
Collapse
Affiliation(s)
- Bingbai Li
- Department of Precision Instrument, Tsinghua University, Beijing, 100084, China
| | - Rongbo Xie
- Department of Precision Instrument, Tsinghua University, Beijing, 100084, China
| | - Zhenci Sun
- Department of Precision Instrument, Tsinghua University, Beijing, 100084, China
| | - Xin Shao
- Center for Biomedical Imaging Research, School of Biomedical Engineering, Tsinghua University, Beijing, 100084, China
| | - Yuan Lian
- Center for Biomedical Imaging Research, School of Biomedical Engineering, Tsinghua University, Beijing, 100084, China
| | - Hua Guo
- Center for Biomedical Imaging Research, School of Biomedical Engineering, Tsinghua University, Beijing, 100084, China
| | - Rui You
- School of Instrument Science and Opto-electronics Engineering, Beijing Information Science and Technology University, Beijing, 100192, China.
| | - Zheng You
- Department of Precision Instrument, Tsinghua University, Beijing, 100084, China.
- Beijing Advanced Innovation Center for Integrated Circuits, Beijing, 100084, China.
| | - Xiaoguang Zhao
- Department of Precision Instrument, Tsinghua University, Beijing, 100084, China.
- Beijing Advanced Innovation Center for Integrated Circuits, Beijing, 100084, China.
| |
Collapse
|
9
|
Sauer ST, Christner SA, Lois AM, Woznicki P, Curtaz C, Kunz AS, Weiland E, Benkert T, Bley TA, Baeßler B, Grunz JP. Deep Learning k-Space-to-Image Reconstruction Facilitates High Spatial Resolution and Scan Time Reduction in Diffusion-Weighted Imaging Breast MRI. J Magn Reson Imaging 2024; 60:1190-1200. [PMID: 37974498 DOI: 10.1002/jmri.29139] [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: 07/14/2023] [Revised: 11/03/2023] [Accepted: 11/04/2023] [Indexed: 11/19/2023] Open
Abstract
BACKGROUND For time-consuming diffusion-weighted imaging (DWI) of the breast, deep learning-based imaging acceleration appears particularly promising. PURPOSE To investigate a combined k-space-to-image reconstruction approach for scan time reduction and improved spatial resolution in breast DWI. STUDY TYPE Retrospective. POPULATION 133 women (age 49.7 ± 12.1 years) underwent multiparametric breast MRI. FIELD STRENGTH/SEQUENCE 3.0T/T2 turbo spin echo, T1 3D gradient echo, DWI (800 and 1600 sec/mm2). ASSESSMENT DWI data were retrospectively processed using deep learning-based k-space-to-image reconstruction (DL-DWI) and an additional super-resolution algorithm (SRDL-DWI). In addition to signal-to-noise ratio and apparent diffusion coefficient (ADC) comparisons among standard, DL- and SRDL-DWI, a range of quantitative similarity (e.g., structural similarity index [SSIM]) and error metrics (e.g., normalized root mean square error [NRMSE], symmetric mean absolute percent error [SMAPE], log accuracy error [LOGAC]) was calculated to analyze structural variations. Subjective image evaluation was performed independently by three radiologists on a seven-point rating scale. STATISTICAL TESTS Friedman's rank-based analysis of variance with Bonferroni-corrected pairwise post-hoc tests. P < 0.05 was considered significant. RESULTS Both DL- and SRDL-DWI allowed for a 39% reduction in simulated scan time over standard DWI (5 vs. 3 minutes). The highest image quality ratings were assigned to SRDL-DWI with good interreader agreement (ICC 0.834; 95% confidence interval 0.818-0.848). Irrespective of b-value, both standard and DL-DWI produced superior SNR compared to SRDL-DWI. ADC values were slightly higher in SRDL-DWI (+0.5%) and DL-DWI (+3.4%) than in standard DWI. Structural similarity was excellent between DL-/SRDL-DWI and standard DWI for either b value (SSIM ≥ 0.86). Calculation of error metrics (NRMSE ≤ 0.05, SMAPE ≤ 0.02, and LOGAC ≤ 0.04) supported the assumption of low voxel-wise error. DATA CONCLUSION Deep learning-based k-space-to-image reconstruction reduces simulated scan time of breast DWI by 39% without influencing structural similarity. Additionally, super-resolution interpolation allows for substantial improvement of subjective image quality. EVIDENCE LEVEL 4 TECHNICAL EFFICACY: Stage 1.
Collapse
Affiliation(s)
- Stephanie Tina Sauer
- Department of Diagnostic and Interventional Radiology, University Hospital Würzburg, Würzburg, Germany
| | - Sara Aniki Christner
- Department of Diagnostic and Interventional Radiology, University Hospital Würzburg, Würzburg, Germany
| | - Anna-Maria Lois
- Department of Diagnostic and Interventional Radiology, University Hospital Würzburg, Würzburg, Germany
| | - Piotr Woznicki
- Department of Diagnostic and Interventional Radiology, University Hospital Würzburg, Würzburg, Germany
| | - Carolin Curtaz
- Department of Obstetrics and Gynecology, University Hospital Würzburg, Würzburg, Germany
| | - Andreas Steven Kunz
- Department of Diagnostic and Interventional Radiology, University Hospital Würzburg, Würzburg, Germany
| | - Elisabeth Weiland
- MR Application Predevelopment, Siemens Healthcare GmbH, Erlangen, Germany
| | - Thomas Benkert
- MR Application Predevelopment, Siemens Healthcare GmbH, Erlangen, Germany
| | - Thorsten Alexander Bley
- Department of Diagnostic and Interventional Radiology, University Hospital Würzburg, Würzburg, Germany
| | - Bettina Baeßler
- Department of Diagnostic and Interventional Radiology, University Hospital Würzburg, Würzburg, Germany
| | - Jan-Peter Grunz
- Department of Diagnostic and Interventional Radiology, University Hospital Würzburg, Würzburg, Germany
| |
Collapse
|
10
|
Hu Y, Gan W, Ying C, Wang T, Eldeniz C, Liu J, Chen Y, An H, Kamilov US. SPICER: Self-supervised learning for MRI with automatic coil sensitivity estimation and reconstruction. Magn Reson Med 2024; 92:1048-1063. [PMID: 38725383 DOI: 10.1002/mrm.30121] [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: 05/29/2023] [Revised: 02/28/2024] [Accepted: 04/02/2024] [Indexed: 06/27/2024]
Abstract
PURPOSE To introduce a novel deep model-based architecture (DMBA), SPICER, that uses pairs of noisy and undersampled k-space measurements of the same object to jointly train a model for MRI reconstruction and automatic coil sensitivity estimation. METHODS SPICER consists of two modules to simultaneously reconstructs accurate MR images and estimates high-quality coil sensitivity maps (CSMs). The first module, CSM estimation module, uses a convolutional neural network (CNN) to estimate CSMs from the raw measurements. The second module, DMBA-based MRI reconstruction module, forms reconstructed images from the input measurements and the estimated CSMs using both the physical measurement model and learned CNN prior. With the benefit of our self-supervised learning strategy, SPICER can be efficiently trained without any fully sampled reference data. RESULTS We validate SPICER on both open-access datasets and experimentally collected data, showing that it can achieve state-of-the-art performance in highly accelerated data acquisition settings (up to10 × $$ 10\times $$ ). Our results also highlight the importance of different modules of SPICER-including the DMBA, the CSM estimation, and the SPICER training loss-on the final performance of the method. Moreover, SPICER can estimate better CSMs than pre-estimation methods especially when the ACS data is limited. CONCLUSION Despite being trained on noisy undersampled data, SPICER can reconstruct high-quality images and CSMs in highly undersampled settings, which outperforms other self-supervised learning methods and matches the performance of the well-known E2E-VarNet trained on fully sampled ground-truth data.
Collapse
Affiliation(s)
- Yuyang Hu
- Department of Electrical and Systems Engineering, Washington University in St. Louis, St. Louis, Missouri
| | - Weijie Gan
- Department of Computer Science and Engineering, Washington University in St. Louis, St. Louis, Missouri
| | - Chunwei Ying
- Mallinckrodt Institute of Radiology, Washington University in St. Louis, St. Louis, Missouri
| | - Tongyao Wang
- Department of Biomedical Engineering, Washington University in St. Louis, St. Louis, Missouri
| | - Cihat Eldeniz
- Mallinckrodt Institute of Radiology, Washington University in St. Louis, St. Louis, Missouri
| | - Jiaming Liu
- Department of Electrical and Systems Engineering, Washington University in St. Louis, St. Louis, Missouri
| | - Yasheng Chen
- Department of Neurology, Washington University in St. Louis, St. Louis, Missouri
| | - Hongyu An
- Department of Electrical and Systems Engineering, Washington University in St. Louis, St. Louis, Missouri
- Mallinckrodt Institute of Radiology, Washington University in St. Louis, St. Louis, Missouri
- Department of Biomedical Engineering, Washington University in St. Louis, St. Louis, Missouri
- Department of Neurology, Washington University in St. Louis, St. Louis, Missouri
| | - Ulugbek S Kamilov
- Department of Electrical and Systems Engineering, Washington University in St. Louis, St. Louis, Missouri
- Department of Computer Science and Engineering, Washington University in St. Louis, St. Louis, Missouri
| |
Collapse
|
11
|
Berkarda Z, Wiedemann S, Wilpert C, Strecker R, Koerzdoerfer G, Nickel D, Bamberg F, Benndorf M, Mayrhofer T, Russe MF, Weiss J, Diallo TD. Deep learning reconstructed T2-weighted Dixon imaging of the spine: Impact on acquisition time and image quality. Eur J Radiol 2024; 178:111633. [PMID: 39067266 DOI: 10.1016/j.ejrad.2024.111633] [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: 03/19/2024] [Revised: 06/30/2024] [Accepted: 07/15/2024] [Indexed: 07/30/2024]
Abstract
PURPOSE To assess the image quality and impact on acquisition time of a novel deep learning based T2 Dixon sequence (T2DL) of the spine. METHODS This prospective, single center study included n = 44 consecutive patients with a clinical indication for lumbar MRI at our university radiology department between September 2022 and March 2023. MRI examinations were performed on 1.5-T and 3-T scanners (MAGNETOM Aera and Vida; Siemens Healthineers, Erlangen, Germany) using dedicated spine coils. The MR study protocol consisted of our standard clinical protocol, including a T2 weighted standard Dixon sequence (T2std) and an additional T2DL acquisition. The latter used a conventional sampling pattern with a higher parallel acceleration factor. The individual contrasts acquired for Dixon water-fat separation were then reconstructed using a dedicated research application. After reconstruction of the contrast images from k-space data, a conventional water-fat separation was performed to provide derived water images. Two readers with 6 and 4 years of experience in interpreting MSK imaging, respectively, analyzed the images in a randomized fashion. Regarding overall image quality, banding artifacts, artifacts, sharpness, noise, and diagnostic confidence were analyzed using a 5-point Likert scale (from 1 = non-diagnostic to 5 = excellent image quality). Statistical analyses included the Wilcoxon signed-rank test and weighted Cohen's kappa statistics. RESULTS Forty-four patients (mean age 53 years (±18), male sex: 39 %) were prospectively included. Thirty-one examinations were performed on 1.5 T and 13 examinations on 3 T scanners. A sequence was successfully acquired in all patients. The total acquisition time of T2DL was 93 s at 1.5-T and 86 s at 3-T, compared to 235 s, and 257 s, respectively for T2std (reduction of acquisition time: 60.4 % at 1.5-T, and 66.5 % at 3-T; p < 0.01). Overall image quality was rated equal for both sequences (median T2DL: 5[3 -5], and median T2std: 5 [2 -5]; p = 0.57). T2DL showed significantly reduced noise levels compared to T2std (5 [4 -5] versus 4 [3 -4]; p < 0.001). In addition, sharpness was rated to be significantly higher in T2DL (5 [4 -5] versus 4 [3 -5]; p < 0.001). Although T2DL displayed significantly more banding artifacts (5 [2 -5] versus 5 [4 -5]; p < 0.001), no significant impact on readers diagnostic confidence between sequences was noted (T2std: 5 [2 -5], and T2DL: 5 [3 -5]; p = 0.61). Substantial inter-reader and intrareader agreement was observed for T2DL overall image quality (κ: 0.77, and κ: 0.8, respectively). CONCLUSION T2DL is feasible, yields an image quality comparable to the reference standard while substantially reducing the acquisition time.
Collapse
Affiliation(s)
- Zeynep Berkarda
- Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Germany
| | - Simon Wiedemann
- Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Germany
| | - Caroline Wilpert
- Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Germany
| | - Ralph Strecker
- EMEA Scientific Partnerships, Siemens Healthcare GmbH, Erlangen, Germany
| | | | - Dominik Nickel
- MR Application Predevelopment, Siemens Healthcare GmbH, Erlangen, Germany
| | - Fabian Bamberg
- Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Germany
| | - Matthias Benndorf
- Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Germany
| | - Thomas Mayrhofer
- School of Business Studies, Stralsund University of Applied Sciences, Stralsund, Germany; Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Maximilian Frederik Russe
- Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Germany
| | - Jakob Weiss
- Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Germany
| | - Thierno D Diallo
- Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Germany.
| |
Collapse
|
12
|
Wang Z, Luo G, Li Y, Cao P. Using a deep learning prior for accelerating hyperpolarized 13C MRSI on synthetic cancer datasets. Magn Reson Med 2024; 92:945-955. [PMID: 38440832 DOI: 10.1002/mrm.30053] [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: 09/12/2023] [Revised: 01/30/2024] [Accepted: 01/30/2024] [Indexed: 03/06/2024]
Abstract
PURPOSE We aimed to incorporate a deep learning prior with k-space data fidelity for accelerating hyperpolarized carbon-13 MRSI, demonstrated on synthetic cancer datasets. METHODS A two-site exchange model, derived from the Bloch equation of MR signal evolution, was firstly used in simulating training and testing data, that is, synthetic phantom datasets. Five singular maps generated from each simulated dataset were used to train a deep learning prior, which was then employed with the fidelity term to reconstruct the undersampled MRI k-space data. The proposed method was assessed on synthetic human brain tumor images (N = 33), prostate cancer images (N = 72), and mouse tumor images (N = 58) for three undersampling factors and 2.5% additive Gaussian noise. Furthermore, varied levels of Gaussian noise with SDs of 2.5%, 5%, and 10% were added on synthetic prostate cancer data, and corresponding reconstruction results were evaluated. RESULTS For quantitative evaluation, peak SNRs were approximately 32 dB, and the accuracy was generally improved for 5 to 8 dB compared with those from compressed sensing with L1-norm regularization or total variation regularization. Reasonable normalized RMS error were obtained. Our method also worked robustly against noise, even on a data with noise SD of 10%. CONCLUSION The proposed singular value decomposition + iterative deep learning model could be considered as a general framework that extended the application of deep learning MRI reconstruction to metabolic imaging. The morphology of tumors and metabolic images could be measured robustly in six times acceleration using our method.
Collapse
Affiliation(s)
- Zuojun Wang
- Department of Diagnostic Radiology, The University of Hong Kong, Hong Kong, People's Republic of China
| | - Guanxiong Luo
- Institute for Diagnostic and Interventional Radiology, University Medical Center Göttingen, Göttingen, Germany
| | - Ye Li
- Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology of Chinese Academy of Sciences, Shenzhen, People's Republic of China
| | - Peng Cao
- Department of Diagnostic Radiology, The University of Hong Kong, Hong Kong, People's Republic of China
| |
Collapse
|
13
|
Zhou X, Zhang Z, Du H, Qiu B. MLMFNet: A multi-level modality fusion network for multi-modal accelerated MRI reconstruction. Magn Reson Imaging 2024; 111:246-255. [PMID: 38663831 DOI: 10.1016/j.mri.2024.04.028] [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: 03/02/2023] [Revised: 04/09/2024] [Accepted: 04/19/2024] [Indexed: 06/01/2024]
Abstract
Magnetic resonance imaging produces detailed anatomical and physiological images of the human body that can be used in the clinical diagnosis and treatment of diseases. However, MRI suffers its comparatively longer acquisition time than other imaging methods and is thus vulnerable to motion artifacts, which ultimately lead to likely failed or even wrong diagnosis. In order to perform faster reconstruction, deep learning-based methods along with traditional strategies such as parallel imaging and compressed sensing come into play in recent years in this field. Meanwhile, in order to better analyze the diseases, it is also often necessary to acquire images in the same region of interest under different modalities, which yield images with different contrast levels. However, most of these aforementioned methods tend to use single-modal images for reconstruction, neglecting the correlation and redundancy information embedded in MR images acquired with different modalities. While there are works on multi-modal reconstruction, the information is yet to be efficiently explored. In this paper, we propose an end-to-end neural network called MLMFNet, which helps the reconstruction of the target modality by using information from the auxiliary modality across feature channels and layers. Specifically, this is highlighted by three components: (I) An encoder based on UNet with a single-stream strategy that fuses auxiliary and target modalities; (II) a decoder that tends to multi-level features from all layers of the encoder, and (III) a channel attention module. Quantitative and qualitative analyses are performed on a public brain dataset and knee brain dataset, which show that the proposed method achieves satisfying results in MRI reconstruction within the multi-modal context, and also demonstrate its effectiveness and potential to be used in clinical practice.
Collapse
Affiliation(s)
- Xiuyun Zhou
- Biomedical Engineering Center, University of Science and Technology of China, Hefei, Anhui 230026, China
| | - Zhenxi Zhang
- Biomedical Engineering Center, University of Science and Technology of China, Hefei, Anhui 230026, China
| | - Hongwei Du
- Biomedical Engineering Center, University of Science and Technology of China, Hefei, Anhui 230026, China.
| | - Bensheng Qiu
- Biomedical Engineering Center, University of Science and Technology of China, Hefei, Anhui 230026, China
| |
Collapse
|
14
|
Gharibshahian M, Torkashvand M, Bavisi M, Aldaghi N, Alizadeh A. Recent advances in artificial intelligent strategies for tissue engineering and regenerative medicine. Skin Res Technol 2024; 30:e70016. [PMID: 39189880 PMCID: PMC11348508 DOI: 10.1111/srt.70016] [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: 06/17/2024] [Accepted: 08/05/2024] [Indexed: 08/28/2024]
Abstract
BACKGROUND Tissue engineering and regenerative medicine (TERM) aim to repair or replace damaged or lost tissues or organs due to accidents, diseases, or aging, by applying different sciences. For this purpose, an essential part of TERM is the designing, manufacturing, and evaluating of scaffolds, cells, tissues, and organs. Artificial intelligence (AI) or the intelligence of machines or software can be effective in all areas where computers play a role. METHODS The "artificial intelligence," "machine learning," "tissue engineering," "clinical evaluation," and "scaffold" keywords used for searching in various databases and articles published from 2000 to 2024 were evaluated. RESULTS The combination of tissue engineering and AI has created a new generation of technological advancement in the biomedical industry. Experience in TERM has been refined using advanced design and manufacturing techniques. Advances in AI, particularly deep learning, offer an opportunity to improve scientific understanding and clinical outcomes in TERM. CONCLUSION The findings of this research show the high potential of AI, machine learning, and robots in the selection, design, and fabrication of scaffolds, cells, tissues, or organs, and their analysis, characterization, and evaluation after their implantation. AI can be a tool to accelerate the introduction of tissue engineering products to the bedside. HIGHLIGHTS The capabilities of artificial intelligence (AI) can be used in different ways in all the different stages of TERM and not only solve the existing limitations, but also accelerate the processes, increase efficiency and precision, reduce costs, and complications after transplantation. ML predicts which technologies have the most efficient and easiest path to enter the market and clinic. The use of AI along with these imaging techniques can lead to the improvement of diagnostic information, the reduction of operator errors when reading images, and the improvement of image analysis (such as classification, localization, regression, and segmentation).
Collapse
Affiliation(s)
- Maliheh Gharibshahian
- Nervous System Stem Cells Research CenterSemnan University of Medical SciencesSemnanIran
- Department of Tissue Engineering and Applied Cell SciencesSchool of MedicineSemnan University of Medical SciencesSemnanIran
| | | | - Mahya Bavisi
- Department of Tissue Engineering and Applied Cell SciencesSchool of Advanced Technologies in MedicineIran University of Medical SciencesTehranIran
| | - Niloofar Aldaghi
- Student Research CommitteeSchool of MedicineShahroud University of Medical SciencesShahroudIran
| | - Akram Alizadeh
- Nervous System Stem Cells Research CenterSemnan University of Medical SciencesSemnanIran
- Department of Tissue Engineering and Applied Cell SciencesSchool of MedicineSemnan University of Medical SciencesSemnanIran
| |
Collapse
|
15
|
Wang J, Salerno M. Deep learning-based rapid image reconstruction and motion correction for high-resolution cartesian first-pass myocardial perfusion imaging at 3T. Magn Reson Med 2024; 92:1104-1114. [PMID: 38576068 DOI: 10.1002/mrm.30106] [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: 12/11/2023] [Revised: 03/19/2024] [Accepted: 03/19/2024] [Indexed: 04/06/2024]
Abstract
PURPOSE To develop and evaluate a deep learning (DL) -based rapid image reconstruction and motion correction technique for high-resolution Cartesian first-pass myocardial perfusion imaging at 3T with whole-heart coverage for both single-slice (SS) and simultaneous multi-slice (SMS) acquisitions. METHODS 3D physics-driven unrolled network architectures were utilized for the reconstruction of high-resolution Cartesian perfusion imaging. The SS and SMS multiband (MB) = 2 networks were trained from 135 slices from 20 subjects. Structural similarity index (SSIM), peak SNR (PSNR), and normalized RMS error (NRMSE) were assessed, and prospective images were blindly graded by two experienced cardiologists (5, excellent; 1, poor). For respiratory motion correction, a 2D U-Net based motion corrected network was proposed, and the temporal fidelity and second-order derivative were calculated to assess the performance of the motion correction. RESULTS Excellent performance was demonstrated in the proposed technique with high SSIM and PSNR, and low NRMSE. Image quality scores were (4.3 [4.3, 4.4], 4.5 [4.4, 4.6], 4.3 [4.3, 4.4], and 4.5 [4.3, 4.5]) for SS DL and SS L1-SENSE, MB = 2 DL and MB = 2 SMS-L1-SENSE, respectively, showing no statistically significant difference (p > 0.05 for SS and SMS) between (SMS)-L1-SENSE and the proposed DL technique. The network inference time was around 4 s per dynamic perfusion series with 40 frames while the time of (SMS)-L1-SENSE with GPU acceleration was approximately 30 min. CONCLUSION The proposed DL-based image reconstruction and motion correction technique enabled rapid and high-quality reconstruction for SS and SMS MB = 2 high-resolution Cartesian first-pass perfusion imaging at 3T.
Collapse
Affiliation(s)
- Junyu Wang
- Department of Cardiovascular Medicine, Stanford University, Stanford, California, USA
| | - Michael Salerno
- Department of Cardiovascular Medicine, Stanford University, Stanford, California, USA
- Department of Radiology, Cardiovascular Imaging, Stanford University, Stanford, California, USA
| |
Collapse
|
16
|
Sun Y, Liu X, Liu Y, Jin R, Pang Y. DIRECTION: Deep cascaded reconstruction residual-based feature modulation network for fast MRI reconstruction. Magn Reson Imaging 2024; 111:157-167. [PMID: 38642780 DOI: 10.1016/j.mri.2024.04.023] [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: 10/30/2023] [Revised: 02/24/2024] [Accepted: 04/14/2024] [Indexed: 04/22/2024]
Abstract
Deep cascaded networks have been extensively studied and applied to accelerate Magnetic Resonance Imaging (MRI) and have shown promising results. Most existing works employ a large cascading number for the sake of superior performances. However, due to the lack of proper guidance, the reconstruction performance can easily reach a plateau and even face degradation if simply increasing the cascading number. In this paper, we aim to boost the reconstruction performance from a novel perspective by proposing a parallel architecture called DIRECTION that fully exploits the guiding value of the reconstruction residual of each subnetwork. Specifically, we introduce a novel Reconstruction Residual-Based Feature Modulation Mechanism (RRFMM) which utilizes the reconstruction residual of the previous subnetwork to guide the next subnetwork at the feature level. To achieve this, a Residual Attention Modulation Block (RAMB) is proposed to generate attention maps using multi-scale residual features to modulate the image features of the corresponding scales. Equipped with this strategy, each subnetwork within the cascaded network possesses its unique optimization objective and emphasis rather than blindly updating its parameters. To further boost the performance, we introduce the Cross-Stage Feature Reuse Connection (CSFRC) and the Reconstruction Dense Connection (RDC), which can reduce information loss and enhance representative ability. We conduct sufficient experiments and evaluate our method on the fastMRI knee dataset using multiple subsampling masks. Comprehensive experimental results show that our method can markedly boost the performance of cascaded networks and significantly outperforms other compared state-of-the-art methods quantitatively and qualitatively.
Collapse
Affiliation(s)
- Yong Sun
- TJK-BIIT Lab, School of Electrical and Information Engineering, Tianjin 300072, China.
| | - Xiaohan Liu
- TJK-BIIT Lab, School of Electrical and Information Engineering, Tianjin 300072, China.
| | - Yiming Liu
- TJK-BIIT Lab, School of Electrical and Information Engineering, Tianjin 300072, China; Tiandatz Technology, Tianjin 301723, China.
| | - Ruiqi Jin
- TJK-BIIT Lab, School of Electrical and Information Engineering, Tianjin 300072, China.
| | - Yanwei Pang
- TJK-BIIT Lab, School of Electrical and Information Engineering, Tianjin 300072, China.
| |
Collapse
|
17
|
Wu R, Li C, Zou J, Liang Y, Wang S. Model-based federated learning for accurate MR image reconstruction from undersampled k-space data. Comput Biol Med 2024; 180:108905. [PMID: 39067156 DOI: 10.1016/j.compbiomed.2024.108905] [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: 01/15/2024] [Revised: 06/15/2024] [Accepted: 07/14/2024] [Indexed: 07/30/2024]
Abstract
Deep learning-based methods have achieved encouraging performances in the field of Magnetic Resonance (MR) image reconstruction. Nevertheless, building powerful and robust deep learning models requires collecting large and diverse datasets from multiple centers. This raises concerns about ethics and data privacy. Recently, federated learning has emerged as a promising solution, enabling the utilization of multi-center data without the need for data transfer between institutions. Despite its potential, existing federated learning methods face challenges due to the high heterogeneity of data from different centers. Aggregation methods based on simple averaging, which are commonly used to combine the client's information, have shown limited reconstruction and generalization capabilities. In this paper, we propose a Model-based Federated learning framework (ModFed) to address these challenges. ModFed has three major contributions: (1) Different from existing data-driven federated learning methods, ModFed designs attention-assisted model-based neural networks that can alleviate the need for large amounts of data on each client; (2) To address the data heterogeneity issue, ModFed proposes an adaptive dynamic aggregation scheme, which can improve the generalization capability and robustness of the trained neural network models; (3) ModFed incorporates a spatial Laplacian attention mechanism and a personalized client-side loss regularization to capture the detailed information for accurate image reconstruction. The effectiveness of the proposed ModFed is evaluated on three in-vivo datasets. Experimental results show that when compared to six existing state-of-the-art federated learning approaches, ModFed achieves better MR image reconstruction performance with increased generalization capability. Codes will be made available at https://github.com/ternencewu123/ModFed.
Collapse
Affiliation(s)
- Ruoyou Wu
- Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China; Pengcheng Laboratory, Shenzhen, 518055, China; University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Cheng Li
- Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China
| | - Juan Zou
- School of Physics and Electronic Science, Changsha University of Science and Technology, Changsha, 410114, China
| | - Yong Liang
- Pengcheng Laboratory, Shenzhen, 518055, China
| | - Shanshan Wang
- Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China.
| |
Collapse
|
18
|
Vosshenrich J, Koerzdoerfer G, Fritz J. Modern acceleration in musculoskeletal MRI: applications, implications, and challenges. Skeletal Radiol 2024; 53:1799-1813. [PMID: 38441617 DOI: 10.1007/s00256-024-04634-2] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/13/2023] [Revised: 02/20/2024] [Accepted: 02/22/2024] [Indexed: 08/09/2024]
Abstract
Magnetic resonance imaging (MRI) is crucial for accurately diagnosing a wide spectrum of musculoskeletal conditions due to its superior soft tissue contrast resolution. However, the long acquisition times of traditional two-dimensional (2D) and three-dimensional (3D) fast and turbo spin-echo (TSE) pulse sequences can limit patient access and comfort. Recent technical advancements have introduced acceleration techniques that significantly reduce MRI times for musculoskeletal examinations. Key acceleration methods include parallel imaging (PI), simultaneous multi-slice acquisition (SMS), and compressed sensing (CS), enabling up to eightfold faster scans while maintaining image quality, resolution, and safety standards. These innovations now allow for 3- to 6-fold accelerated clinical musculoskeletal MRI exams, reducing scan times to 4 to 6 min for joints and spine imaging. Evolving deep learning-based image reconstruction promises even faster scans without compromising quality. Current research indicates that combining acceleration techniques, deep learning image reconstruction, and superresolution algorithms will eventually facilitate tenfold accelerated musculoskeletal MRI in routine clinical practice. Such rapid MRI protocols can drastically reduce scan times by 80-90% compared to conventional methods. Implementing these rapid imaging protocols does impact workflow, indirect costs, and workload for MRI technologists and radiologists, which requires careful management. However, the shift from conventional to accelerated, deep learning-based MRI enhances the value of musculoskeletal MRI by improving patient access and comfort and promoting sustainable imaging practices. This article offers a comprehensive overview of the technical aspects, benefits, and challenges of modern accelerated musculoskeletal MRI, guiding radiologists and researchers in this evolving field.
Collapse
Affiliation(s)
- Jan Vosshenrich
- Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA
- Department of Radiology, University Hospital Basel, Basel, Switzerland
| | | | - Jan Fritz
- Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA.
| |
Collapse
|
19
|
Liebrand LC, Karkalousos D, Poirion É, Emmer BJ, Roosendaal SD, Marquering HA, Majoie CBLM, Savatovsky J, Caan MWA. Deep learning for efficient reconstruction of highly accelerated 3D FLAIR MRI in neurological deficits. MAGMA (NEW YORK, N.Y.) 2024:10.1007/s10334-024-01200-8. [PMID: 39212832 DOI: 10.1007/s10334-024-01200-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/30/2024] [Revised: 08/07/2024] [Accepted: 08/08/2024] [Indexed: 09/04/2024]
Abstract
OBJECTIVE To compare compressed sensing (CS) and the Cascades of Independently Recurrent Inference Machines (CIRIM) with respect to image quality and reconstruction times when 12-fold accelerated scans of patients with neurological deficits are reconstructed. MATERIALS AND METHODS Twelve-fold accelerated 3D T2-FLAIR images were obtained from a cohort of 62 patients with neurological deficits on 3 T MRI. Images were reconstructed offline via CS and the CIRIM. Image quality was assessed in a blinded and randomized manner by two experienced interventional neuroradiologists and one experienced pediatric neuroradiologist on imaging artifacts, perceived spatial resolution (sharpness), anatomic conspicuity, diagnostic confidence, and contrast. The methods were also compared in terms of self-referenced quality metrics, image resolution, patient groups and reconstruction time. In ten scans, the contrast ratio (CR) was determined between lesions and white matter. The effect of acceleration factor was assessed in a publicly available fully sampled dataset, since ground truth data are not available in prospectively accelerated clinical scans. Specifically, 451 FLAIR scans, including scans with white matter lesions, were adopted from the FastMRI database to evaluate structural similarity (SSIM) and the CR of lesions and white matter on ranging acceleration factors from four-fold up to 12-fold. RESULTS Interventional neuroradiologists significantly preferred the CIRIM for imaging artifacts, anatomic conspicuity, and contrast. One rater significantly preferred the CIRIM in terms of sharpness and diagnostic confidence. The pediatric neuroradiologist preferred CS for imaging artifacts and sharpness. Compared to CS, the CIRIM reconstructions significantly improved in terms of imaging artifacts and anatomic conspicuity (p < 0.01) for higher resolution scans while yielding a 28% higher SNR (p = 0.001) and a 5.8% lower CR (p = 0.04). There were no differences between patient groups. Additionally, CIRIM was five times faster than CS was. An increasing acceleration factor did not lead to changes in CR (p = 0.92), but led to lower SSIM (p = 0.002). DISCUSSION Patients with neurological deficits can undergo MRI at a range of moderate to high acceleration. DL reconstruction outperforms CS in terms of image resolution, efficient denoising with a modest reduction in contrast and reduced reconstruction times.
Collapse
Affiliation(s)
- Luka C Liebrand
- Department of Biomedical Engineering & Physics, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, 1105 AZ, Amsterdam, The Netherlands
- Amsterdam Neuroscience, Brain Imaging, Amsterdam, The Netherlands
| | - Dimitrios Karkalousos
- Department of Biomedical Engineering & Physics, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, 1105 AZ, Amsterdam, The Netherlands
- Amsterdam Neuroscience, Brain Imaging, Amsterdam, The Netherlands
- Department of Radiology and Nuclear Medicine, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, Amsterdam, The Netherlands
| | - Émilie Poirion
- Fondation Rothschild Hospital, 29 Rue Manin, Paris, France
| | - Bart J Emmer
- Department of Radiology and Nuclear Medicine, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, Amsterdam, The Netherlands
| | - Stefan D Roosendaal
- Department of Radiology and Nuclear Medicine, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, Amsterdam, The Netherlands
| | - Henk A Marquering
- Department of Biomedical Engineering & Physics, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, 1105 AZ, Amsterdam, The Netherlands
- Department of Radiology and Nuclear Medicine, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, Amsterdam, The Netherlands
| | - Charles B L M Majoie
- Department of Radiology and Nuclear Medicine, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, Amsterdam, The Netherlands
| | | | - Matthan W A Caan
- Department of Biomedical Engineering & Physics, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, 1105 AZ, Amsterdam, The Netherlands.
- Amsterdam Neuroscience, Brain Imaging, Amsterdam, The Netherlands.
| |
Collapse
|
20
|
Grössinger D, Spann SM, Stollberger R, Pfeuffer J, Koten JW, Wood G. Real-time fMRI neurofeedback of the anterior insula using arterial spin labelling. Eur J Neurosci 2024. [PMID: 39193617 DOI: 10.1111/ejn.16502] [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: 09/23/2022] [Revised: 07/02/2024] [Accepted: 07/28/2024] [Indexed: 08/29/2024]
Abstract
Arterial spin labelling (ASL) is the only non-invasive technique that allows absolute quantification of perfusion and is increasingly used in brain activation studies. Contrary to the blood oxygen level-dependent (BOLD) effect ASL measures the cerebral blood flow (CBF) directly. However, the ASL signal has a lower signal-to-noise ratio (SNR), than the BOLD signal, which constrains its utilization in neurofeedback studies. If successful, ASL neurofeedback can be used to aid in the rehabilitation of health conditions with impaired blood flow, for example, stroke. We provide the first ASL-based neurofeedback study incorporating a double-blind, sham-controlled design. A pseudo-continuous ASL (pCASL) approach with background suppression and 3D GRASE readout was combined with a real-time post-processing pipeline. The real-time pipeline allows to monitor the ASL signal and provides real-time feedback on the neural activity to the subject. In total 41 healthy adults (19-56 years) divided into three groups underwent a neurofeedback-based emotion imagery training of the left anterior insula. Two groups differing only in the explicitness level of instruction received real training and a third group received sham feedback. Only those participants receiving real feedback with explicit instruction showed significantly higher absolute CBF values in the trained region during neurofeedback than participants receiving sham feedback. However, responder analyses of percent signal change values show no differences in activation between the three groups. Persisting limitations, such as the lower SNR, confounding effects of arterial transit time and partial volume effects still impact negatively the implementation of ASL neurofeedback.
Collapse
Affiliation(s)
| | - Stefan M Spann
- Institute of Medical Engineering, Graz University of Technology, Graz, Austria
| | - Rudolf Stollberger
- Institute of Medical Engineering, Graz University of Technology, Graz, Austria
- BioTechMed-Graz, Graz, Austria
| | - Josef Pfeuffer
- Siemens Healthcare, Application Development, Erlangen, Germany
| | | | - Guilherme Wood
- Institute of Psychology, University of Graz, Graz, Austria
- BioTechMed-Graz, Graz, Austria
| |
Collapse
|
21
|
Dane B, Bagga B, Bansal B, Beier S, Kim S, Reddy A, Fenty F, Keerthivasan M, Chandarana H. Accelerated T2-weighted MRI of the bowel at 3T using a single-shot technique with deep learning-based image reconstruction: impact on image quality and disease detection. Acad Radiol 2024:S1076-6332(24)00586-5. [PMID: 39198137 DOI: 10.1016/j.acra.2024.08.023] [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: 05/06/2024] [Revised: 07/26/2024] [Accepted: 08/12/2024] [Indexed: 09/01/2024]
Abstract
RATIONALE AND OBJECTIVE A single-shot T2-weighted deep-learning-based image reconstruction (DL-HASTE) has been recently developed allowing for shorter acquisition time than conventional half-Fourier acquisition single-shot turbo-spin echo (HASTE). The purpose of this study was to compare image quality of conventional 6 mm HASTE with DL-HASTE at 4 mm and 6 mm slice thickness. MATERIALS AND METHODS 91 patients (51 female; mean±SD age: 44±10years) who underwent 3T MR enterography from 5/15/2023-7/15/2023 including pelvic conventional HASTE and DL-HASTE were included. Patients either had 4 mm-DL-HASTE or 6 mm-DL-HASTE. Four abdominal radiologists, blinded to sequence type, independently evaluated overall image quality, artifacts over bowel, bowel wall sharpness, and confidence for the presence/absence of bowel abnormalities on 5-point Likert scales. Readers recorded the presence/absence of ileal wall thickening, ileal inflammation, stricture, and penetrating disease on each sequence. Wilcoxon signed-rank test with continuity correction was used for paired comparisons and Wilcoxon rank sum test was used for unpaired ordinal comparisons. A p < .05 indicated statistical significance. RESULTS Acquisition times for 6 mm HASTE, 4 mm-DL-HASTE, and 6 mm-DL-HASTE were 64 s, 51 s, and 49 s, respectively. Overall image quality and bowel sharpness were significantly improved for 4 mm-DL-HASTE versus HASTE for 3/4 readers (all p < .05) and similar for the 4th reader (p > .05). Diagnostic confidence was similar for all readers (p > .05). 6 mm-DL-HASTE was similar to HASTE for bowel sharpness, image quality, and confidence for 3/4 readers (all p > .05). The presence of ileal thickening, ileal inflammation, stricture, and penetrating disease were similar for all readers for HASTE, 4 mm-DL-HASTE, and 6 mm-DL-HASTE (all p > .05). CONCLUSION 4 mm-DL-HASTE had superior image quality than conventional HASTE at shorter acquisition time.
Collapse
Affiliation(s)
- Bari Dane
- NYU Langone Health Department of Radiology, 660 1st Avenue, New York, NY 10016 (B.D., B.B., S.B., S.K., A.R., F.F., H.C.); NYU Long Island Department of Radiology, Mineola, NY 11501 (B.D., B.B., B.B., S.B., A.R., F.F., M.K., H.C.).
| | - Barun Bagga
- NYU Langone Health Department of Radiology, 660 1st Avenue, New York, NY 10016 (B.D., B.B., S.B., S.K., A.R., F.F., H.C.); NYU Long Island Department of Radiology, Mineola, NY 11501 (B.D., B.B., B.B., S.B., A.R., F.F., M.K., H.C.)
| | - Bhavik Bansal
- NYU Long Island Department of Radiology, Mineola, NY 11501 (B.D., B.B., B.B., S.B., A.R., F.F., M.K., H.C.); All India Institute of Medical Sciences, New Delhi, India (B.B.)
| | - Sarah Beier
- NYU Langone Health Department of Radiology, 660 1st Avenue, New York, NY 10016 (B.D., B.B., S.B., S.K., A.R., F.F., H.C.); NYU Long Island Department of Radiology, Mineola, NY 11501 (B.D., B.B., B.B., S.B., A.R., F.F., M.K., H.C.)
| | - Sooah Kim
- NYU Langone Health Department of Radiology, 660 1st Avenue, New York, NY 10016 (B.D., B.B., S.B., S.K., A.R., F.F., H.C.)
| | - Arthi Reddy
- NYU Langone Health Department of Radiology, 660 1st Avenue, New York, NY 10016 (B.D., B.B., S.B., S.K., A.R., F.F., H.C.); NYU Long Island Department of Radiology, Mineola, NY 11501 (B.D., B.B., B.B., S.B., A.R., F.F., M.K., H.C.)
| | - Felicia Fenty
- NYU Langone Health Department of Radiology, 660 1st Avenue, New York, NY 10016 (B.D., B.B., S.B., S.K., A.R., F.F., H.C.); NYU Long Island Department of Radiology, Mineola, NY 11501 (B.D., B.B., B.B., S.B., A.R., F.F., M.K., H.C.)
| | - Mahesh Keerthivasan
- NYU Long Island Department of Radiology, Mineola, NY 11501 (B.D., B.B., B.B., S.B., A.R., F.F., M.K., H.C.); Siemens Healthineers, Malvern, NJ (M.K.)
| | - Hersh Chandarana
- NYU Langone Health Department of Radiology, 660 1st Avenue, New York, NY 10016 (B.D., B.B., S.B., S.K., A.R., F.F., H.C.); NYU Long Island Department of Radiology, Mineola, NY 11501 (B.D., B.B., B.B., S.B., A.R., F.F., M.K., H.C.)
| |
Collapse
|
22
|
Vornehm M, Wetzl J, Giese D, Fürnrohr F, Pang J, Chow K, Gebker R, Ahmad R, Knoll F. CineVN: Variational network reconstruction for rapid functional cardiac cine MRI. Magn Reson Med 2024. [PMID: 39188085 DOI: 10.1002/mrm.30260] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/27/2024] [Revised: 07/09/2024] [Accepted: 08/01/2024] [Indexed: 08/28/2024]
Abstract
PURPOSE To develop a reconstruction method for highly accelerated cardiac cine MRI with high spatiotemporal resolution and low temporal blurring, and to demonstrate accurate estimation of ventricular volumes and myocardial strain in healthy subjects and in patients. METHODS The proposed method, called CineVN, employs a spatiotemporal Variational Network combined with conjugate gradient descent for optimized data consistency and improved image quality. The method is first evaluated on retrospectively undersampled cine MRI data in terms of image quality. Then, prospectively accelerated data are acquired in 18 healthy subjects both segmented over two heartbeats per slice as well as in real time with 1.6 mm isotropic resolution. Ventricular volumes and strain parameters are computed and compared to a compressed sensing reconstruction and to a conventional reference cine MRI acquisition. Lastly, the method is demonstrated in 46 patients and ventricular volumes and strain parameters are evaluated. RESULTS CineVN outperformed compressed sensing in image quality metrics on retrospectively undersampled data. Functional parameters and myocardial strain were the most accurate for CineVN compared to two state-of-the-art compressed sensing methods. CONCLUSION Deep learning-based reconstruction using our proposed method enables accurate evaluation of cardiac function in real-time cine MRI with high spatiotemporal resolution. This has the potential to improve cardiac imaging particularly for patients with arrhythmia or impaired breath-hold capability.
Collapse
Affiliation(s)
- Marc Vornehm
- Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
- Magnetic Resonance, Siemens Healthineers AG, Erlangen, Germany
| | - Jens Wetzl
- Magnetic Resonance, Siemens Healthineers AG, Erlangen, Germany
| | - Daniel Giese
- Magnetic Resonance, Siemens Healthineers AG, Erlangen, Germany
- Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Florian Fürnrohr
- Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Jianing Pang
- Siemens Medical Solutions USA Inc, Chicago, Illinois, USA
| | - Kelvin Chow
- Siemens Medical Solutions USA Inc, Chicago, Illinois, USA
| | - Rolf Gebker
- MVZ Diagnostikum Berlin 2020 GmbH, Berlin, Germany
| | - Rizwan Ahmad
- Biomedical Engineering, The Ohio State University, Columbus, Ohio, USA
| | - Florian Knoll
- Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
- Department of Radiology, New York University Grossman School of Medicine, New York, New York, USA
| |
Collapse
|
23
|
Bathla G, Messina SA, Black DF, Benson JC, Kollasch P, Nickel MD, Soni N, Rucker BC, Mark IT, Diehn FE, Agarwal AK. Deep Learning-Based Reconstruction of 3D T1 SPACE Vessel Wall Imaging Provides Improved Image Quality with Reduced Scan Times: A Preliminary Study. AJNR Am J Neuroradiol 2024:ajnr.A8382. [PMID: 38889969 DOI: 10.3174/ajnr.a8382] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2024] [Accepted: 06/06/2024] [Indexed: 06/20/2024]
Abstract
BACKGROUND AND PURPOSE Intracranial vessel wall imaging is technically challenging to implement, given the simultaneous requirements of high spatial resolution, excellent blood and CSF signal suppression, and clinically acceptable gradient times. Herein, we present our preliminary findings on the evaluation of a deep learning-optimized sequence using T1-weighted imaging. MATERIALS AND METHODS Clinical and optimized deep learning-based image reconstruction T1 3D Sampling Perfection with Application optimized Contrast using different flip angle Evolution (SPACE) were evaluated, comparing noncontrast sequences in 10 healthy controls and postcontrast sequences in 5 consecutive patients. Images were reviewed on a Likert-like scale by 4 fellowship-trained neuroradiologists. Scores (range, 1-4) were separately assigned for 11 vessel segments in terms of vessel wall and lumen delineation. Additionally, images were evaluated in terms of overall background noise, image sharpness, and homogeneous CSF signal. Segment-wise scores were compared using paired samples t tests. RESULTS The scan time for the clinical and deep learning-based image reconstruction sequences were 7:26 minutes and 5:23 minutes respectively. Deep learning-based image reconstruction images showed consistently higher wall signal and lumen visualization scores, with the differences being statistically significant in most vessel segments on both pre- and postcontrast images. Deep learning-based image reconstruction had lower background noise, higher image sharpness, and uniform CSF signal. Depiction of intracranial pathologies was better or similar on the deep learning-based image reconstruction. CONCLUSIONS Our preliminary findings suggest that deep learning-based image reconstruction-optimized intracranial vessel wall imaging sequences may be helpful in achieving shorter gradient times with improved vessel wall visualization and overall image quality. These improvements may help with wider adoption of intracranial vessel wall imaging in clinical practice and should be further validated on a larger cohort.
Collapse
Affiliation(s)
- Girish Bathla
- From the Department of Radiology (G.B., S.A.M., D.F.B., J.C.B., B.C.R., I.T.M., F.E.D.), Mayo Clinic, Rochester, Minnesota
| | - Steven A Messina
- From the Department of Radiology (G.B., S.A.M., D.F.B., J.C.B., B.C.R., I.T.M., F.E.D.), Mayo Clinic, Rochester, Minnesota
| | - David F Black
- From the Department of Radiology (G.B., S.A.M., D.F.B., J.C.B., B.C.R., I.T.M., F.E.D.), Mayo Clinic, Rochester, Minnesota
| | - John C Benson
- From the Department of Radiology (G.B., S.A.M., D.F.B., J.C.B., B.C.R., I.T.M., F.E.D.), Mayo Clinic, Rochester, Minnesota
| | - Peter Kollasch
- Siemens Healthineers AG (P.K., M.D.N.), Forchheim, Germany
| | | | - Neetu Soni
- Department of Radiology (N.S., A.K.A.), Mayo Clinic, Jacksonville, Florida
| | - Brian C Rucker
- From the Department of Radiology (G.B., S.A.M., D.F.B., J.C.B., B.C.R., I.T.M., F.E.D.), Mayo Clinic, Rochester, Minnesota
| | - Ian T Mark
- From the Department of Radiology (G.B., S.A.M., D.F.B., J.C.B., B.C.R., I.T.M., F.E.D.), Mayo Clinic, Rochester, Minnesota
| | - Felix E Diehn
- From the Department of Radiology (G.B., S.A.M., D.F.B., J.C.B., B.C.R., I.T.M., F.E.D.), Mayo Clinic, Rochester, Minnesota
| | - Amit K Agarwal
- Department of Radiology (N.S., A.K.A.), Mayo Clinic, Jacksonville, Florida
| |
Collapse
|
24
|
Shang Z, Chauhan V, Devi K, Patil S. Artificial Intelligence, the Digital Surgeon: Unravelling Its Emerging Footprint in Healthcare - The Narrative Review. J Multidiscip Healthc 2024; 17:4011-4022. [PMID: 39165254 PMCID: PMC11333562 DOI: 10.2147/jmdh.s482757] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2024] [Accepted: 08/09/2024] [Indexed: 08/22/2024] Open
Abstract
Background Artificial Intelligence (AI) holds transformative potential for the healthcare industry, offering innovative solutions for diagnosis, treatment planning, and improving patient outcomes. As AI continues to be integrated into healthcare systems, it promises advancements across various domains. This review explores the diverse applications of AI in healthcare, along with the challenges and limitations that need to be addressed. The aim is to provide a comprehensive overview of AI's impact on healthcare and to identify areas for further development and focus. Main Applications The review discusses the broad range of AI applications in healthcare. In medical imaging and diagnostics, AI enhances the accuracy and efficiency of diagnostic processes, aiding in early disease detection. AI-powered clinical decision support systems assist healthcare professionals in patient management and decision-making. Predictive analytics using AI enables the prediction of patient outcomes and identification of potential health risks. AI-driven robotic systems have revolutionized surgical procedures, improving precision and outcomes. Virtual assistants and chatbots enhance patient interaction and support, providing timely information and assistance. In the pharmaceutical industry, AI accelerates drug discovery and development by identifying potential drug candidates and predicting their efficacy. Additionally, AI improves administrative efficiency and operational workflows in healthcare, streamlining processes and reducing costs. AI-powered remote monitoring and telehealth solutions expand access to healthcare, particularly in underserved areas. Challenges and Limitations Despite the significant promise of AI in healthcare, several challenges persist. Ensuring the reliability and consistency of AI-driven outcomes is crucial. Privacy and security concerns must be navigated carefully, particularly in handling sensitive patient data. Ethical considerations, including bias and fairness in AI algorithms, need to be addressed to prevent unintended consequences. Overcoming these challenges is critical for the ethical and successful integration of AI in healthcare. Conclusion The integration of AI into healthcare is advancing rapidly, offering substantial benefits in improving patient care and operational efficiency. However, addressing the associated challenges is essential to fully realize the transformative potential of AI in healthcare. Future efforts should focus on enhancing the reliability, transparency, and ethical standards of AI technologies to ensure they contribute positively to global health outcomes.
Collapse
Affiliation(s)
- Zifang Shang
- Guangdong Engineering Technological Research Centre of Clinical Molecular Diagnosis and Antibody Drugs, Meizhou People’s Hospital (Huangtang Hospital), Meizhou Academy of Medical Sciences, Meizhou, People’s Republic of China
| | - Varun Chauhan
- Multi-Disciplinary Research Unit, Government Institute of Medical Sciences, Greater Noida, India
| | - Kirti Devi
- Department of Medicine, Government Institute of Medical Sciences, Greater Noida, India
| | - Sandip Patil
- Department Haematology and Oncology, Shenzhen Children’s Hospital, Shenzhen, People’s Republic of China
| |
Collapse
|
25
|
Olthof SC, Weiland E, Benkert T, Wessling D, Leyhr D, Afat S, Nikolaou K, Preibsch H. Optimizing Image Quality with High-Resolution, Deep-Learning-Based Diffusion-Weighted Imaging in Breast Cancer Patients at 1.5 T. Diagnostics (Basel) 2024; 14:1742. [PMID: 39202230 PMCID: PMC11353399 DOI: 10.3390/diagnostics14161742] [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: 06/11/2024] [Revised: 08/01/2024] [Accepted: 08/08/2024] [Indexed: 09/03/2024] Open
Abstract
The objective of this study was to evaluate a high-resolution deep-learning (DL)-based diffusion-weighted imaging (DWI) sequence for breast magnetic resonance imaging (MRI) in comparison to a standard DWI sequence (DWIStd) at 1.5 T. It is a prospective study of 38 breast cancer patients, who were scanned with DWIStd and DWIDL. Both DWI sequences were scored for image quality, sharpness, artifacts, contrast, noise, and diagnostic confidence with a Likert-scale from 1 (non-diagnostic) to 5 (excellent). The lesion diameter was evaluated on b 800 DWI, apparent diffusion coefficient (ADC), and the second subtraction (SUB) of the contrast-enhanced T1 VIBE. SNR was also calculated. Statistics included correlation analyses and paired t-tests. High-resolution DWIDL offered significantly superior image quality, sharpness, noise, contrast, and diagnostic confidence (each p < 0.02)). Artifacts were significantly higher in DWIDL by one reader (M = 4.62 vs. 4.36 Likert scale, p < 0.01) without affecting the diagnostic confidence. SNR was higher in DWIDL for b 50 and ADC maps (each p = 0.07). Acquisition time was reduced by 22% in DWIDL. The lesion diameters in DWI b 800DL and Std and ADCDL and Std were respectively 6% lower compared to the 2nd SUB. A DL-based diffusion sequence at 1.5 T in breast MRI offers a higher resolution and a faster acquisition, including only minimally more artefacts without affecting the diagnostic confidence.
Collapse
Affiliation(s)
- Susann-Cathrin Olthof
- Department of Diagnostic and Interventional Radiology, University Hospital of Tuebingen, 72076 Tuebingen, Germany; (S.A.); (K.N.); (H.P.)
| | - Elisabeth Weiland
- MR Application Predevelopment, Siemens Healthineers AG, 91052 Erlangen, Germany; (E.W.); (T.B.)
| | - Thomas Benkert
- MR Application Predevelopment, Siemens Healthineers AG, 91052 Erlangen, Germany; (E.W.); (T.B.)
| | - Daniel Wessling
- Department of Neuroradiology, University Hospital of Heidelberg, 69120 Heidelberg, Germany;
| | - Daniel Leyhr
- Faculty of Economics and Social Sciences, Institute of Sports Science & Methods Center, University of Tuebingen, 72074 Tuebingen, Germany;
| | - Saif Afat
- Department of Diagnostic and Interventional Radiology, University Hospital of Tuebingen, 72076 Tuebingen, Germany; (S.A.); (K.N.); (H.P.)
| | - Konstantin Nikolaou
- Department of Diagnostic and Interventional Radiology, University Hospital of Tuebingen, 72076 Tuebingen, Germany; (S.A.); (K.N.); (H.P.)
- Cluster of Excellence iFIT (EXC 2180) “Image Guided and Functionally Instructed Tumor Therapies”, University of Tuebingen, 72074 Tuebingen, Germany
| | - Heike Preibsch
- Department of Diagnostic and Interventional Radiology, University Hospital of Tuebingen, 72076 Tuebingen, Germany; (S.A.); (K.N.); (H.P.)
| |
Collapse
|
26
|
Yang Z, Shen D, Chan KWY, Huang J. Attention-Based MultiOffset Deep Learning Reconstruction of Chemical Exchange Saturation Transfer (AMO-CEST) MRI. IEEE J Biomed Health Inform 2024; 28:4636-4647. [PMID: 38776205 DOI: 10.1109/jbhi.2024.3404225] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/24/2024]
Abstract
One challenge of chemical exchange saturation transfer (CEST) magnetic resonance imaging (MRI) is the long scan time due to multiple acquisitions of images at different saturation frequency offsets. k-space under-sampling strategy is commonly used to accelerate MRI acquisition, while this could introduce artifacts and reduce signal-to-noise ratio (SNR). To accelerate CEST-MRI acquisition while maintaining suitable image quality, we proposed an attention-based multioffset deep learning reconstruction network (AMO-CEST) with a multiple radial k-space sampling strategy for CEST-MRI. The AMO-CEST also contains dilated convolution to enlarge the receptive field and data consistency module to preserve the sampled k-space data. We evaluated the proposed method on a mouse brain dataset containing 5760 CEST images acquired at a pre-clinical 3 T MRI scanner. Quantitative results demonstrated that AMO-CEST showed obvious improvement over zero-filling method with a PSNR enhancement of 11 dB, a SSIM enhancement of 0.15, and a NMSE decrease of [Formula: see text] in three acquisition orientations. Compared with other deep learning-based models, AMO-CEST showed visual and quantitative improvements in images from three different orientations. We also extracted molecular contrast maps, including the amide proton transfer (APT) and the relayed nuclear Overhauser enhancement (rNOE). The results demonstrated that the CEST contrast maps derived from the CEST images of AMO-CEST were comparable to those derived from the original high-resolution CEST images. The proposed AMO-CEST can efficiently reconstruct high-quality CEST images from under-sampled k-space data and thus has the potential to accelerate CEST-MRI acquisition.
Collapse
|
27
|
Feuerriegel GC, Goller SS, von Deuster C, Sutter R. Inflammatory Knee Synovitis: Evaluation of an Accelerated FLAIR Sequence Compared With Standard Contrast-Enhanced Imaging. Invest Radiol 2024; 59:599-604. [PMID: 38329824 DOI: 10.1097/rli.0000000000001065] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/10/2024]
Abstract
OBJECTIVES The aim of this study was to assess the diagnostic value and accuracy of a deep learning (DL)-accelerated fluid attenuated inversion recovery (FLAIR) sequence with fat saturation (FS) in patients with inflammatory synovitis of the knee. MATERIALS AND METHODS Patients with suspected knee synovitis were retrospectively included between January and September 2023. All patients underwent a 3 T knee magnetic resonance imaging including a DL-accelerated noncontrast FLAIR FS sequence (acquisition time: 1 minute 38 seconds) and a contrast-enhanced (CE) T1-weighted FS sequence (acquisition time: 4 minutes 50 seconds), which served as reference standard. All knees were scored by 2 radiologists using the semiquantitative modified knee synovitis score, effusion synovitis score, and Hoffa inflammation score. Diagnostic confidence, image quality, and image artifacts were rated on separate Likert scales. Wilcoxon signed rank test was used to compare the semiquantitative scores. Interreader and intrareader reproducibility were calculated using Cohen κ. RESULTS Fifty-five patients (mean age, 52 ± 17 years; 28 females) were included in the study. Twenty-seven patients (49%) had mild to moderate synovitis (synovitis score 6-13), and 17 patients (31%) had severe synovitis (synovitis score >14). No signs of synovitis were detected in 11 patients (20%) (synovitis score <5). Semiquantitative assessment of the whole knee synovitis score showed no significant difference between the DL-accelerated FLAIR sequence and the CE T1-weighted sequence (mean FLAIR score: 10.69 ± 8.83, T1 turbo spin-echo FS: 10.74 ± 10.32; P = 0.521). Both interreader and intrareader reproducibility were excellent (range Cohen κ [0.82-0.96]). CONCLUSIONS Assessment of inflammatory knee synovitis using a DL-accelerated noncontrast FLAIR FS sequence was feasible and equivalent to CE T1-weighted FS imaging.
Collapse
Affiliation(s)
- Georg C Feuerriegel
- From the Department of Radiology, Balgrist University Hospital, Faculty of Medicine, University of Zurich, Zurich, Switzerland (G.C.F., S.S.G., R.S.); Advanced Clinical Imaging Technology, Siemens Healthineers International AG, Zurich, Switzerland (C.v.D.); and Swiss Center for Musculoskeletal Imaging, Balgrist Campus, Zurich, Switzerland (C.v.D.)
| | | | | | | |
Collapse
|
28
|
Li Q, Xu WY, Sun NN, Feng QX, Hou YJ, Sang ZT, Zhu ZN, Hsu YC, Nickel D, Xu H, Zhang YD, Liu XS. Deep learning-accelerated T2WI: image quality, efficiency, and staging performance against BLADE T2WI for gastric cancer. Abdom Radiol (NY) 2024; 49:2574-2584. [PMID: 38662208 DOI: 10.1007/s00261-024-04323-7] [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: 02/29/2024] [Revised: 03/29/2024] [Accepted: 03/29/2024] [Indexed: 04/26/2024]
Abstract
PURPOSE The purpose of our study is to investigate image quality, efficiency, and diagnostic performance of a deep learning-accelerated single-shot breath-hold (DLSB) against BLADE for T2-weighted MR imaging (T2WI) for gastric cancer (GC). METHODS 112 patients with GCs undergoing gastric MRI were prospectively enrolled between Aug 2022 and Dec 2022. Axial DLSB-T2WI and BLADE-T2WI of stomach were scanned with same spatial resolution. Three radiologists independently evaluated the image qualities using a 5-scale Likert scales (IQS) in terms of lesion delineation, gastric wall boundary conspicuity, and overall image quality. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated in measurable lesions. T staging was conducted based on the results of both sequences for GC patients with gastrectomy. Pairwise comparisons between DLSB-T2WI and BLADE-T2WI were performed using the Wilcoxon signed-rank test, paired t-test, and chi-squared test. Kendall's W, Fleiss' Kappa, and intraclass correlation coefficient values were used to determine inter-reader reliability. RESULTS Against BLADE, DLSB reduced total acquisition time of T2WI from 495 min (mean 4:42 per patient) to 33.6 min (18 s per patient), with better overall image quality that produced 9.43-fold, 8.00-fold, and 18.31-fold IQS upgrading against BALDE, respectively, in three readers. In 69 measurable lesions, DLSB-T2WI had higher mean SNR and higher CNR than BLADE-T2WI. Among 71 patients with gastrectomy, DLSB-T2WI resulted in comparable accuracy to BLADE-T2WI in staging GCs (P > 0.05). CONCLUSIONS DLSB-T2WI demonstrated shorter acquisition time, better image quality, and comparable staging accuracy, which could be an alternative to BLADE-T2WI for gastric cancer imaging.
Collapse
Affiliation(s)
- Qiong Li
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Wei-Yue Xu
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Na-Na Sun
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Qiu-Xia Feng
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Ya-Jun Hou
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Zi-Tong Sang
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Zhen-Ning Zhu
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Yi-Cheng Hsu
- MR Collaboration, Siemens Healthineers Ltd, Shanghai, China
| | - Dominik Nickel
- MR Applications Predevelopment, Siemens Healthcare GmbH, Erlangen, Germany
| | - Hao Xu
- Department of General Surgery, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Yu-Dong Zhang
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Xi-Sheng Liu
- Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China.
| |
Collapse
|
29
|
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
|
30
|
Bosbach WA, Merdes KC, Jung B, Montazeri E, Anderson S, Mitrakovic M, Daneshvar K. Deep Learning Reconstruction of Accelerated MRI: False-Positive Cartilage Delamination Inserted in MRI Arthrography Under Traction. Top Magn Reson Imaging 2024; 33:e0313. [PMID: 39016321 DOI: 10.1097/rmr.0000000000000313] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2024] [Accepted: 05/28/2024] [Indexed: 07/18/2024]
Abstract
OBJECTIVES The radiological imaging industry is developing and starting to offer a range of novel artificial intelligence software solutions for clinical radiology. Deep learning reconstruction of magnetic resonance imaging data seems to allow for the acceleration and undersampling of imaging data. Resulting reduced acquisition times would lead to greater machine utility and to greater cost-efficiency of machine operations. MATERIALS AND METHODS Our case shows images from magnetic resonance arthrography under traction of the right hip joint from a 30-year-old, otherwise healthy, male patient. RESULTS The undersampled image data when reconstructed by a deep learning tool can contain false-positive cartilage delamination and false-positive diffuse cartilage defects. CONCLUSIONS In the future, precision of this novel technology will have to be put to thorough testing. Bias of systems, in particular created by the choice of training data, will have to be part of those assessments.
Collapse
Affiliation(s)
- Wolfram A Bosbach
- Department of Diagnostic, Interventional and Pediatric Radiology (DIPR), Inselspital, Bern University Hospital, University of Bern, Switzerland
| | | | | | | | | | | | | |
Collapse
|
31
|
Levac B, Kumar S, Jalal A, Tamir JI. Accelerated motion correction with deep generative diffusion models. Magn Reson Med 2024; 92:853-868. [PMID: 38688874 DOI: 10.1002/mrm.30082] [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: 09/18/2023] [Revised: 01/02/2024] [Accepted: 02/23/2024] [Indexed: 05/02/2024]
Abstract
PURPOSE The aim of this work is to develop a method to solve the ill-posed inverse problem of accelerated image reconstruction while correcting forward model imperfections in the context of subject motion during MRI examinations. METHODS The proposed solution uses a Bayesian framework based on deep generative diffusion models to jointly estimate a motion-free image and rigid motion estimates from subsampled and motion-corrupt two-dimensional (2D) k-space data. RESULTS We demonstrate the ability to reconstruct motion-free images from accelerated two-dimensional (2D) Cartesian and non-Cartesian scans without any external reference signal. We show that our method improves over existing correction techniques on both simulated and prospectively accelerated data. CONCLUSION We propose a flexible framework for retrospective motion correction of accelerated MRI based on deep generative diffusion models, with potential application to other forward model corruptions.
Collapse
Affiliation(s)
- Brett Levac
- Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, Texas, USA
| | - Sidharth Kumar
- Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, Texas, USA
| | - Ajil Jalal
- Electrical Engineering and Computer Sciences, University of California at Berkeley, Berkeley, California, USA
| | - Jonathan I Tamir
- Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, Texas, USA
| |
Collapse
|
32
|
Cheng H, Hou X, Huang G, Jia S, Yang G, Nie S. Feature Fusion for Multi-Coil Compressed MR Image Reconstruction. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024; 37:1969-1979. [PMID: 38459398 PMCID: PMC11300769 DOI: 10.1007/s10278-024-01057-2] [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: 10/30/2023] [Revised: 02/14/2024] [Accepted: 02/15/2024] [Indexed: 03/10/2024]
Abstract
Magnetic resonance imaging (MRI) occupies a pivotal position within contemporary diagnostic imaging modalities, offering non-invasive and radiation-free scanning. Despite its significance, MRI's principal limitation is the protracted data acquisition time, which hampers broader practical application. Promising deep learning (DL) methods for undersampled magnetic resonance (MR) image reconstruction outperform the traditional approaches in terms of speed and image quality. However, the intricate inter-coil correlations have been insufficiently addressed, leading to an underexploitation of the rich information inherent in multi-coil acquisitions. In this article, we proposed a method called "Multi-coil Feature Fusion Variation Network" (MFFVN), which introduces an encoder to extract the feature from multi-coil MR image directly and explicitly, followed by a feature fusion operation. Coil reshaping enables the 2D network to achieve satisfactory reconstruction results, while avoiding the introduction of a significant number of parameters and preserving inter-coil information. Compared with VN, MFFVN yields an improvement in the average PSNR and SSIM of the test set, registering enhancements of 0.2622 dB and 0.0021 dB respectively. This uplift can be attributed to the integration of feature extraction and fusion stages into the network's architecture, thereby effectively leveraging and combining the multi-coil information for enhanced image reconstruction quality. The proposed method outperforms the state-of-the-art methods on fastMRI dataset of multi-coil brains under a fourfold acceleration factor without incurring substantial computation overhead.
Collapse
Affiliation(s)
- Hang Cheng
- School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, China
| | - Xuewen Hou
- Radiotherapy Business Unit, Shanghai United Imaging Healthcare Co., Ltd., Shanghai, 201807, China
| | - Gang Huang
- Shanghai Key Laboratory of Molecular Imaging, Shanghai University of Medicine and Health Sciences, Shanghai, 201318, China
| | - Shouqiang Jia
- Department of Radiology, Jinan People's Hospital Affiliated to Shandong First Medical University, Jinan Shandong, 271199, China.
| | - Guang Yang
- Shanghai Key Laboratory of Magnetic Resonance, Department of Physics, East China Normal University, Shanghai, 200062, China.
| | - Shengdong Nie
- School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, China.
| |
Collapse
|
33
|
Liu C, Li Z, Chen Z, Zhao B, Zheng Z, Song X. Highly-accelerated CEST MRI using frequency-offset-dependent k-space sampling and deep-learning reconstruction. Magn Reson Med 2024; 92:688-701. [PMID: 38623899 DOI: 10.1002/mrm.30089] [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: 10/10/2023] [Revised: 01/31/2024] [Accepted: 03/02/2024] [Indexed: 04/17/2024]
Abstract
PURPOSE To develop a highly accelerated CEST Z-spectral acquisition method using a specifically-designed k-space sampling pattern and corresponding deep-learning-based reconstruction. METHODS For k-space down-sampling, a customized pattern was proposed for CEST, with the randomized probability following a frequency-offset-dependent (FOD) function in the direction of saturation offset. For reconstruction, the convolution network (CNN) was enhanced with a Partially Separable (PS) function to optimize the spatial domain and frequency domain separately. Retrospective experiments on a self-acquired human brain dataset (13 healthy adults and 15 brain tumor patients) were conducted using k-space resampling. The prospective performance was also assessed on six healthy subjects. RESULTS In retrospective experiments, the combination of FOD sampling and PS network (FOD + PSN) showed the best quantitative metrics for reconstruction, outperforming three other combinations of conventional sampling with varying density and a regular CNN (nMSE and SSIM, p < 0.001 for healthy subjects). Across all acceleration factors from 4 to 14, the FOD + PSN approach consistently outperformed the comparative methods in four contrast maps including MTRasym, MTRrex, as well as the Lorentzian Difference maps of amide and nuclear Overhauser effect (NOE). In the subspace replacement experiment, the error distribution demonstrated the denoising benefits achieved in the spatial subspace. Finally, our prospective results obtained from healthy adults and brain tumor patients (14×) exhibited the initial feasibility of our method, albeit with less accurate reconstruction than retrospective ones. CONCLUSION The combination of FOD sampling and PSN reconstruction enabled highly accelerated CEST MRI acquisition, which may facilitate CEST metabolic MRI for brain tumor patients.
Collapse
Affiliation(s)
- Chuyu Liu
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, Tsinghua University, Beijing, China
| | - Zhongsen Li
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, Tsinghua University, Beijing, China
| | - Zhensen Chen
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China
- Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence (Fudan University), Ministry of Education, Shanghai, China
| | - Benqi Zhao
- Department of Radiology, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University, Beijing, China
| | - Zhuozhao Zheng
- Department of Radiology, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University, Beijing, China
| | - Xiaolei Song
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, Tsinghua University, Beijing, China
| |
Collapse
|
34
|
Shen L, Xu H, Liao Q, Yuan Y, Yu D, Wei J, Yang Z, Wang L. A Feasibility Study of AI-Assisted Compressed Sensing in Prostate T2-Weighted Imaging. Acad Radiol 2024:S1076-6332(24)00434-3. [PMID: 39068095 DOI: 10.1016/j.acra.2024.06.048] [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: 04/21/2024] [Revised: 06/15/2024] [Accepted: 06/28/2024] [Indexed: 07/30/2024]
Abstract
RATIONALE AND OBJECTIVES To evaluate the image quality and PI-RADS scoring performance of prostate T2-weighted imaging (T2WI) based on AI-assisted compressed sensing (ACS). MATERIALS AND METHODS In this prospective study, adult male urological outpatients or inpatients underwent prostate MRI, including T2WI, diffusion-weighted imaging and apparent diffusion coefficient maps. Three accelerated scanning protocols using parallel imaging (PI) and ACS: T2WIPI, T2WIACS1 and T2WIACS2 were evaluated through comparative analysis. Quantitative analysis included signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), slope profile, and edge rise distance (ERD). Image quality was qualitatively assessed using a five-point Likert scale (ranging from 1 = non-diagnostic to 5 = excellent). PI-RADS scores were determined for the largest or most suspicious lesions in each patient. The Friedman test and one-way ANOVA with post hoc tests were utilized for group comparisons, with statistical significance set at P < 0.05. RESULTS This study included 40 participants. Compared to PI, ACS reduced acquisition time by over 50%, significantly enhancing the CNR of sagittal and axial T2WI (P < 0.05), significantly improving the image quality of sagittal and axial T2WI (P < 0.05). No significant differences were observed in slope profile, ERD, and PI-RADS scores between groups (P > 0.05). CONCLUSION ACS reduced prostate T2WI acquisition time by half while improving image quality without affecting PI-RADS scores.
Collapse
Affiliation(s)
- Liting Shen
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing 100050, China (L.S., H.X., Q.L., Y.Y., Z.Y., L.W.)
| | - Hui Xu
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing 100050, China (L.S., H.X., Q.L., Y.Y., Z.Y., L.W.)
| | - Qian Liao
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing 100050, China (L.S., H.X., Q.L., Y.Y., Z.Y., L.W.)
| | - Ying Yuan
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing 100050, China (L.S., H.X., Q.L., Y.Y., Z.Y., L.W.)
| | - Dan Yu
- United Imaging Research Institute of Intelligent Imaging, Beijing 100050, China (D.Y.)
| | - Jie Wei
- Shanghai United Imaging Intelligence Co., Ltd., Shanghai 200000, China (J.W.)
| | - Zhenghan Yang
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing 100050, China (L.S., H.X., Q.L., Y.Y., Z.Y., L.W.)
| | - Liang Wang
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing 100050, China (L.S., H.X., Q.L., Y.Y., Z.Y., L.W.).
| |
Collapse
|
35
|
Chaika M, Brendel JM, Ursprung S, Herrmann J, Gassenmaier S, Brendlin A, Werner S, Nickel MD, Nikolaou K, Afat S, Almansour H. Deep Learning Reconstruction of Prospectively Accelerated MRI of the Pancreas: Clinical Evaluation of Shortened Breath-Hold Examinations With Dixon Fat Suppression. Invest Radiol 2024:00004424-990000000-00235. [PMID: 39043213 DOI: 10.1097/rli.0000000000001110] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/25/2024]
Abstract
OBJECTIVE Deep learning (DL)-enabled magnetic resonance imaging (MRI) reconstructions can enable shortening of breath-hold examinations and improve image quality by reducing motion artifacts. Prospective studies with DL reconstructions of accelerated MRI of the upper abdomen in the context of pancreatic pathologies are lacking. In a clinical setting, the purpose of this study is to investigate the performance of a novel DL-based reconstruction algorithm in T1-weighted volumetric interpolated breath-hold examinations with partial Fourier sampling and Dixon fat suppression (hereafter, VIBE-DixonDL). The objective is to analyze its impact on acquisition time, image sharpness and quality, diagnostic confidence, pancreatic lesion conspicuity, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). METHODS This prospective single-center study included participants with various pancreatic pathologies who gave written consent from January 2023 to September 2023. During the same session, each participant underwent 2 MRI acquisitions using a 1.5 T scanner: conventional precontrast and postcontrast T1-weighted VIBE acquisitions with Dixon fat suppression (VIBE-Dixon, reference standard) using 4-fold parallel imaging acceleration and 6-fold accelerated VIBE-Dixon acquisitions with partial Fourier sampling utilizing a novel DL reconstruction tailored to the acquisition. A qualitative image analysis was performed by 4 readers. Acquisition time, image sharpness, overall image quality, image noise and artifacts, diagnostic confidence, as well as pancreatic lesion conspicuity and size were compared. Furthermore, a quantitative analysis of SNR and CNR was performed. RESULTS Thirty-two participants were evaluated (mean age ± SD, 62 ± 19 years; 20 men). The VIBE-DixonDL method enabled up to 52% reduction in average breath-hold time (7 seconds for VIBE-DixonDL vs 15 seconds for VIBE-Dixon, P < 0.001). A significant improvement of image sharpness, overall image quality, diagnostic confidence, and pancreatic lesion conspicuity was observed in the images recorded using VIBE-DixonDL (P < 0.001). Furthermore, a significant reduction of image noise and motion artifacts was noted in the images recorded using the VIBE-DixonDL technique (P < 0.001). In addition, for all readers, there was no evidence of a difference in lesion size measurement between VIBE-Dixon and VIBE-DixonDL. Interreader agreement between VIBE-Dixon and VIBE-DixonDL regarding lesion size was excellent (intraclass correlation coefficient, >90). Finally, a statistically significant increase of pancreatic SNR in VIBE-DIXONDL was observed in both the precontrast (P = 0.025) and postcontrast images (P < 0.001). Also, an increase of splenic SNR in VIBE-DIXONDL was observed in both the precontrast and postcontrast images, but only reaching statistical significance in the postcontrast images (P = 0.34 and P = 0.003, respectively). Similarly, an increase of pancreas CNR in VIBE-DIXONDL was observed in both the precontrast and postcontrast images, but only reaching statistical significance in the postcontrast images (P = 0.557 and P = 0.026, respectively). CONCLUSIONS The prospectively accelerated, DL-enhanced VIBE with Dixon fat suppression was clinically feasible. It enabled a 52% reduction in breath-hold time and provided superior image quality, diagnostic confidence, and pancreatic lesion conspicuity. This technique might be especially useful for patients with limited breath-hold capacity.
Collapse
Affiliation(s)
- Marianna Chaika
- From the Department of Diagnostic and Interventional Radiology, Eberhard Karls University, Tübingen University Hospital, Tübingen, Germany (M.C., J.M.B., S.U., J.H., S.G., A.B., S.W., K.N., S.A., H.A.); MR Application Predevelopment, Siemens Healthineers AG, Forchheim, Germany (M.D.N.); and Cluster of Excellence iFIT (EXC 2180) "Image Guided and Functionally Instructed Tumor, Therapies," University of Tübingen, Tübingen, Germany (K.N.)
| | | | | | | | | | | | | | | | | | | | | |
Collapse
|
36
|
Peng W, Wan L, Tong X, Yang F, Zhao R, Chen S, Wang S, Li Y, Hu M, Li M, Li L, Zhang H. Prospective and multi-reader evaluation of deep learning reconstruction-based accelerated rectal MRI: image quality, diagnostic performance, and reading time. Eur Radiol 2024:10.1007/s00330-024-10882-6. [PMID: 39017934 DOI: 10.1007/s00330-024-10882-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2024] [Revised: 04/08/2024] [Accepted: 05/02/2024] [Indexed: 07/18/2024]
Abstract
OBJECTIVES To evaluate deep learning reconstruction (DLR)-based accelerated rectal magnetic resonance imaging (MRI) compared with standard MRI. MATERIALS AND METHODS Patients with biopsy-confirmed rectal adenocarcinoma between November/2022 and May/2023 in a single centre were prospectively enrolled for an intra-individual comparison between standard fast spin-echo (FSEstandard) and DLR-based FSE (FSEDL) sequences. Quantitative and qualitative image quality metrics of the pre-therapeutic MRIs were evaluated in all patients; diagnostic performance and evaluating time for T-staging, N-staging, extramural vascular invasion (EMVI), and mesorectal fascia (MRF) status was further analysed in patients undergoing curative surgery, with histopathologic results as the diagnostic gold standard. RESULTS A total of 117 patients were enrolled, with 60 patients undergoing curative surgery. FSEDL reduced the acquisition time by 65% than FSEstandard. FSEDL exhibited higher signal-to-noise ratios, contrast-to-noise ratio, and subjective scores (noise, tumour margin clarity, visualisation of bowel wall layering and MRF, overall image quality, and diagnostic confidence) than FSEstandard (p < 0.001). Reduced artefacts were observed in FSEDL for patients without spasmolytics (p < 0.05). FSEDL provided higher T-staging accuracy by junior readers than FSEstandard (reader 1, 58.33% vs 70.00%, p = 0.016; reader 3, 60.00% vs 76.67%, p = 0.021), with similar N-staging, EMVI, and MRF performance. No significant difference was observed for senior readers. FSEDL exhibited shorter diagnostic time in all readers' T-staging and overall evaluation, and junior readers' EMVI and MRF (p < 0.05). CONCLUSION FSEDL provided improved image quality, reading time, and junior radiologists' T-staging accuracy than FSEstandard, while reducing the acquisition time by 65%. CLINICAL RELEVANCE STATEMENT DLR is clinically applicable for rectal MRI, providing improved image quality with shorter scanning time, which may ease the examination burden. It is beneficial for diagnostic optimisation in improving junior radiologists' T-staging accuracy and reading time. KEY POINTS The rising incidence of rectal cancer has demanded enhanced efficiency and quality in imaging examinations. FSEDL demonstrated superior image quality and had a 65% reduced acquisition time. FSEDL can improve the diagnostic accuracy of T-staging and reduce the reading time for assessing rectal cancer.
Collapse
Affiliation(s)
- Wenjing Peng
- Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Lijuan Wan
- Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Xiaowan Tong
- Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Fan Yang
- Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Rui Zhao
- Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Shuang Chen
- Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | | | | | - Mancang Hu
- Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Min Li
- GE Healthcare, Beijing, China
| | - Lin Li
- Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
| | - Hongmei Zhang
- Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
| |
Collapse
|
37
|
Marth AA, von Deuster C, Sommer S, Feuerriegel GC, Goller SS, Sutter R, Nanz D. Accelerated High-Resolution Deep Learning Reconstruction Turbo Spin Echo MRI of the Knee at 7 T. Invest Radiol 2024:00004424-990000000-00230. [PMID: 38960863 DOI: 10.1097/rli.0000000000001095] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/05/2024]
Abstract
OBJECTIVES The aim of this study was to compare the image quality of 7 T turbo spin echo (TSE) knee images acquired with varying factors of parallel-imaging acceleration reconstructed with deep learning (DL)-based and conventional algorithms. MATERIALS AND METHODS This was a prospective single-center study. Twenty-three healthy volunteers underwent 7 T knee magnetic resonance imaging. Two-, 3-, and 4-fold accelerated high-resolution fat-signal-suppressing proton density (PD-fs) and T1-weighted coronal 2D TSE acquisitions with an encoded voxel volume of 0.31 × 0.31 × 1.5 mm3 were acquired. Each set of raw data was reconstructed with a DL-based and a conventional Generalized Autocalibrating Partially Parallel Acquisition (GRAPPA) algorithm. Three readers rated image contrast, sharpness, artifacts, noise, and overall quality. Friedman analysis of variance and the Wilcoxon signed rank test were used for comparison of image quality criteria. RESULTS The mean age of the participants was 32.0 ± 8.1 years (15 male, 8 female). Acquisition times at 4-fold acceleration were 4 minutes 15 seconds (PD-fs, Supplemental Video is available at http://links.lww.com/RLI/A938) and 3 minutes 9 seconds (T1, Supplemental Video available at http://links.lww.com/RLI/A939). At 4-fold acceleration, image contrast, sharpness, noise, and overall quality of images reconstructed with the DL-based algorithm were significantly better rated than the corresponding GRAPPA reconstructions (P < 0.001). Four-fold accelerated DL-reconstructed images scored significantly better than 2- to 3-fold GRAPPA-reconstructed images with regards to image contrast, sharpness, noise, and overall quality (P ≤ 0.031). Image contrast of PD-fs images at 2-fold acceleration (P = 0.087), image noise of T1-weighted images at 2-fold acceleration (P = 0.180), and image artifacts for both sequences at 2- and 3-fold acceleration (P ≥ 0.102) of GRAPPA reconstructions were not rated differently than those of 4-fold accelerated DL-reconstructed images. Furthermore, no significant difference was observed for all image quality measures among 2-fold, 3-fold, and 4-fold accelerated DL reconstructions (P ≥ 0.082). CONCLUSIONS This study explored the technical potential of DL-based image reconstruction in accelerated 2D TSE acquisitions of the knee at 7 T. DL reconstruction significantly improved a variety of image quality measures of high-resolution TSE images acquired with a 4-fold parallel-imaging acceleration compared with a conventional reconstruction algorithm.
Collapse
Affiliation(s)
- Adrian Alexander Marth
- From the Swiss Center for Musculoskeletal Imaging, Balgrist Campus AG, Zurich, Switzerland (A.A.M., C.v.D., S.S., D.N.); Department of Radiology, Balgrist University Hospital, Zurich, Switzerland (A.A.M., G.C.F., S.S.G., R.S.); Advanced Clinical Imaging Technology, Siemens Healthineers International AG, Zurich, Switzerland (C.v.D., S.S.); and Medical Faculty, University of Zurich, Zurich, Switzerland (R.S., D.N.)
| | | | | | | | | | | | | |
Collapse
|
38
|
Yan C, Liu Y, Wang C, Fan W, Zhu Y. Accelerated cardiac cine magnetic resonance imaging using deep low-rank plus sparse network: validation in patients. Quant Imaging Med Surg 2024; 14:5131-5143. [PMID: 39022294 PMCID: PMC11250298 DOI: 10.21037/qims-24-17] [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: 01/09/2024] [Accepted: 06/03/2024] [Indexed: 07/20/2024]
Abstract
Background Accurate and reproducible assessment of left ventricular (LV) volumes is important in managing various cardiac conditions. However, patients are required to hold their breath multiple times during data acquisition, which may result in discomfort and restrict cardiac motion, potentially compromising the accuracy of the detected results. Accelerated imaging techniques can help reduce the number of breath holds needed, potentially improving patient comfort and the reliability of the LV assessment. This study aimed to prospectively evaluate the feasibility and accuracy of LV assessment with a model-based low-rank plus sparse network (L+S-Net) for accelerated magnetic resonance (MR) cine imaging. Methods Fourty-one patients with different cardiac conditions were recruited in this study. Both accelerated MR cine imaging with L+S-Net and traditional electrocardiogram (ECG)-gated segmented cine were performed for each patient. Subjective image quality (IQ) score and quantitative LV volume function parameters were measured and compared between L+S-Net and traditional standards. The IQ score and LV volume measurements of cardiovascular magnetic resonance (CMR) images reconstructed by L+S-Net and standard cine were compared by paired t-test. The acquisition time of the two methods was also calculated. Results In a quantitative analysis, L+S-Net and standard cine yielded similar measurements for all parameters of LV function (ejection fraction: 35±22 for standard vs. 33±23 for L+S-Net), although L+S-Net had slightly lower IQ scores than standard cine CMR (4.2±0.5 for L+S-Net vs. 4.8±0.4 for standard cine; P<0.001). The mean acquisition time of L+S-Net and standard cine was 0.83±0.08 vs. 6.35±0.78 s per slice (P<0.001). Conclusions Assessment of LV function with L+S-Net at 3.0 T yields comparable results to the reference standard, albeit with a reduced acquisition time. This feature enhances the clinical applicability of the L+S-Net approach, helping alleviate patient discomfort and motion artifacts that may arise due to prolonged acquisition time.
Collapse
Affiliation(s)
- Chenyuan Yan
- Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Yuanyuan Liu
- Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Che Wang
- Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Weixiong Fan
- Department of Magnetic Resonance, Guangdong Provincial Key Laboratory of Precision Medicine and Clinical Translational Research of Hakka Population, Meizhou People’s Hospital, Meizhou, China
| | - Yanjie Zhu
- Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| |
Collapse
|
39
|
Baker RR, Muthurangu V, Rega M, Walsh SB, Steeden JA. Rapid 2D 23Na MRI of the calf using a denoising convolutional neural network. Magn Reson Imaging 2024; 110:184-194. [PMID: 38642779 DOI: 10.1016/j.mri.2024.04.027] [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: 03/06/2024] [Revised: 04/12/2024] [Accepted: 04/17/2024] [Indexed: 04/22/2024]
Abstract
PURPOSE 23Na MRI can be used to quantify in-vivo tissue sodium concentration (TSC), but the inherently low 23Na signal leads to long scan times and/or noisy or low-resolution images. Reconstruction algorithms such as compressed sensing (CS) have been proposed to mitigate low signal-to-noise ratio (SNR); although, these can result in unnatural images, suboptimal denoising and long processing times. Recently, machine learning has been increasingly used to denoise 1H MRI acquisitions; however, this approach typically requires large volumes of high-quality training data, which is not readily available for 23Na MRI. Here, we propose using 1H data to train a denoising convolutional neural network (CNN), which we subsequently demonstrate on prospective 23Na images of the calf. METHODS 1893 1H fat-saturated transverse slices of the knee from the open-source fastMRI dataset were used to train denoising CNNs for different levels of noise. Synthetic low SNR images were generated by adding gaussian noise to the high-quality 1H k-space data before reconstruction to create paired training data. For prospective testing, 23Na images of the calf were acquired in 10 healthy volunteers with a total of 150 averages over ten minutes, which were used as a reference throughout the study. From this data, images with fewer averages were retrospectively reconstructed using a non-uniform fast Fourier transform (NUFFT) as well as CS, with the NUFFT images subsequently denoised using the trained CNN. RESULTS CNNs were successfully applied to 23Na images reconstructed with 50, 40 and 30 averages. Muscle and skin apparent TSC quantification from CNN-denoised images were equivalent to those from CS images, with <0.9 mM bias compared to reference values. Estimated SNR was significantly higher in CNN-denoised images compared to NUFFT, CS and reference images. Quantitative edge sharpness was equivalent for all images. For subjective image quality ranking, CNN-denoised images ranked equally best with reference images and significantly better than NUFFT and CS images. CONCLUSION Denoising CNNs trained on 1H data can be successfully applied to 23Na images of the calf; thus, allowing scan time to be reduced from ten minutes to two minutes with little impact on image quality or apparent TSC quantification accuracy.
Collapse
Affiliation(s)
- Rebecca R Baker
- UCL Centre for Medical Imaging, University College London, London, UK; UCL Centre for Translational Cardiovascular Imaging, University College London, London, UK.
| | - Vivek Muthurangu
- UCL Centre for Translational Cardiovascular Imaging, University College London, London, UK.
| | - Marilena Rega
- Institute of Nuclear Medicine, University College Hospital, London, UK.
| | - Stephen B Walsh
- Department of Renal Medicine, University College London, London, UK.
| | - Jennifer A Steeden
- UCL Centre for Translational Cardiovascular Imaging, University College London, London, UK.
| |
Collapse
|
40
|
Herman JD, Roca RE, O’Neill AG, Wong ML, Goud Lingala S, Pineda AR. Task-based assessment for neural networks: evaluating undersampled MRI reconstructions based on human observer signal detection. J Med Imaging (Bellingham) 2024; 11:045503. [PMID: 39144582 PMCID: PMC11321363 DOI: 10.1117/1.jmi.11.4.045503] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2023] [Revised: 06/17/2024] [Accepted: 07/22/2024] [Indexed: 08/16/2024] Open
Abstract
Purpose Recent research explores using neural networks to reconstruct undersampled magnetic resonance imaging. Because of the complexity of the artifacts in the reconstructed images, there is a need to develop task-based approaches to image quality. We compared conventional global quantitative metrics to evaluate image quality in undersampled images generated by a neural network with human observer performance in a detection task. The purpose is to study which acceleration (2×, 3×, 4×, 5×) would be chosen with the conventional metrics and compare it to the acceleration chosen by human observer performance. Approach We used common global metrics for evaluating image quality: the normalized root mean squared error (NRMSE) and structural similarity (SSIM). These metrics are compared with a measure of image quality that incorporates a subtle signal for a specific task to allow for image quality assessment that locally evaluates the effect of undersampling on a signal. We used a U-Net to reconstruct under-sampled images with 2×, 3×, 4×, and 5× one-dimensional undersampling rates. Cross-validation was performed for a 500- and a 4000-image training set with both SSIM and MSE losses. A two-alternative forced choice (2-AFC) observer study was carried out for detecting a subtle signal (small blurred disk) from images with the 4000-image training set. Results We found that for both loss functions, the human observer performance on the 2-AFC studies led to a choice of a 2× undersampling, but the SSIM and NRMSE led to a choice of a 3× undersampling. Conclusions For this detection task using a subtle small signal at the edge of detectability, SSIM and NRMSE led to an overestimate of the achievable undersampling using a U-Net before a steep loss of image quality between 2×, 3×, 4×, 5× undersampling rates when compared to the performance of human observers in the detection task.
Collapse
Affiliation(s)
- Joshua D. Herman
- Manhattan College, Department of Mathematics, The Bronx, New York, United States
| | - Rachel E. Roca
- Manhattan College, Department of Mathematics, The Bronx, New York, United States
| | - Alexandra G. O’Neill
- Manhattan College, Department of Mathematics, The Bronx, New York, United States
| | - Marcus L. Wong
- Manhattan College, Department of Mathematics, The Bronx, New York, United States
| | - Sajan Goud Lingala
- University of Iowa, Roy J. Carver Department of Biomedical Engineering, Iowa City, Iowa, United States
| | - Angel R. Pineda
- Manhattan College, Department of Mathematics, The Bronx, New York, United States
| |
Collapse
|
41
|
Brendel JM, Jacoby J, Dehdab R, Ursprung S, Fritz V, Werner S, Herrmann J, Brendlin AS, Gassenmaier S, Schick F, Nickel D, Nikolaou K, Afat S, Almansour H. Prospective Deployment of Deep Learning Reconstruction Facilitates Highly Accelerated Upper Abdominal MRI. Acad Radiol 2024:S1076-6332(24)00356-8. [PMID: 38955591 DOI: 10.1016/j.acra.2024.05.044] [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: 05/13/2024] [Revised: 05/24/2024] [Accepted: 05/26/2024] [Indexed: 07/04/2024]
Abstract
RATIONALE AND OBJECTIVES To compare a conventional T1 volumetric interpolated breath-hold examination (VIBE) with SPectral Attenuated Inversion Recovery (SPAIR) fat saturation and a deep learning (DL)-reconstructed accelerated VIBE sequence with SPAIR fat saturation achieving a 50 % reduction in breath-hold duration (hereafter, VIBE-SPAIRDL) in terms of image quality and diagnostic confidence. MATERIALS AND METHODS This prospective study enrolled consecutive patients referred for upper abdominal MRI from November 2023 to December 2023 at a single tertiary center. Patients underwent upper abdominal MRI with acquisition of non-contrast and gadobutrol-enhanced conventional VIBE-SPAIR (fourfold acceleration, acquisition time 16 s) and VIBE-SPAIRDL (sixfold acceleration, acquisition time 8 s) on a 1.5 T scanner. Image analysis was performed by four readers, evaluating homogeneity of fat suppression, perceived signal-to-noise ratio (SNR), edge sharpness, artifact level, lesion detectability and diagnostic confidence. A statistical power analysis for patient sample size estimation was performed. Image quality parameters were compared by a repeated measures analysis of variance, and interreader agreement was assessed using Fleiss' κ. RESULTS Among 450 consecutive patients, 45 patients were evaluated (mean age, 60 years ± 15 [SD]; 27 men, 18 women). VIBE-SPAIRDL acquisition demonstrated superior SNR (P < 0.001), edge sharpness (P < 0.001), and reduced artifacts (P < 0.001) with substantial to almost perfect interreader agreement for non-contrast (κ: 0.70-0.91) and gadobutrol-enhanced MRI (κ: 0.68-0.87). No evidence of a difference was found between conventional VIBE-SPAIR and VIBE-SPAIRDL regarding homogeneity of fat suppression, lesion detectability, or diagnostic confidence (all P > 0.05). CONCLUSION Deep learning reconstruction of VIBE-SPAIR facilitated a reduction of breath-hold duration by half, while reducing artifacts and improving image quality. SUMMARY Deep learning reconstruction of prospectively accelerated T1 volumetric interpolated breath-hold examination for upper abdominal MRI enabled a 50 % reduction in breath-hold time with superior image quality. KEY RESULTS 1) In a prospective analysis of 45 patients referred for upper abdominal MRI, accelerated deep learning (DL)-reconstructed VIBE images with spectral fat saturation (SPAIR) showed better overall image quality, with better perceived signal-to-noise ratio and less artifacts (all P < 0.001), despite a 50 % reduction in acquisition time compared to conventional VIBE. 2) No evidence of a difference was found between conventional VIBE-SPAIR and accelerated VIBE-SPAIRDL regarding lesion detectability or diagnostic confidence.
Collapse
Affiliation(s)
- Jan M Brendel
- Department of Radiology, Diagnostic and Interventional Radiology, Tuebingen University Hospital, University of Tuebingen, Tuebingen, Germany
| | - Johann Jacoby
- Institute of Clinical Epidemiology and Applied Biometry, Tuebingen University Hospital, University of Tuebingen, Tuebingen, Germany
| | - Reza Dehdab
- Department of Radiology, Diagnostic and Interventional Radiology, Tuebingen University Hospital, University of Tuebingen, Tuebingen, Germany
| | - Stephan Ursprung
- Department of Radiology, Diagnostic and Interventional Radiology, Tuebingen University Hospital, University of Tuebingen, Tuebingen, Germany
| | - Victor Fritz
- Department of Radiology, Section for Experimental Radiology, Tuebingen University Hospital, University of Tuebingen, Tuebingen, Germany
| | - Sebastian Werner
- Department of Radiology, Diagnostic and Interventional Radiology, Tuebingen University Hospital, University of Tuebingen, Tuebingen, Germany
| | - Judith Herrmann
- Department of Radiology, Diagnostic and Interventional Radiology, Tuebingen University Hospital, University of Tuebingen, Tuebingen, Germany
| | - Andreas S Brendlin
- Department of Radiology, Diagnostic and Interventional Radiology, Tuebingen University Hospital, University of Tuebingen, Tuebingen, Germany
| | - Sebastian Gassenmaier
- Department of Radiology, Diagnostic and Interventional Radiology, Tuebingen University Hospital, University of Tuebingen, Tuebingen, Germany
| | - Fritz Schick
- Department of Radiology, Section for Experimental Radiology, Tuebingen University Hospital, University of Tuebingen, Tuebingen, Germany
| | - Dominik Nickel
- Department of MR Application Predevelopment, Siemens Healthineers, Forchheim, Germany
| | - Konstantin Nikolaou
- Department of Radiology, Diagnostic and Interventional Radiology, Tuebingen University Hospital, University of Tuebingen, Tuebingen, Germany; Cluster of Excellence iFIT (EXC 2180) "Image-guided and Functionally Instructed Tumor Therapies", University of Tuebingen, Tuebingen, Germany
| | - Saif Afat
- Department of Radiology, Diagnostic and Interventional Radiology, Tuebingen University Hospital, University of Tuebingen, Tuebingen, Germany
| | - Haidara Almansour
- Department of Radiology, Diagnostic and Interventional Radiology, Tuebingen University Hospital, University of Tuebingen, Tuebingen, Germany.
| |
Collapse
|
42
|
Liu X, Pang Y, Liu Y, Jin R, Sun Y, Liu Y, Xiao J. Dual-domain faster Fourier convolution based network for MR image reconstruction. Comput Biol Med 2024; 177:108603. [PMID: 38781646 DOI: 10.1016/j.compbiomed.2024.108603] [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: 01/31/2024] [Revised: 04/15/2024] [Accepted: 05/11/2024] [Indexed: 05/25/2024]
Abstract
Deep learning methods for fast MRI have shown promise in reconstructing high-quality images from undersampled multi-coil k-space data, leading to reduced scan duration. However, existing methods encounter challenges related to limited receptive fields in dual-domain (k-space and image domains) reconstruction networks, rigid data consistency operations, and suboptimal refinement structures, which collectively restrict overall reconstruction performance. This study introduces a comprehensive framework that addresses these challenges and enhances MR image reconstruction quality. Firstly, we propose Faster Inverse Fourier Convolution (FasterIFC), a frequency domain convolutional operator that significantly expands the receptive field of k-space domain reconstruction networks. Expanding the information extraction range to the entire frequency spectrum according to the spectral convolution theorem in Fourier theory enables the network to easily utilize richer redundant long-range information from adjacent, symmetrical, and diagonal locations of multi-coil k-space data. Secondly, we introduce a novel softer Data Consistency (softerDC) layer, which achieves an enhanced balance between data consistency and smoothness. This layer facilitates the implementation of diverse data consistency strategies across distinct frequency positions, addressing the inflexibility observed in current methods. Finally, we present the Dual-Domain Faster Fourier Convolution Based Network (D2F2), which features a centrosymmetric dual-domain parallel structure based on FasterIFC. This architecture optimally leverages dual-domain data characteristics while substantially expanding the receptive field in both domains. Coupled with the softerDC layer, D2F2 demonstrates superior performance on the NYU fastMRI dataset at multiple acceleration factors, surpassing state-of-the-art methods in both quantitative and qualitative evaluations.
Collapse
Affiliation(s)
- Xiaohan Liu
- TJK-BIIT Lab, School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China; Tiandatz Technology Co. Ltd., Tianjin, 300072, China.
| | - Yanwei Pang
- TJK-BIIT Lab, School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China.
| | - Yiming Liu
- TJK-BIIT Lab, School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China.
| | - Ruiqi Jin
- TJK-BIIT Lab, School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China.
| | - Yong Sun
- TJK-BIIT Lab, School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China.
| | - Yu Liu
- TJK-BIIT Lab, School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China.
| | - Jing Xiao
- TJK-BIIT Lab, School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China; Department of Economic Management, Hebei Chemical and Pharmaceutical College, Shijiazhuang, Hebei, 050026, China.
| |
Collapse
|
43
|
Heckel R, Jacob M, Chaudhari A, Perlman O, Shimron E. Deep learning for accelerated and robust MRI reconstruction. MAGMA (NEW YORK, N.Y.) 2024; 37:335-368. [PMID: 39042206 DOI: 10.1007/s10334-024-01173-8] [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: 04/03/2024] [Revised: 05/24/2024] [Accepted: 05/28/2024] [Indexed: 07/24/2024]
Abstract
Deep learning (DL) has recently emerged as a pivotal technology for enhancing magnetic resonance imaging (MRI), a critical tool in diagnostic radiology. This review paper provides a comprehensive overview of recent advances in DL for MRI reconstruction, and focuses on various DL approaches and architectures designed to improve image quality, accelerate scans, and address data-related challenges. It explores end-to-end neural networks, pre-trained and generative models, and self-supervised methods, and highlights their contributions to overcoming traditional MRI limitations. It also discusses the role of DL in optimizing acquisition protocols, enhancing robustness against distribution shifts, and tackling biases. Drawing on the extensive literature and practical insights, it outlines current successes, limitations, and future directions for leveraging DL in MRI reconstruction, while emphasizing the potential of DL to significantly impact clinical imaging practices.
Collapse
Affiliation(s)
- Reinhard Heckel
- Department of computer engineering, Technical University of Munich, Munich, Germany
| | - Mathews Jacob
- Department of Electrical and Computer Engineering, University of Iowa, Iowa, 52242, IA, USA
| | - Akshay Chaudhari
- Department of Radiology, Stanford University, Stanford, 94305, CA, USA
- Department of Biomedical Data Science, Stanford University, Stanford, 94305, CA, USA
| | - Or Perlman
- Department of Biomedical Engineering, Tel Aviv University, Tel Aviv, Israel
- Sagol School of Neuroscience, Tel Aviv University, Tel Aviv, Israel
| | - Efrat Shimron
- Department of Electrical and Computer Engineering, Technion-Israel Institute of Technology, Haifa, 3200004, Israel.
- Department of Biomedical Engineering, Technion-Israel Institute of Technology, Haifa, 3200004, Israel.
| |
Collapse
|
44
|
Zhang C, Piccini D, Demirel OB, Bonanno G, Roy CW, Yaman B, Moeller S, Shenoy C, Stuber M, Akçakaya M. Large-scale 3D non-Cartesian coronary MRI reconstruction using distributed memory-efficient physics-guided deep learning with limited training data. MAGMA (NEW YORK, N.Y.) 2024; 37:429-438. [PMID: 38743377 DOI: 10.1007/s10334-024-01157-8] [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: 10/10/2023] [Revised: 02/19/2024] [Accepted: 03/13/2024] [Indexed: 05/16/2024]
Abstract
OBJECT To enable high-quality physics-guided deep learning (PG-DL) reconstruction of large-scale 3D non-Cartesian coronary MRI by overcoming challenges of hardware limitations and limited training data availability. MATERIALS AND METHODS While PG-DL has emerged as a powerful image reconstruction method, its application to large-scale 3D non-Cartesian MRI is hindered by hardware limitations and limited availability of training data. We combine several recent advances in deep learning and MRI reconstruction to tackle the former challenge, and we further propose a 2.5D reconstruction using 2D convolutional neural networks, which treat 3D volumes as batches of 2D images to train the network with a limited amount of training data. Both 3D and 2.5D variants of the PG-DL networks were compared to conventional methods for high-resolution 3D kooshball coronary MRI. RESULTS Proposed PG-DL reconstructions of 3D non-Cartesian coronary MRI with 3D and 2.5D processing outperformed all conventional methods both quantitatively and qualitatively in terms of image assessment by an experienced cardiologist. The 2.5D variant further improved vessel sharpness compared to 3D processing, and scored higher in terms of qualitative image quality. DISCUSSION PG-DL reconstruction of large-scale 3D non-Cartesian MRI without compromising image size or network complexity is achieved, and the proposed 2.5D processing enables high-quality reconstruction with limited training data.
Collapse
Affiliation(s)
- Chi Zhang
- Electrical and Computer Engineering, University of Minnesota, 200 Union Street S.E., Minneapolis, MN, 55455, USA
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, USA
| | - Davide Piccini
- Department of Diagnostic and Interventional Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
- Advanced Clinical Imaging Technology, Siemens Healthineers International, Lausanne, Switzerland
| | - Omer Burak Demirel
- Electrical and Computer Engineering, University of Minnesota, 200 Union Street S.E., Minneapolis, MN, 55455, USA
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, USA
| | - Gabriele Bonanno
- Advanced Clinical Imaging Technology, Siemens Healthineers International, Lausanne, Switzerland
| | - Christopher W Roy
- Department of Diagnostic and Interventional Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
| | - Burhaneddin Yaman
- Electrical and Computer Engineering, University of Minnesota, 200 Union Street S.E., Minneapolis, MN, 55455, USA
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, USA
| | - Steen Moeller
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, USA
| | - Chetan Shenoy
- Department of Medicine (Cardiology), University of Minnesota, Minneapolis, MN, 55455, USA
| | - Matthias Stuber
- Department of Diagnostic and Interventional Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
- Center for Biomedical Imaging, Lausanne, Switzerland
| | - Mehmet Akçakaya
- Electrical and Computer Engineering, University of Minnesota, 200 Union Street S.E., Minneapolis, MN, 55455, USA.
- Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, USA.
| |
Collapse
|
45
|
Yoo RE, Choi SH. Deep Learning-based Image Enhancement Techniques for Fast MRI in Neuroimaging. Magn Reson Med Sci 2024; 23:341-351. [PMID: 38684425 PMCID: PMC11234952 DOI: 10.2463/mrms.rev.2023-0153] [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] [Indexed: 05/02/2024] Open
Abstract
Despite its superior soft tissue contrast and non-invasive nature, MRI requires long scan times due to its intrinsic signal acquisition principles, a main drawback which technological advancements in MRI have been focused on. In particular, scan time reduction is a natural requirement in neuroimaging due to detailed structures requiring high resolution imaging and often volumetric (3D) acquisitions, and numerous studies have recently attempted to harness deep learning (DL) technology in enabling scan time reduction and image quality improvement. Various DL-based image reconstruction products allow for additional scan time reduction on top of existing accelerated acquisition methods without compromising the image quality.
Collapse
Affiliation(s)
- Roh-Eul Yoo
- Department of Radiology, National Cancer Center, Goyang-si, Republic of Korea
- Department of Radiology, Seoul National University College of Medicine, Seoul, Republic of Korea
| | - Seung Hong Choi
- Department of Radiology, National Cancer Center, Goyang-si, Republic of Korea
- Department of Radiology, Seoul National University College of Medicine, Seoul, Republic of Korea
- Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea
- Center for Nanoparticle Research, Institute for Basic Science (IBS), Seoul, Republic of Korea
| |
Collapse
|
46
|
Zhou Z, Hu P, Qi H. Stop moving: MR motion correction as an opportunity for artificial intelligence. MAGMA (NEW YORK, N.Y.) 2024; 37:397-409. [PMID: 38386151 DOI: 10.1007/s10334-023-01144-5] [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: 09/28/2023] [Revised: 12/09/2023] [Accepted: 12/19/2023] [Indexed: 02/23/2024]
Abstract
Subject motion is a long-standing problem of magnetic resonance imaging (MRI), which can seriously deteriorate the image quality. Various prospective and retrospective methods have been proposed for MRI motion correction, among which deep learning approaches have achieved state-of-the-art motion correction performance. This survey paper aims to provide a comprehensive review of deep learning-based MRI motion correction methods. Neural networks used for motion artifacts reduction and motion estimation in the image domain or frequency domain are detailed. Furthermore, besides motion-corrected MRI reconstruction, how estimated motion is applied in other downstream tasks is briefly introduced, aiming to strengthen the interaction between different research areas. Finally, we identify current limitations and point out future directions of deep learning-based MRI motion correction.
Collapse
Affiliation(s)
- Zijian Zhou
- School of Biomedical Engineering, ShanghaiTech University, 4th Floor, BME Building, 393 Middle Huaxia Road, Pudong District, Shanghai, 201210, China
- Shanghai Clinical Research and Trial Center, ShanghaiTech University, Shanghai, China
| | - Peng Hu
- School of Biomedical Engineering, ShanghaiTech University, 4th Floor, BME Building, 393 Middle Huaxia Road, Pudong District, Shanghai, 201210, China.
- Shanghai Clinical Research and Trial Center, ShanghaiTech University, Shanghai, China.
| | - Haikun Qi
- School of Biomedical Engineering, ShanghaiTech University, 4th Floor, BME Building, 393 Middle Huaxia Road, Pudong District, Shanghai, 201210, China.
- Shanghai Clinical Research and Trial Center, ShanghaiTech University, Shanghai, China.
| |
Collapse
|
47
|
Bian W, Jang A, Liu F. Improving quantitative MRI using self-supervised deep learning with model reinforcement: Demonstration for rapid T1 mapping. Magn Reson Med 2024; 92:98-111. [PMID: 38342980 PMCID: PMC11055673 DOI: 10.1002/mrm.30045] [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: 08/04/2023] [Revised: 12/21/2023] [Accepted: 01/23/2024] [Indexed: 02/13/2024]
Abstract
PURPOSE This paper proposes a novel self-supervised learning framework that uses model reinforcement, REference-free LAtent map eXtraction with MOdel REinforcement (RELAX-MORE), for accelerated quantitative MRI (qMRI) reconstruction. The proposed method uses an optimization algorithm to unroll an iterative model-based qMRI reconstruction into a deep learning framework, enabling accelerated MR parameter maps that are highly accurate and robust. METHODS Unlike conventional deep learning methods which require large amounts of training data, RELAX-MORE is a subject-specific method that can be trained on single-subject data through self-supervised learning, making it accessible and practically applicable to many qMRI studies. Using quantitativeT 1 $$ {\mathrm{T}}_1 $$ mapping as an example, the proposed method was applied to the brain, knee and phantom data. RESULTS The proposed method generates high-quality MR parameter maps that correct for image artifacts, removes noise, and recovers image features in regions of imperfect image conditions. Compared with other state-of-the-art conventional and deep learning methods, RELAX-MORE significantly improves efficiency, accuracy, robustness, and generalizability for rapid MR parameter mapping. CONCLUSION This work demonstrates the feasibility of a new self-supervised learning method for rapid MR parameter mapping, that is readily adaptable to the clinical translation of qMRI.
Collapse
Affiliation(s)
- Wanyu Bian
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, Massachusetts, USA
- Harvard Medical School, Boston, Massachusetts, USA
| | - Albert Jang
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, Massachusetts, USA
- Harvard Medical School, Boston, Massachusetts, USA
| | - Fang Liu
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, Massachusetts, USA
- Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|
48
|
Guan Y, Li Y, Ke Z, Peng X, Liu R, Li Y, Du YP, Liang ZP. Learning-Assisted Fast Determination of Regularization Parameter in Constrained Image Reconstruction. IEEE Trans Biomed Eng 2024; 71:2253-2264. [PMID: 38376982 DOI: 10.1109/tbme.2024.3367762] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/22/2024]
Abstract
OBJECTIVE To leverage machine learning (ML) for fast selection of optimal regularization parameter in constrained image reconstruction. METHODS Constrained image reconstruction is often formulated as a regularization problem and selecting a good regularization parameter value is an essential step. We solved this problem using an ML-based approach by leveraging the finding that for a specific constrained reconstruction problem defined for a fixed class of image functions, the optimal regularization parameter value is weakly subject-dependent and the dependence can be captured using few experimental data. The proposed method has four key steps: a) solution of a given constrained reconstruction problem for a few (say, 3) pre-selected regularization parameter values, b) extraction of multiple approximated quality metrics from the initial reconstructions, c) predicting the true quality metrics values from the approximated values using pre-trained neural networks, and d) determination of the optimal regularization parameter by fusing the predicted quality metrics. RESULTS The effectiveness of the proposed method was demonstrated in two constrained reconstruction problems. Compared with L-curve-based method, the proposed method determined the regularization parameters much faster and produced substantially improved reconstructions. Our method also outperformed state-of-the-art learning-based methods when trained with limited experimental data. CONCLUSION This paper demonstrates the feasibility and improved reconstruction quality by using machine learning to determine the regularization parameter in constrained reconstruction. SIGNIFICANCE The proposed method substantially reduces the computational burden of the traditional methods (e.g., L-curve) or relaxes the requirement of large training data by modern learning-based methods, thus enhancing the practical utility of constrained reconstruction.
Collapse
|
49
|
Wang C, Lyu J, Wang S, Qin C, Guo K, Zhang X, Yu X, Li Y, Wang F, Jin J, Shi Z, Xu Z, Tian Y, Hua S, Chen Z, Liu M, Sun M, Kuang X, Wang K, Wang H, Li H, Chu Y, Yang G, Bai W, Zhuang X, Wang H, Qin J, Qu X. CMRxRecon: A publicly available k-space dataset and benchmark to advance deep learning for cardiac MRI. Sci Data 2024; 11:687. [PMID: 38918497 PMCID: PMC11199635 DOI: 10.1038/s41597-024-03525-4] [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: 07/10/2023] [Accepted: 06/14/2024] [Indexed: 06/27/2024] Open
Abstract
Cardiac magnetic resonance imaging (CMR) has emerged as a valuable diagnostic tool for cardiac diseases. However, a significant drawback of CMR is its slow imaging speed, resulting in low patient throughput and compromised clinical diagnostic quality. The limited temporal resolution also causes patient discomfort and introduces artifacts in the images, further diminishing their overall quality and diagnostic value. There has been growing interest in deep learning-based CMR imaging algorithms that can reconstruct high-quality images from highly under-sampled k-space data. However, the development of deep learning methods requires large training datasets, which have so far not been made publicly available for CMR. To address this gap, we released a dataset that includes multi-contrast, multi-view, multi-slice and multi-coil CMR imaging data from 300 subjects. Imaging studies include cardiac cine and mapping sequences. The 'CMRxRecon' dataset contains raw k-space data and auto-calibration lines. Our aim is to facilitate the advancement of state-of-the-art CMR image reconstruction by introducing standardized evaluation criteria and making the dataset freely accessible to the research community.
Collapse
Affiliation(s)
- Chengyan Wang
- Human Phenome Institute, Fudan University, Shanghai, China
| | - Jun Lyu
- Department of Psychiatry, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Shuo Wang
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, Shanghai, China
| | - Chen Qin
- Department of Electrical and Electronic Engineering & I-X, Imperial College London, London, UK
| | - Kunyuan Guo
- Department of Electronic Science, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, National Institute for Data Science in Health and Medicine, Institute of Artificial Intelligence, Xiamen University, Xiamen, China
| | - Xinyu Zhang
- Human Phenome Institute, Fudan University, Shanghai, China
| | - Xiaotong Yu
- Department of Electronic Science, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, National Institute for Data Science in Health and Medicine, Institute of Artificial Intelligence, Xiamen University, Xiamen, China
| | - Yan Li
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Fanwen Wang
- Department of Bioengineering/Imperial-X, Imperial College London, London, UK
| | - Jianhua Jin
- School of Data Science, Fudan University, Shanghai, China
| | - Zhang Shi
- Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, China
| | - Ziqiang Xu
- School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China
| | - Yapeng Tian
- Department of Computer Science, The University of Texas at Dallas, Richardson, USA
| | - Sha Hua
- Department of Cardiovascular Medicine, Ruijin Hospital Lu Wan Branch, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Zhensen Chen
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, 200433, China
| | - Meng Liu
- Human Phenome Institute, Fudan University, Shanghai, China
| | - Mengting Sun
- Human Phenome Institute, Fudan University, Shanghai, China
| | - Xutong Kuang
- Human Phenome Institute, Fudan University, Shanghai, China
| | - Kang Wang
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, Shanghai, China
| | - Haoran Wang
- Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, Shanghai, China
| | - Hao Li
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, 200433, China
| | | | - Guang Yang
- Department of Bioengineering/Imperial-X, Imperial College London, London, UK
| | - Wenjia Bai
- Department of Brain Sciences, Imperial College London, London, UK
- Department of Computing, Imperial College London, London, UK
| | - Xiahai Zhuang
- School of Data Science, Fudan University, Shanghai, China
| | - He Wang
- Human Phenome Institute, Fudan University, Shanghai, China
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, 200433, China
| | - Jing Qin
- School of Nursing, The Hong Kong Polytechnic University, Hong Kong, China.
| | - Xiaobo Qu
- Department of Electronic Science, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, National Institute for Data Science in Health and Medicine, Institute of Artificial Intelligence, Xiamen University, Xiamen, China.
| |
Collapse
|
50
|
Vashistha R, Almuqbel MM, Palmer NJ, Keenan RJ, Gilbert K, Wells S, Lynch A, Li A, Kingston-Smith S, Melzer TR, Koerzdoerfer G, O'Brien K. Evaluation of deep-learning TSE images in clinical musculoskeletal imaging. J Med Imaging Radiat Oncol 2024. [PMID: 38837669 DOI: 10.1111/1754-9485.13714] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2023] [Accepted: 05/15/2024] [Indexed: 06/07/2024]
Abstract
In this study, we compared the fat-saturated (FS) and non-FS turbo spin echo (TSE) magnetic resonance imaging knee sequences reconstructed conventionally (conventional-TSE) against a deep learning-based reconstruction of accelerated TSE (DL-TSE) scans. A total of 232 conventional-TSE and DL-TSE image pairs were acquired for comparison. For each consenting patient, one of the clinically acquired conventional-TSE proton density-weighted sequences in the sagittal or coronal planes (FS and non-FS), or in the axial plane (non-FS), was repeated using a research DL-TSE sequence. The DL-TSE reconstruction resulted in an image resolution that increased by at least 45% and scan times that were up to 52% faster compared to the conventional TSE. All images were acquired on a MAGNETOM Vida 3T scanner (Siemens Healthineers AG, Erlangen, Germany). The reporting radiologists, blinded to the acquisition time, were requested to qualitatively compare the DL-TSE against the conventional-TSE reconstructions. Despite having a faster acquisition time, the DL-TSE was rated to depict smaller structures better for 139/232 (60%) cases, equivalent for 72/232 (31%) cases and worse for 21/232 (9%) cases compared to the conventional-TSE. Overall, the radiologists preferred the DL-TSE reconstruction in 124/232 (53%) cases and stated no preference, implying equivalence, for 65/232 (28%) cases. DL-TSE reconstructions enabled faster acquisition times while enhancing spatial resolution and preserving the image contrast. From these results, the DL-TSE provided added or comparable clinical value and utility in less time. DL-TSE offers the opportunity to further reduce the overall examination time and improve patient comfort with no loss in diagnostic accuracy.
Collapse
Affiliation(s)
- Rajat Vashistha
- ARC Centre for Innovation in Biomedical Imaging Technology, The University of Queensland, Brisbane, Queensland, Australia
- Siemens Healthcare Pty Ltd, Brisbane, Queensland, Australia
| | - Mustafa M Almuqbel
- Pacific Radiology Group, Christchurch, New Zealand
- New Zealand Brain Research Institute, Christchurch, New Zealand
- Department of Medicine, University of Otago, Christchurch, New Zealand
- South Australia Health and Medical Research Institute, Adelaide, South Australia, Australia
| | | | - Ross J Keenan
- Pacific Radiology Group, Christchurch, New Zealand
- Department of Radiology, Christchurch Hospital, Christchurch, New Zealand
| | | | - Scott Wells
- Pacific Radiology Group, Christchurch, New Zealand
| | - Andrew Lynch
- Pacific Radiology Group, Christchurch, New Zealand
| | - Andrew Li
- Pacific Radiology Group, Christchurch, New Zealand
| | | | - Tracy R Melzer
- New Zealand Brain Research Institute, Christchurch, New Zealand
- Department of Medicine, University of Otago, Christchurch, New Zealand
- School of Psychology, Speech and Hearing, University of Canterbury, Christchurch, New Zealand
| | | | - Kieran O'Brien
- ARC Centre for Innovation in Biomedical Imaging Technology, The University of Queensland, Brisbane, Queensland, Australia
- Siemens Healthcare Pty Ltd, Brisbane, Queensland, Australia
| |
Collapse
|