1
|
Miller Z, Johnson KM. Motion compensated self supervised deep learning for highly accelerated 3D ultrashort Echo time pulmonary MRI. Magn Reson Med 2023; 89:2361-2375. [PMID: 36744745 PMCID: PMC10590257 DOI: 10.1002/mrm.29586] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2022] [Revised: 12/09/2022] [Accepted: 12/29/2022] [Indexed: 02/07/2023]
Abstract
PURPOSE To investigate motion compensated, self-supervised, model based deep learning (MBDL) as a method to reconstruct free breathing, 3D pulmonary UTE acquisitions. THEORY AND METHODS A self-supervised eXtra dimension MBDL architecture (XD-MBDL) was developed that combined respiratory states to reconstruct a single high-quality 3D image. Non-rigid motion fields were incorporated into this architecture by estimating motion fields from a lower resolution motion resolved (XD-GRASP) reconstruction. Motion compensated XD-MBDL was evaluated on lung UTE datasets with and without contrast and compared to constrained reconstructions and variants of self-supervised MBDL that do not account for dynamic respiratory states or leverage motion correction. RESULTS Images reconstructed using XD-MBDL demonstrate improved image quality as measured by apparent SNR (aSNR), contrast to noise ratio (CNR), and visual assessment relative to self-supervised MBDL approaches that do not account for dynamic respiratory states, XD-GRASP and a recently proposed motion compensated iterative reconstruction strategy (iMoCo). Additionally, XD-MBDL reduced reconstruction time relative to both XD-GRASP and iMoCo. CONCLUSION A method was developed to allow self-supervised MBDL to combine multiple respiratory states to reconstruct a single image. This method was combined with graphics processing unit (GPU)-based image registration to further improve reconstruction quality. This approach showed promising results reconstructing a user-selected respiratory phase from free breathing 3D pulmonary UTE acquisitions.
Collapse
Affiliation(s)
- Zachary Miller
- Department of Biomedical Engineering, University of Wisconsin, Madison, Wisconsin, USA
| | - Kevin M. Johnson
- Department of Medical Physics, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA
- Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA
| |
Collapse
|
2
|
Kossen T, Madai VI, Mutke MA, Hennemuth A, Hildebrand K, Behland J, Aslan C, Hilbert A, Sobesky J, Bendszus M, Frey D. Image-to-image generative adversarial networks for synthesizing perfusion parameter maps from DSC-MR images in cerebrovascular disease. Front Neurol 2023; 13:1051397. [PMID: 36703627 PMCID: PMC9871486 DOI: 10.3389/fneur.2022.1051397] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2022] [Accepted: 12/15/2022] [Indexed: 01/11/2023] Open
Abstract
Stroke is a major cause of death or disability. As imaging-based patient stratification improves acute stroke therapy, dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI) is of major interest in image brain perfusion. However, expert-level perfusion maps require a manual or semi-manual post-processing by a medical expert making the procedure time-consuming and less-standardized. Modern machine learning methods such as generative adversarial networks (GANs) have the potential to automate the perfusion map generation on an expert level without manual validation. We propose a modified pix2pix GAN with a temporal component (temp-pix2pix-GAN) that generates perfusion maps in an end-to-end fashion. We train our model on perfusion maps infused with expert knowledge to encode it into the GANs. The performance was trained and evaluated using the structural similarity index measure (SSIM) on two datasets including patients with acute stroke and the steno-occlusive disease. Our temp-pix2pix architecture showed high performance on the acute stroke dataset for all perfusion maps (mean SSIM 0.92-0.99) and good performance on data including patients with the steno-occlusive disease (mean SSIM 0.84-0.99). While clinical validation is still necessary for future studies, our results mark an important step toward automated expert-level perfusion maps and thus fast patient stratification.
Collapse
Affiliation(s)
- Tabea Kossen
- Charité Lab for Artificial Intelligence in Medicine (CLAIM), Charité-Universitätsmedizin Berlin, Berlin, Germany,Department of Computer Engineering and Microelectronics, Computer Vision and Remote Sensing, Technical University Berlin, Berlin, Germany,*Correspondence: Tabea Kossen ✉
| | - Vince I. Madai
- Charité Lab for Artificial Intelligence in Medicine (CLAIM), Charité-Universitätsmedizin Berlin, Berlin, Germany,QUEST Center for Responsible Research, Berlin Institute of Health (BIH), Charité-Universitätsmedizin Berlin, Berlin, Germany,Faculty of Computing, Engineering and the Built Environment, School of Computing and Digital Technology, Birmingham City University, Birmingham, United Kingdom
| | - Matthias A. Mutke
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
| | - Anja Hennemuth
- Department of Computer Engineering and Microelectronics, Computer Vision and Remote Sensing, Technical University Berlin, Berlin, Germany,Institute for Imaging Science and Computational Modelling in Cardiovascular Medicine, Charité-Universitätsmedizin Berlin, Berlin, Germany,Fraunhofer MEVIS, Bremen, Germany
| | - Kristian Hildebrand
- Department of Computer Science and Media, Berlin University of Applied Sciences and Technology, Berlin, Germany
| | - Jonas Behland
- Charité Lab for Artificial Intelligence in Medicine (CLAIM), Charité-Universitätsmedizin Berlin, Berlin, Germany
| | - Cagdas Aslan
- Department of Computer Science and Media, Berlin University of Applied Sciences and Technology, Berlin, Germany
| | - Adam Hilbert
- Charité Lab for Artificial Intelligence in Medicine (CLAIM), Charité-Universitätsmedizin Berlin, Berlin, Germany
| | - Jan Sobesky
- Center for Stroke Research Berlin, Charité-Universitätsmedizin Berlin, Berlin, Germany,Johanna-Etienne-Hospital, Neuss, Germany
| | - Martin Bendszus
- Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany
| | - Dietmar Frey
- Charité Lab for Artificial Intelligence in Medicine (CLAIM), Charité-Universitätsmedizin Berlin, Berlin, Germany
| |
Collapse
|
3
|
Gao C, Ghodrati V, Shih SF, Wu HH, Liu Y, Nickel MD, Vahle T, Dale B, Sai V, Felker E, Surawech C, Miao Q, Finn JP, Zhong X, Hu P. Undersampling artifact reduction for free-breathing 3D stack-of-radial MRI based on a deep adversarial learning network. Magn Reson Imaging 2023; 95:70-79. [PMID: 36270417 PMCID: PMC10163826 DOI: 10.1016/j.mri.2022.10.010] [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: 07/26/2022] [Revised: 10/06/2022] [Accepted: 10/14/2022] [Indexed: 11/05/2022]
Abstract
PURPOSE Stack-of-radial MRI allows free-breathing abdominal scans, however, it requires relatively long acquisition time. Undersampling reduces scan time but can cause streaking artifacts and degrade image quality. This study developed deep learning networks with adversarial loss and evaluated the performance of reducing streaking artifacts and preserving perceptual image sharpness. METHODS A 3D generative adversarial network (GAN) was developed for reducing streaking artifacts in stack-of-radial abdominal scans. Training and validation datasets were self-gated to 5 respiratory states to reduce motion artifacts and to effectively augment the data. The network used a combination of three loss functions to constrain the anatomy and preserve image quality: adversarial loss, mean-squared-error loss and structural similarity index loss. The performance of the network was investigated for 3-5 times undersampled data from 2 institutions. The performance of the GAN for 5 times accelerated images was compared with a 3D U-Net and evaluated using quantitative NMSE, SSIM and region of interest (ROI) measurements as well as qualitative scores of radiologists. RESULTS The 3D GAN showed similar NMSE (0.0657 vs. 0.0559, p = 0.5217) and significantly higher SSIM (0.841 vs. 0.798, p < 0.0001) compared to U-Net. ROI analysis showed GAN removed streaks in both the background air and the tissue and was not significantly different from the reference mean and variations. Radiologists' scores showed GAN had a significant improvement of 1.6 point (p = 0.004) on a 4-point scale in streaking score while no significant difference in sharpness score compared to the input. CONCLUSION 3D GAN removes streaking artifacts and preserves perceptual image details.
Collapse
Affiliation(s)
- Chang Gao
- Department of Radiological Sciences, University of California Los Angeles, Los Angeles, CA, United States; Inter-Departmental Graduate Program of Physics and Biology in Medicine, University of California Los Angeles, Los Angeles, CA, United States
| | - Vahid Ghodrati
- Department of Radiological Sciences, University of California Los Angeles, Los Angeles, CA, United States; Inter-Departmental Graduate Program of Physics and Biology in Medicine, University of California Los Angeles, Los Angeles, CA, United States
| | - Shu-Fu Shih
- Department of Radiological Sciences, University of California Los Angeles, Los Angeles, CA, United States; Department of Bioengineering, University of California Los Angeles, Los Angeles, CA, United States
| | - Holden H Wu
- Department of Radiological Sciences, University of California Los Angeles, Los Angeles, CA, United States; Inter-Departmental Graduate Program of Physics and Biology in Medicine, University of California Los Angeles, Los Angeles, CA, United States; Department of Bioengineering, University of California Los Angeles, Los Angeles, CA, United States
| | - Yongkai Liu
- Department of Radiological Sciences, University of California Los Angeles, Los Angeles, CA, United States; Inter-Departmental Graduate Program of Physics and Biology in Medicine, University of California Los Angeles, Los Angeles, CA, United States
| | | | - Thomas Vahle
- MR Application Predevelopment, Siemens Healthcare GmbH, Erlangen, Germany
| | - Brian Dale
- MR R&D Collaborations, Siemens Medical Solutions USA, Inc., Cary, NC, United States
| | - Victor Sai
- Department of Radiological Sciences, University of California Los Angeles, Los Angeles, CA, United States
| | - Ely Felker
- Department of Radiological Sciences, University of California Los Angeles, Los Angeles, CA, United States
| | - Chuthaporn Surawech
- Department of Radiological Sciences, University of California Los Angeles, Los Angeles, CA, United States; Department of Radiology, Division of Diagnostic Radiology, Faculty of Medicine, Chulalongkorn University and King Chulalongkorn Memorial Hospital, Bangkok, Thailand
| | - Qi Miao
- Department of Radiological Sciences, University of California Los Angeles, Los Angeles, CA, United States; Department of Radiology, The First Affiliated Hospital of China Medical University, Shenyang, Liaoning Province, China
| | - J Paul Finn
- Department of Radiological Sciences, University of California Los Angeles, Los Angeles, CA, United States; Inter-Departmental Graduate Program of Physics and Biology in Medicine, University of California Los Angeles, Los Angeles, CA, United States
| | - Xiaodong Zhong
- MR R&D Collaborations, Siemens Medical Solutions USA, Inc., Los Angeles, CA, United States
| | - Peng Hu
- Department of Radiological Sciences, University of California Los Angeles, Los Angeles, CA, United States; Inter-Departmental Graduate Program of Physics and Biology in Medicine, University of California Los Angeles, Los Angeles, CA, United States.
| |
Collapse
|
4
|
Bhuta S, Patel NJ, Ciricillo JA, Haddad MN, Khokher W, Mhanna M, Patel M, Burmeister C, Malas H, Kammeyer JA. Cardiac Magnetic Resonance Imaging for the Diagnosis of Infective Endocarditis in the COVID-19 Era. Curr Probl Cardiol 2022; 48:101396. [PMID: 36126764 PMCID: PMC9481470 DOI: 10.1016/j.cpcardiol.2022.101396] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2022] [Accepted: 09/07/2022] [Indexed: 10/30/2022]
Abstract
INTRODUCTION In the COVID-19 pandemic, to minimize aerosol-generating procedures, cardiac magnetic resonance imaging (CMR) was utilized at our institution as an alternative to transesophageal echocardiography (TEE) for diagnosing infective endocarditis (IE). METHODS This retrospective study evaluated the clinical utility of CMR for detecting IE among 14 patients growing typical microorganisms on blood cultures or meeting modified Duke criteria. RESULTS 7 cases were treated for IE. In 2 cases, CMR results were notable for possible leaflet vegetations and were clinically meaningful in guiding antibiotic therapy, obtaining further imaging, and/or pursuing surgical intervention. In 2 cases, vegetations were missed on CMR but detected on TEE. In 3 cases, CMR was nondiagnostic, but patients were treated empirically. There was no difference in antibiotic duration or outcomes over 1 year. CONCLUSION CMR demonstrated mixed results in diagnosing valvular vegetations and guiding clinical decision making. Further prospective controlled trials of CMR vs TEE are warranted.
Collapse
Affiliation(s)
- Sapan Bhuta
- The Ohio State University Wexner Medical Center, Columbus, OH, USA
| | - Neha J Patel
- University of Toledo College of Medicine and Life Sciences, Toledo, OH, USA
| | - Jacob A Ciricillo
- University of Toledo College of Medicine and Life Sciences, Toledo, OH, USA
| | - Michael N Haddad
- University of Toledo College of Medicine and Life Sciences, Toledo, OH, USA
| | - Waleed Khokher
- University of Toledo College of Medicine and Life Sciences, Toledo, OH, USA
| | - Mohammed Mhanna
- Division of Cardiology, Department of Medicine, University of Iowa, Iowa City, IA, USA
| | - Mitra Patel
- University of Toledo College of Medicine and Life Sciences, Toledo, OH, USA
| | | | - Hazem Malas
- University of Toledo College of Medicine and Life Sciences, Toledo, OH, USA; ProMedica Toledo Hospital, Toledo, OH, USA
| | - Joel A Kammeyer
- University of Toledo College of Medicine and Life Sciences, Toledo, OH, USA; ProMedica Toledo Hospital, Toledo, OH, USA.
| |
Collapse
|