1
|
Islam KT, Zhong S, Zakavi P, Chen Z, Kavnoudias H, Farquharson S, Durbridge G, Barth M, McMahon KL, Parizel PM, Dwyer A, Egan GF, Law M, Chen Z. Improving portable low-field MRI image quality through image-to-image translation using paired low- and high-field images. Sci Rep 2023; 13:21183. [PMID: 38040835 PMCID: PMC10692211 DOI: 10.1038/s41598-023-48438-1] [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: 08/22/2023] [Accepted: 11/27/2023] [Indexed: 12/03/2023] Open
Abstract
Low-field portable magnetic resonance imaging (MRI) scanners are more accessible, cost-effective, sustainable with lower carbon emissions than superconducting high-field MRI scanners. However, the images produced have relatively poor image quality, lower signal-to-noise ratio, and limited spatial resolution. This study develops and investigates an image-to-image translation deep learning model, LoHiResGAN, to enhance the quality of low-field (64mT) MRI scans and generate synthetic high-field (3T) MRI scans. We employed a paired dataset comprising T1- and T2-weighted MRI sequences from the 64mT and 3T and compared the performance of the LoHiResGAN model with other state-of-the-art models, including GANs, CycleGAN, U-Net, and cGAN. Our proposed method demonstrates superior performance in terms of image quality metrics, such as normalized root-mean-squared error, structural similarity index measure, peak signal-to-noise ratio, and perception-based image quality evaluator. Additionally, we evaluated the accuracy of brain morphometry measurements for 33 brain regions across the original 3T, 64mT, and synthetic 3T images. The results indicate that the synthetic 3T images created using our proposed LoHiResGAN model significantly improve the image quality of low-field MRI data compared to other methods (GANs, CycleGAN, U-Net, cGAN) and provide more consistent brain morphometry measurements across various brain regions in reference to 3T. Synthetic images generated by our method demonstrated high quality both quantitatively and qualitatively. However, additional research, involving diverse datasets and clinical validation, is necessary to fully understand its applicability for clinical diagnostics, especially in settings where high-field MRI scanners are less accessible.
Collapse
Affiliation(s)
- Kh Tohidul Islam
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, Australia.
| | - Shenjun Zhong
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, Australia
- Australian National Imaging Facility, Brisbane, QLD, Australia
| | - Parisa Zakavi
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, Australia
| | - Zhifeng Chen
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, Australia
- Department of Data Science and AI, Faculty of Information Technology, Monash University, Melbourne, VIC, Australia
| | - Helen Kavnoudias
- Department of Neuroscience, Central Clinical School, Monash University, Melbourne, VIC, Australia
- Department of Radiology, Alfred Hospital, Melbourne, VIC, Australia
| | | | - Gail Durbridge
- Herston Imaging Research Facility, University of Queensland, Brisbane, QLD, Australia
| | - Markus Barth
- School of Information Technology and Electrical Engineering and Centre for Advanced Imaging, University of Queensland, Brisbane, QLD, Australia
| | - Katie L McMahon
- School of Clinical Science, Herston Imaging Research Facility, Queensland University of Technology, Brisbane, QLD, Australia
| | - Paul M Parizel
- David Hartley Chair of Radiology, Department of Radiology, Royal Perth Hospital, Perth, WA, Australia
- Medical School, University of Western Australia, Perth, WA, Australia
| | - Andrew Dwyer
- South Australian Health and Medical Research Institute, Adelaide, SA, Australia
| | - Gary F Egan
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, Australia
| | - Meng Law
- Department of Neuroscience, Central Clinical School, Monash University, Melbourne, VIC, Australia
- Department of Radiology, Alfred Hospital, Melbourne, VIC, Australia
| | - Zhaolin Chen
- Monash Biomedical Imaging, Monash University, Melbourne, VIC, Australia
- Department of Data Science and AI, Faculty of Information Technology, Monash University, Melbourne, VIC, Australia
| |
Collapse
|