Movienet: Deep space–time-coil reconstruction network without k-space data consistency for fast motion-resolved 4D MRI Journal Article
| Authors: | Murray, V.; Siddiq, S.; Crane, C.; El Homsi, M.; Kim, T. H.; Wu, C.; Otazo, R. |
| Article Title: | Movienet: Deep space–time-coil reconstruction network without k-space data consistency for fast motion-resolved 4D MRI |
| Abstract: | Purpose: To develop a novel deep learning approach for 4D-MRI reconstruction, named Movienet, which exploits space–time-coil correlations and motion preservation instead of k-space data consistency, to accelerate the acquisition of golden-angle radial data and enable subsecond reconstruction times in dynamic MRI. Methods: Movienet uses a U-net architecture with modified residual learning blocks that operate entirely in the image domain to remove aliasing artifacts and reconstruct an unaliased motion-resolved 4D image. Motion preservation is enforced by sorting the input image and reference for training in a linear motion order from expiration to inspiration. The input image was collected with a lower scan time than the reference XD-GRASP image used for training. Movienet is demonstrated for motion-resolved 4D MRI and motion-resistant 3D MRI of abdominal tumors on a therapeutic 1.5T MR-Linac (1.5-fold acquisition acceleration) and diagnostic 3T MRI scanners (2-fold and 2.25-fold acquisition acceleration for 4D and 3D, respectively). Image quality was evaluated quantitatively and qualitatively by expert clinical readers. Results: The reconstruction time of Movienet was 0.69 s (4 motion states) and 0.75 s (10 motion states), which is substantially lower than iterative XD-GRASP and unrolled reconstruction networks. Movienet enables faster acquisition than XD-GRASP with similar overall image quality and improved suppression of streaking artifacts. Conclusion: Movienet accelerates data acquisition with respect to compressed sensing and reconstructs 4D images in less than 1 s, which would enable an efficient implementation of 4D MRI in a clinical setting for fast motion-resistant 3D anatomical imaging or motion-resolved 4D imaging. © 2023 International Society for Magnetic Resonance in Medicine. |
| Keywords: | clinical article; controlled study; pancreas cancer; nuclear magnetic resonance imaging; magnetic resonance imaging; algorithm; image enhancement; quantitative analysis; image quality; imaging, three-dimensional; diagnosis; informed consent; image processing, computer-assisted; image processing; motion; respiration; image reconstruction; qualitative analysis; breathing; respiratory gated imaging; respiratory-gated imaging techniques; procedures; data acquisition; acceleration; dynamic mri; three-dimensional imaging; fourier transform; human; article; iterative methods; deep learning; data consistency; 4d mri; four-dimensional imaging; reconstruction networks; 4d images; fast motions; k-space datum; spacetime; deep space time coil reconstruction network; fast motion resolved four dimensional magnetic resonance imaging; k space data consistency; modified residual learning block; nonuniform fast fourier transform |
| Journal Title: | Magnetic Resonance in Medicine |
| Volume: | 91 |
| Issue: | 2 |
| ISSN: | 0740-3194 |
| Publisher: | John Wiley & Sons |
| Date Published: | 2024-02-01 |
| Start Page: | 600 |
| End Page: | 614 |
| Language: | English |
| DOI: | 10.1002/mrm.29892 |
| PUBMED: | 37849064 |
| PROVIDER: | scopus |
| PMCID: | PMC10842259 |
| DOI/URL: | |
| Notes: | The MSK Cancer Center Support Grant (P30 CA008748) is acknowledged in the PDF -- Corresponding author is MSK author: Victor Murray -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
Related MSK Work