Deep learning for radial SMS myocardial perfusion reconstruction using the 3D residual booster U-net

• Published in: Magnetic resonance imaging Vol. 83; pp. 178 - 188
• Main Authors: Le, Johnathan, Tian, Ye, Mendes, Jason, Wilson, Brent, Ibrahim, Mark, DiBella, Edward, Adluru, Ganesh
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.11.2021
• Subjects: 3D U-Net; boosting; deep learning; Myocardial perfusion; radial simultaneous multi-slice; residual learning; deep learning; radial simultaneous multi-slice; boosting; 3D U-Net; Myocardial perfusion; residual learning
• ISSN: 0730-725X; 1873-5894; 1873-5894
• DOI: 10.1016/j.mri.2021.08.007

To develop an end-to-end deep learning solution for quickly reconstructing radial simultaneous multi-slice (SMS) myocardial perfusion datasets with comparable quality to the pixel tracking spatiotemporal constrained reconstruction (PT-STCR) method. Dynamic contrast enhanced (DCE) radial SMS myocardial perfusion data were obtained from 20 subjects who were scanned at rest and/or stress with or without ECG gating using a saturation recovery radial CAIPI turboFLASH sequence. Input to the networks consisted of complex coil combined images reconstructed using the inverse Fourier transform of undersampled radial SMS k-space data. Ground truth images were reconstructed using the PT-STCR pipeline. The performance of the residual booster 3D U-Net was tested by comparing it to state-of-the-art network architectures including MoDL, CRNN-MRI, and other U-Net variants. Results demonstrate significant improvements in speed requiring approximately 8 seconds to reconstruct one radial SMS dataset which is approximately 200 times faster than the PT-STCR method. Images reconstructed with the residual booster 3D U-Net retain quality of ground truth PT-STCR images (0.963 SSIM/40.238 PSNR/0.147 NRMSE). The residual booster 3D U-Net has superior performance compared to existing network architectures in terms of image quality, temporal dynamics, and reconstruction time. Residual and booster learning combined with the 3D U-Net architecture was shown to be an effective network for reconstructing high-quality images from undersampled radial SMS datasets while bypassing the reconstruction time of the PT-STCR method.