Deep-learning based super-resolution for 3D isotropic coronary MR angiography in less than a minute

Purpose: To develop and evaluate a novel and generalizable super-resolution (SR) deep-learning framework for motion-compensated isotropic 3D coronary MR angiography (CMRA) which allows free-breathing acquisitions in less than a minute. Methods: Undersampled motion-corrected reconstructions have enabled free-breathing isotropic 3D CMRA in ~5-10min acquisition times. In this work, we propose a deep learning-based SR framework, combined with non-rigid respiratory motion compensation, to shorten the acquisition time to less than 1min. A generative adversarial network (GAN) is proposed consisting of two cascaded Enhanced Deep Residual Network generator, a trainable discriminator, and a perceptual loss network. A 16-fold increase in spatial resolution is achieved by reconstructing a high-resolution (HR) isotropic CMRA (0.9mm3 or 1.2mm3) from a low-resolution (LR) anisotropic CMRA (0.9x3.6x3.6mm3 or 1.2x4.8x4.8mm3). The impact and generalization of the proposed SRGAN approach to different input resolutions and operation on image and patch-level is investigated. SRGAN was evaluated on a retrospective downsampled cohort of 50 patients and on 16 prospective patients that were scanned with LR-CMRA in ~50s under free-breathing. Vessel sharpness and length of the coronary arteries from the SR-CMRA is compared against the HR-CMRA. Results: SR-CMRA showed statistically significant (p<0.001) improved vessel sharpness (34.1% pm 12.3%) and length (41.5% pm 8.1%) compared to LR-CMRA. Good generalization to input resolution and image/patch-level processing was found. SR-CMRA enabled recovery of coronary stenosis similar to HR-CMRA with comparable qualitative performance. Conclusion: The proposed SR-CMRA provides a 16-fold increase in spatial resolution with comparable image quality to HR-CMRA while reducing the predictable scan time to <1min.