Keywords: AI/ML Image Reconstruction, AI/ML Image Reconstruction
Motivation: High-isotropic-resolution whole-heart CMR involves long and unpredictable scan times, often necessitating compromises to be made on the acquired resolution.
Goal(s): To develop a deep-learning-based framework for the reconstruction of high-resolution good-quality whole-heart images from fast undersampled low-resolution scans.
Approach: The Super-MoCo-MoDL framework was extended to combine undersampled and super-resolution reconstruction and then applied to reconstruct 0.9-mm3 isotropic-resolution whole-heart images from 2-minute 4.5-fold-undersampled 1.8×1.8×0.9-mm3 acquisitions.
Results: Sharp high-resolution whole-heart images at 0.9 mm3 were obtained, with an overall acceleration of 18-fold and ~2-minute reconstruction time. Comparable image quality to a high-resolution acquisition was observed, with no significant difference in measured vessel-sharpness values.
Impact: Extending Super-MoCo-MoDL for combined super-resolution and undersampled reconstruction allows sharp whole-heart 3D 0.9-mm3 isotropic-resolution images to be obtained from low-resolution 2-minute scans with 18-fold overall acceleration. This represents a promising approach towards achieving fast high-resolution 3D clinical CMR.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Keywords