Keywords: Myocardium, AI/ML Image Reconstruction, 3D Cardiac Cine, Image Restoration, Super-resolution
Motivation: Advance low-cost shielding-free ultra-low-field (ULF) MRI for cardiac imaging by tackling its two fundamental limitations, low spatial resolution and signal-to-noise ratio.
Goal(s): To acquire 3D cardiac cine data at 0.05T, and boost 4D image quality with deep learning by leveraging spatiotemporal information available in 3D cardiac cine data.
Approach: We implemented 3D bSSFP for 0.05T 3D cardiac cine imaging and developed a 4D recurrent deep learning framework with fully 4D convolutions.
Results: Proposed 4D framework effectively suppressed noise, artefacts while restoring anatomical details and temporal coherence in 0.05T 3D cardiac cine data. This approach potentially enables heart function and morphology assessment at 0.05T.
Impact: Enhancing image resolution and fidelity for 8-min 0.05T free-breathing 3D cardiac cine imaging using data-driven 4D deep learning approach potentially enables assessment of cardiac function and morphology at 0.05 Tesla.
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