Keywords: Machine Learning/Artificial Intelligence, AI/ML Image Reconstruction
Motivation: Conventional cardiac CINE MRI requires multiple slices and breath-holds, leading to long scans and potential slice misalignment.
Goal(s): We aim to perform an efficient multi-slice single-breath-hold cardiac CINE at 1.5T and 0.55T.
Approach: Multi-slice single-breath-hold cardiac CINE at 1.5T and 0.55T is achieved by reducing the acquisition time of each slice to 1-1.5 s and reconstructing all slices simultaneously with a novel self-supervised slice and time dependent Deep Image Prior (ST-DIP) neural network.
Results: ST-DIP obtains high-quality images in 8-slice (8 s) CINE at 1.5T and 3-slice (4.5 s) CINE at 0.55T, outperforming conventional methods in image quality for both 0.55T and 1.5T.
Impact: The proposed approach enables the acquisition of multiple cardiac CINE slices in just one breath hold, both at 1.5T and 0.55T. This reduces acquisition time and thus minimizes slice misalignment for cardiac CINE exams.
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