Multi-Slice Single-Breath-Hold Cardiac CINE with Slice and Time-Dependent Deep Image Prior at 1.5T and 0.55T

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.