Keywords: AI/ML Image Reconstruction, Machine Learning/Artificial Intelligence, cardiac cine, unrolled deep network, deformable
Motivation: Conventional CNN-based unrolling networks have a significant limitation in accurately capturing complex, non-rigid cardiac motions and deformations.
Goal(s): To develop a new deep unrolling method capable of accurately reconstructing local features and motions in cardiac cine MR images.
Approach: We propose a Spatiotemporal Deformable Unrolling Network (SDUN) for cardiac cine MR Reconstruction, which adapts the sampling grid to complex motions and deformations of the heart by learning bias values from input feature maps.
Results: The proposed method was test on in-house acquired cardiac cine MR data and provided SOTA reconstructions with a PSNR of 44.4548 and a SSIM of 0.9854 at 16X acceleration.
Impact: The proposed method SDUN provides an effective scheme for accurately capturing and learning complex cardiac motions and deformations in cardiac cine MR reconstruction through employing a deformable and adaptive CNN in proximal network.
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