Meeting Banner
Abstract #3287

Alternating Joint Learning Approach for Variational Networks and Sampling Pattern in Parallel MRI

Marcelo Victor Wust Zibetti1, Florian Knoll2, and Ravinder Regatte1
1Radiology, NYU Langone Health, New York, NY, United States, 2Department of Artificial Intelligence in Biomedical Engineering, FAU Erlangen-Nuremberg, Erlangen, Germany

Synopsis

We propose a new alternating learning approach to jointly learn the sampling pattern (SP) and the parameters of a variational network (VN) for acquisition and reconstruction on 3D Cartesian parallel MRI problems. This approach is composed of alternating short training with BASS algorithm to learn the SP, and ADAM algorithm to learn the parameters of the VN, both with forced monotonicity. The results illustrate that this approach provides reduced error when compared to other joint learning approaches, and surpasses VN trained with recently developed fixed SPs.

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.

Click here for more information on becoming a member.

Keywords