Keywords: Machine Learning/Artificial Intelligence, CEST & MT
Motivation: To obtain optimized schedules for a multi-slice CEST sequence
Goal(s): To develop a deep learning schedule optimization approach for joint continuous and discrete scan parameters optimization.
Approach: A joint deep learning framework was developed and used to generate optimized 10-slice acquisition schedules. The optimized schedules were compared in simulations to a random 10-slice schedule and an optimized 1-slice schedule. The optimized 10-slice and 1-slice schedules were also compared in vivo in a healthy subject.
Results: The proposed approach yielded acquisition schedules that provided tissue maps with lower error than a random schedule or an optimized 1-slice schedule.
Impact: This work proposes a novel deep learning framework that enables simultaneous optimization of continuous and discrete scan parameters for a rapid quantitative multi-slice CEST sequence. The proposed method provides acquisition schedules that enable quantitative CEST imaging with lower error.
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