Keywords: Other AI/ML, Machine Learning/Artificial Intelligence, Transformers, Contrast Generation, Quantification, Relaxometry, CEST, MT, Field Mapping
Motivation: Multi-contrast and multi-metabolite CEST, MT, and relaxivity imaging necessitate a separate pulse sequence for each application of interest, rendering it time-consuming and seldom performed in clinical settings.
Goal(s): To develop a computational framework that learns the RF excitation to tissue response manifold transfer, enabling on-demand contrast generation.
Approach: A hybrid CNN transformer was designed to generate a new set of contrast-weighted and quantitative images in response to a user-defined (on-demand) unseen set of acquisition parameters. Validation was performed on four subjects and patients scanned at two sites.
Results: An excellent similarity between the generated images and ground-truth was obtained with 94% acceleration.
Impact: A deep learning framework was designed to provide rich biological information in less than 30 seconds. It can capture the magnetic signal dynamics in humans and decode the tissue response to RF excitation, constituting a deep MRI on a chip.
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