Meeting Banner
Abstract #2456

Accelerating multi-contrast CEST MRI by recovery of sparsely sampled Z-spectrum offsets and B1s using a transformer-based neural network

Anshuman Swain1, Neil Wilson1, Paul Jacobs1, Blake Benyard1, and Ravinder Reddy1
1Center for Advanced Metabolic Imaging in Precision Medicine, Department of Radiology, University of Pennsylvania, Philadelphia, PA, United States

Synopsis

Keywords: CEST / APT / NOE, CEST & MT, Transformer, DL-based imputation, Accelerated MRI

Motivation: Chemical exchange saturation transfer (CEST) MRI provides metabolic information in vivo with high spatial specificity. However, acquisition of the canonical Z-spectrum and multiple contrasts is time-consuming and thus hinders rapid clinical translation.

Goal(s): Develop a novel method using a deep neural network to accelerate CEST acquisitions across offsets and saturation powers.

Approach: A state-of-the-art transformer-based network is used to recover densely sampled Z-spectra from sparsely sampled offsets across multiple saturation powers, allowing for an accelerated multi-B1 CEST acquisition.

Results: The neural network performs well in recovering sparsely sampled Z-spectra across multiple B1s, with low RMSE ad high image fidelity.

Impact: A state-of-the-art transformer-based network, SAITS, successfully recovers sparsely sampled Z-spectrum offsets and B1s, allowing for multi-contrast CEST MRI and B1 inhomogeneity correction. Given low reconstruction error and high image fidelity, this method facilitates rapid clinical translation of Z-spectrum acquisitions.

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