Meeting Banner
Abstract #4762

Swin-Transformer based B0 inhomogeneity correction for GluCEST and NOE MRI

Yiran Li1, Paul Jacobs2, Dushyant Kumar2, Anshuman Swain2, Ravi Prakash Re Nanga2, John Detre2, Ravinder Reddy2, and Ze Wang1
1Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, United States, 2University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, United States

Synopsis

Keywords: CEST / APT / NOE, CEST / APT / NOE, Deep learning

Motivation: For B0 correction of GluCEST MRI, some deep learning-based algorithms have been developed to significantly accelerate the Z-spectrum calibration process.

Goal(s): When applied to CEST imaging involving other metabolites, and to Nuclear Overhauser Effect (NOE) MRI, the performance of the model declined substantially. Our goal is to develop a new model that can handle different metabolites.

Approach: To address this issue, we proposed a Swin-Transformer-based model designed to handle both NOE and Glutamate-weighted CEST MRI separately.

Results: Preliminary results demonstrate strong performance on both GluCEST and NOE datasets, indicating the potential for a generalizable model applicable to other CEST agents.

Impact: This success of the proposed method suggests that the Swin Transformer could potentially serve as a general model for B0 correction across various metabolites in a single model if sufficient data is available.

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