Keywords: Microstructure, Diffusion Acquisition, Diffusion Modeling; Gradients; Machine Learning/Artificial Intelligence
Motivation: The Neurite Exchange Imaging (NEXI) model provides valuable insights into gray matter microstructure but requires lengthy scan times, limiting translation to clinical and research studies.
Goal(s): Reduce NEXI acquisition time on the CONNECTOM 2.0 scanner while retaining accuracy, with the potential for future clinical application.
Approach: Using Recursive Feature Elimination with SHAP and XGBoost, we identified essential b-value and diffusion time combinations to shorten the protocol. This method allowed us to reduce scan time by 50%, focusing on the most informative features.
Results: The optimized protocol reduced acquisition time from 30 to 15 minutes, preserving accuracy in NEXI parameters and brain spatial patterns.
Impact: We demonstrate an effective method for reducing Neurite Exchange Imaging acquisition time on the CONNECTOM 2.0 scanner. This approach has potential for broader application on clinical scanners in routine neuroimaging, facilitating gray matter microstructure insights in patient populations.
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