Reducing the NEXI acquisition time for the quantification of human gray matter microstructure on the CONNECTOM 2.0 scanner

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.