Reduced NEXI protocol for the quantification of human gray matter microstructure on the Connectome 2.0 scanner
arXiv:2509.09513v3 Announce Type: replace-cross Abstract: Biophysical diffusion MRI models like Neurite Exchange Imaging (NEXI) are essential for probing gray matter microstructure, estimating compartment diffusivities, neurite fraction, and exchange time. However, NEXI's multi-shell, multi-diffusion-time requirements cause prohibitively long acquisitions. Leveraging the Connectome 2.0 ultra-high gradient scanner, we developed a time-efficient protocol using an Explainable AI (XAI) framework. Combining XGBoost, SHAP, and Recursive Feature Elimination trained on synthetic signals, XAI identifie
The continuous advancements in MRI technology (Connectome 2.0) and the increasing sophistication of Explainable AI (XAI) frameworks are converging to enable new diagnostic capabilities.
This development allows for faster, more accurate quantitative analysis of brain microstructure, which is crucial for understanding neurological diseases and drug development.
The ability to perform complex biophysical modeling like NEXI with significantly reduced acquisition times makes these advanced diagnostic tools more practical for clinical and research settings.
- · Neuroscience researchers
- · Medical diagnostic developers
- · Pharmaceutical companies
- · AI companies specializing in medical imaging
- · Traditional diffusion MRI protocols
- · Diagnostic approaches relying solely on qualitative assessments
More widespread adoption of detailed gray matter microstructure analysis in clinical diagnostics and drug trials.
Accelerated understanding of neurodegenerative diseases and improved precision in therapeutic interventions.
Potential for early detection and personalized treatment strategies for complex neurological conditions, reducing healthcare burdens long-term.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI