Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.09513 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914518864494592 |
|---|---|
| author | Uhl, Quentin Pavan, Tommaso Gerold, Julianna Chan, Kwok-Shing Jun, Yohan Fujita, Shohei Bhatt, Aneri Ma, Yixin Wang, Qiaochu Lee, Hong-Hsi Huang, Susie Y. Bilgic, Berkin Jelescu, Ileana |
| author_facet | Uhl, Quentin Pavan, Tommaso Gerold, Julianna Chan, Kwok-Shing Jun, Yohan Fujita, Shohei Bhatt, Aneri Ma, Yixin Wang, Qiaochu Lee, Hong-Hsi Huang, Susie Y. Bilgic, Berkin Jelescu, Ileana |
| contents | 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 identified an optimal 8-feature subset, cutting scan time from 27 to 14 minutes. Validated in vivo in seven healthy participants, the XAI protocol was benchmarked against the full 15-feature acquisition, a Cram'er-Rao Lower Bound (CRLB) theoretical optimum, and two heuristics ("Mid-Range" and "Corner"). It robustly reproduced parameter estimates and maintained test-retest reproducibility. Remarkably, the XAI selection converged to the CRLB optimum. This validates XAI's optimality while highlighting its main advantage: achieving gold-standard optimization without complex analytical Jacobians, making it easily adaptable to numerical models or complex noise where CRLB is intractable. Furthermore, XAI showed superior in vivo robustness over heuristics: "Mid-Range" sampling yielded biased exchange time estimates from insufficient temporal diversity, while "Corner" sampling gave unstable intra-neurite diffusivity estimates (5-fold higher CV) due to noise sensitivity. Ultimately, this robust 14-minute protocol accelerates exchange-sensitive microstructural mapping, establishing a model-agnostic optimization framework adaptable to future ultra-high gradient systems and existing clinical scanners. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09513 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reduced NEXI protocol for the quantification of human gray matter microstructure on the Connectome 2.0 scanner Uhl, Quentin Pavan, Tommaso Gerold, Julianna Chan, Kwok-Shing Jun, Yohan Fujita, Shohei Bhatt, Aneri Ma, Yixin Wang, Qiaochu Lee, Hong-Hsi Huang, Susie Y. Bilgic, Berkin Jelescu, Ileana Medical Physics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Image and Video Processing J.3 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 identified an optimal 8-feature subset, cutting scan time from 27 to 14 minutes. Validated in vivo in seven healthy participants, the XAI protocol was benchmarked against the full 15-feature acquisition, a Cram'er-Rao Lower Bound (CRLB) theoretical optimum, and two heuristics ("Mid-Range" and "Corner"). It robustly reproduced parameter estimates and maintained test-retest reproducibility. Remarkably, the XAI selection converged to the CRLB optimum. This validates XAI's optimality while highlighting its main advantage: achieving gold-standard optimization without complex analytical Jacobians, making it easily adaptable to numerical models or complex noise where CRLB is intractable. Furthermore, XAI showed superior in vivo robustness over heuristics: "Mid-Range" sampling yielded biased exchange time estimates from insufficient temporal diversity, while "Corner" sampling gave unstable intra-neurite diffusivity estimates (5-fold higher CV) due to noise sensitivity. Ultimately, this robust 14-minute protocol accelerates exchange-sensitive microstructural mapping, establishing a model-agnostic optimization framework adaptable to future ultra-high gradient systems and existing clinical scanners. |
| title | Reduced NEXI protocol for the quantification of human gray matter microstructure on the Connectome 2.0 scanner |
| topic | Medical Physics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Image and Video Processing J.3 |
| url | https://arxiv.org/abs/2509.09513 |