Preprint
Aug 2026
Protocol generalisation for brain tissue microstructure estimation via hypernetwork-controlled geometric deep learning
Results demonstrate that the proposed method achieves reduced RMSE and bias on synthetic data, as well as higher agreement with conventional NODDI fitting on real data, indicating improved robustness to unseen b-values and a reduced need for retraining.
A. Brigliadori, Leevi Kerkela, Hui Zhang
· 0 citations