Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
The authors recast diffusion MRI microstructure mapping from a collection of ill-posed, independent voxel fits into a unified global inverse problem that reconstructs the entire tissue parameter field jointly. To resolve the resulting nonconvex optimization without external training data, the framework combines an untrained coordinate-based neural representation for continuous spatial priors with coregistered T1-weighted anatomical guidance. Evaluated on synthetic and in-vivo data, this zero-shot global inversion consistently outperforms both conventional voxel-wise estimators and data-driven deep learning baselines.
Solving diffusion MRI microstructure mapping as a unified global field rather than isolated voxels—regularized solely by an untrained neural network and standard T1 anatomy—outperforms supervised baselines without requiring any training data.
Diffusion MRI microstructure mapping (MM) is conventionally solved voxel by voxel, ignoring the fact that tissue microstructure forms a spatially organized field. This isolation leaves each estimation problem ill-posed and nonconvex. We instead cast MM as a single global inverse problem, reconstructing the entire parameter field jointly from all measurements of a subject. An untrained neural representation supplies implicit spatial priors and eases the nonconvex optimization, requiring no training data, while coregistered T1-weighted anatomy contributes structural guidance that is freely available in standard protocols. On both synthetic and in-vivo data, our method compares favorably with established voxel-wise and learning-based baselines, suggesting global inversion is a promising alternative.