Jointly Estimation of Microstructure Maps Across Acquisition Protocols

Diffusion MRI (dMRI) allows for examining microarchitecture profiles and tissue changes using specific microstructure modeling but depends on advanced acquisition protocol and well-established biological model assumptions. It is also limited in clinical applications due to lengthy acquisition time and dense q-space sampling requirements. In this study, we present a method that aims to estimate multiple functional microstructural parameters robustly, thereby enhancing clinical applications with different acquisition protocols. Instead of learning the mapping between dMRI and microstructure maps directly, our approach learns a set of explainable over-completed tissue-compartment kernels between parameterized spherical mean signal and widely-used microstructure maps and apply into the joint characterization of multiple biological models. We validate the effectiveness of our method using an in vivo dataset across different health conditions collected by a clinical scanner. This work sets the foundation for future techniques that integrate clinical data acquisition protocols and enhance sensitivity to microstructure measures. The code is provided at https://github.com/1nlandempire/JEMAP.