Microstructure.jl: a Julia Package for Probabilistic Microstructure Model Fitting with Diffusion MRI

TL;DR

Microstructure.jl is a Julia package that enables probabilistic estimation of tissue microstructure parameters from diffusion MRI data, supporting various models and advanced estimation techniques for improved analysis.

Contribution

It introduces a flexible, extensible Julia framework for probabilistic microstructure modeling, including new modules, methods, and practical applications with real datasets.

Findings

Supports multiple established microstructure models

Provides robust parameter estimation with MCMC and neural networks

Demonstrates effectiveness on synthesized and real datasets

Abstract

Microstructure.jl is a Julia package designed for probabilistic estimation of tissue microstructural parameters from diffusion or combined diffusion-relaxometry MRI data. It provides a flexible and extensible framework for defining compartment models and includes robust and unified estimators for parameter fitting and uncertainty quantification. The package incorporates several established models from the literature, such as the spherical mean technique and soma and neurite density imaging (SANDI), along with their extensions for analyzing combined diffusion and T2 mapping data acquired at multiple echo times. For parameter estimation, it features methods like Markov Chain Monte Carlo (MCMC) sampling and Monte Carlo dropout with neural networks, which provide probabilistic estimates by approximating the posterior distributions of model parameters. In this study, we introduce the major modules, functionality, and design of this package. We demonstrate its usage in optimizing acquisition protocols and evaluating model fitting performance with synthesized datasets. We also showcase practical applications with publicly available datasets. Microstructure.jl is applicable to in vivo and ex vivo imaging data acquired with typical research, high-performance, or pre-clinical scanners.