$μ$GUIDE: a framework for quantitative imaging via generalized uncertainty-driven inference using deep learning
This work addresses the challenge of quantitative imaging in MRI for researchers and clinicians by providing a more efficient uncertainty estimation method, though it appears incremental as it builds on existing Bayesian and deep learning techniques.
The authors tackled the problem of estimating tissue microstructure parameters from MRI data by proposing μGUIDE, a Bayesian framework that uses deep learning for feature selection and simulation-based inference, resulting in reduced computational costs compared to conventional methods without relying on acquisition constraints.
This work proposes $μ$GUIDE: a general Bayesian framework to estimate posterior distributions of tissue microstructure parameters from any given biophysical model or MRI signal representation, with exemplar demonstration in diffusion-weighted MRI. Harnessing a new deep learning architecture for automatic signal feature selection combined with simulation-based inference and efficient sampling of the posterior distributions, $μ$GUIDE bypasses the high computational and time cost of conventional Bayesian approaches and does not rely on acquisition constraints to define model-specific summary statistics. The obtained posterior distributions allow to highlight degeneracies present in the model definition and quantify the uncertainty and ambiguity of the estimated parameters.