μGUIDE: a framework for quantitative imaging via generalized uncertainty-driven inference using deep learning DOI Open Access

Maeliss Jallais,

Marco Palombo

Опубликована: Окт. 30, 2024

This work proposes μGUIDE: a general Bayesian framework to estimate posterior distributions of tissue microstructure parameters from any given biophysical model or signal representation, with exemplar demonstration in diffusion-weighted MRI. Harnessing new deep learning architecture for automatic feature selection combined simulationbased inference and efficient sampling the distributions, μGUIDE bypasses high computational time cost conventional approaches does not rely on acquisition constraints define model-specific summary statistics. The obtained allow highlight degeneracies present definition quantify uncertainty ambiguity estimated parameters.

Язык: Английский

μGUIDE: a framework for quantitative imaging via generalized uncertainty-driven inference using deep learning DOI Open Access

Maeliss Jallais,

Marco Palombo

Опубликована: Окт. 30, 2024

This work proposes μGUIDE: a general Bayesian framework to estimate posterior distributions of tissue microstructure parameters from any given biophysical model or signal representation, with exemplar demonstration in diffusion-weighted MRI. Harnessing new deep learning architecture for automatic feature selection combined simulationbased inference and efficient sampling the distributions, μGUIDE bypasses high computational time cost conventional approaches does not rely on acquisition constraints define model-specific summary statistics. The obtained allow highlight degeneracies present definition quantify uncertainty ambiguity estimated parameters.

Язык: Английский

Процитировано

0