Loading...
DWI simulation-assisted machine learning models for microstructure estimation
Rafael-Patino, Jonathan Yu, Thomas Delvigne, Victor Barakovic, Muhamed Pizzolato, Marco Girard, Gabriel Jones, Derek K. Canales-Rodríguez, Erick J. Thiran, Jean-Philippe
Rafael-Patino, Jonathan
Yu, Thomas
Delvigne, Victor
Barakovic, Muhamed
Pizzolato, Marco
Girard, Gabriel
Jones, Derek K.
Canales-Rodríguez, Erick J.
Thiran, Jean-Philippe
Abstract
Diffusion MRI (DW-MRI) allows for the detailed exploration of the brain white matter microstructure, with applications in both research and the clinic. However, state-of-the-art methods for microstructure estimation suffer from known limitations, such as the overestimation of the mean axon diameter, and the infeasibility of fitting diameter distributions. In this study, we propose to eschew current modeling-based approaches in favor of a novel, simulation-assisted machine learning approach. In particular, we train machine learning (ML) algorithms on a large dataset of simulated diffusion MRI signals from white matter regions with different axon diameter distributions and packing densities. We show, on synthetic data, that the trained models provide an accurate and efficient estimation of microstructural parameters in-silico and from DW-MRI data with moderately high b-values (4000 s/mm2
). Further, we show, on in-vivo data, that the estimators trained from simulations can provide parameter estimates which are close to the values expected from histology.
Keywords
diffusion MRI, machine learning, Monte-Carlo simulations
Date
2020
Type
Conference paper
Journal
Book
Computational Diffusion MRI : MICCAI Workshop, Shenzhen, China, October 2019
Volume
Issue
Page Range
125-134
Article Number
ACU Department
Collections
Relation URI
Source URL
Event URL
Open Access Status
Published as green open access
License
File Access
Controlled
Open
Open