Model-informed machine learning for multi-component T<sub>2</sub> relaxometry.

Details

Ressource 1Download: Yu_Signal.pdf (6136.90 [Ko])
State: Public
Version: Final published version
License: CC BY-NC-ND 4.0
Serval ID
serval:BIB_934FD7FA4F63
Type
Article: article from journal or magazin.
Collection
Publications
Institution
Title
Model-informed machine learning for multi-component T<sub>2</sub> relaxometry.
Journal
Medical image analysis
Author(s)
Yu T., Canales-Rodríguez E.J., Pizzolato M., Piredda G.F., Hilbert T., Fischi-Gomez E., Weigel M., Barakovic M., Bach Cuadra M., Granziera C., Kober T., Thiran J.P.
ISSN
1361-8423 (Electronic)
ISSN-L
1361-8415
Publication state
Published
Issued date
04/2021
Peer-reviewed
Oui
Volume
69
Pages
101940
Language
english
Notes
Publication types: Journal Article ; Research Support, Non-U.S. Gov't
Publication Status: ppublish
Abstract
Recovering the T <sub>2</sub> distribution from multi-echo T <sub>2</sub> magnetic resonance (MR) signals is challenging but has high potential as it provides biomarkers characterizing the tissue micro-structure, such as the myelin water fraction (MWF). In this work, we propose to combine machine learning and aspects of parametric (fitting from the MRI signal using biophysical models) and non-parametric (model-free fitting of the T <sub>2</sub> distribution from the signal) approaches to T <sub>2</sub> relaxometry in brain tissue by using a multi-layer perceptron (MLP) for the distribution reconstruction. For training our network, we construct an extensive synthetic dataset derived from biophysical models in order to constrain the outputs with a priori knowledge of in vivo distributions. The proposed approach, called Model-Informed Machine Learning (MIML), takes as input the MR signal and directly outputs the associated T <sub>2</sub> distribution. We evaluate MIML in comparison to a Gaussian Mixture Fitting (parametric) and Regularized Non-Negative Least Squares algorithms (non-parametric) on synthetic data, an ex vivo scan, and high-resolution scans of healthy subjects and a subject with Multiple Sclerosis. In synthetic data, MIML provides more accurate and noise-robust distributions. In real data, MWF maps derived from MIML exhibit the greatest conformity to anatomical scans, have the highest correlation to a histological map of myelin volume, and the best unambiguous lesion visualization and localization, with superior contrast between lesions and normal appearing tissue. In whole-brain analysis, MIML is 22 to 4980 times faster than the non-parametric and parametric methods, respectively.
Keywords
relaxometry, Machine learning, Myelin water imaging, relaxometry
Pubmed
Web of science
Open Access
Yes
Create date
25/01/2021 9:48
Last modification date
15/05/2021 5:31
Usage data