Bayesian Optimization of Sampling Densities in MRI - Archive ouverte HAL Access content directly
Journal Articles Journal of Machine Learning for Biomedical Imaging Year : 2023

Bayesian Optimization of Sampling Densities in MRI

Abstract

Data-driven optimization of sampling patterns in MRI has recently received a significant attention. Following recent observations on the combinatorial number of minimizers in off-the-grid optimization, we propose a framework to globally optimize the sampling densities using Bayesian optimization. Using a dimension reduction technique, we optimize the sampling trajectories more than 20 times faster than conventional off-the-grid methods, with a restricted number of training samples. This method -- among other benefits -- discards the need of automatic differentiation. Its performance is slightly worse than state-of-the-art learned trajectories since it reduces the space of admissible trajectories, but comes with significant computational advantages. Other contributions include: i) a careful evaluation of the distance in probability space to generate trajectories ii) a specific training procedure on families of operators for unrolled reconstruction networks and iii) a gradient projection based scheme for trajectory optimization.
Fichier principal
Vignette du fichier
Bayesian Optimization of Sampling Densities in MRI - Gossard et al.pdf (5.3 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Licence

Dates and versions

hal-03777230 , version 1 (14-09-2022)
hal-03777230 , version 2 (12-06-2023)

Licence

Identifiers

Cite

Alban Gossard, Frédéric de Gournay, Pierre Weiss. Bayesian Optimization of Sampling Densities in MRI. Journal of Machine Learning for Biomedical Imaging, 2023, 2, pp.253. ⟨10.59275/j.melba.2023-8172⟩. ⟨hal-03777230v2⟩
153 View
56 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More