EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Introducing µGUIDE for quantitative imaging via generalized uncertainty-driven inference using deep learning

Maëliss Jallais iD, Marco Palombo iD

eLife · 26.11.2024 · 13

DOI: 10.7554/elife.101069 ↗

Kurz gefasst

Fachartikel in der Zeitschrift eLife, online erschienen am 26.11.2024. Verfasst von Maëliss Jallais und 1 weiteren Autor:innen. Beteiligte Einrichtung: Cardiff University Brain Research Imaging Centre (CUBRIC), Cardiff University, Cardiff, United Kingdom. Hauptthemen laut MEDLINE: Deep Learning, Bayes Theorem. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 91 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wellcome Trust, UK Research and Innovation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 magnetic resonance imaging. Harnessing a new deep learning architecture for automatic signal feature selection combined with simulation-based inference and efficient sampling of the posterior distributions, µGUIDE 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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningBayes TheoremUncertaintyHumansDiffusion Magnetic Resonance ImagingImage Processing, Computer-Assisted

Stichwörter der Autor:innen

Bayesian inferencediffusion MRIhumanmicrostructure imagingneurosciencequantitative MRIsimulation-based inferenceuncertainty quantification

Autor:innen und Institutionen

  • Cardiff University Brain Research Imaging Centre (CUBRIC), Cardiff University, Cardiff, United Kingdom.
  • School of Computer Science and Informatics, Cardiff University, Cardiff, United Kingdom.

ORCID-Profile: Maëliss Jallais, Marco Palombo

Förderung

  • Wellcome Trust
  • UK Research and Innovation

Zitieren

APA

Jallais, M., & Palombo, M. (2024). Introducing µGUIDE for quantitative imaging via generalized uncertainty-driven inference using deep learning. eLife, 13. https://doi.org/10.7554/elife.101069

Vancouver

Jallais M, Palombo M. Introducing µGUIDE for quantitative imaging via generalized uncertainty-driven inference using deep learning. eLife. 2024;13. doi:10.7554/elife.101069

BibTeX
@article{Jallais2024,
  author = {Jallais, Maëliss and Palombo, Marco},
  title = {Introducing µGUIDE for quantitative imaging via generalized uncertainty-driven inference using deep learning},
  journal = {eLife},
  year = {2024},
  volume = {13},
  doi = {10.7554/elife.101069}
}
Kostenlos starten →