Going beyond voxel-wise deconvolution in perfusion MRI: learning and leveraging spatio-temporal regularities with the stU-Net - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

Going beyond voxel-wise deconvolution in perfusion MRI: learning and leveraging spatio-temporal regularities with the stU-Net

Résumé

We present a deep learning method able to accurately predict quantitative perfusion maps from raw perfusion sequences, even in low-dose regimes of gadolinium-based contrast agent. The proposed stU-Net architecture is composed of a 2dimensional decoder and a 3-dimensional encoder able to exploit spatio-temporal regularities by learning convolutional filters that jointly act on the spatial and temporal domains. The method is evaluated on a public data set containing 49 patients with brain tumors, using an original approach to simulate low-dose perfusion sequences.
Fichier principal
Vignette du fichier
ISBI_2021__DSC.pdf (1.55 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03128610 , version 1 (02-02-2021)

Identifiants

  • HAL Id : hal-03128610 , version 1

Citer

Julien Veron Vialard, Marc-Michel Rohé, Philippe Robert, François Nicolas, Alexandre Bône. Going beyond voxel-wise deconvolution in perfusion MRI: learning and leveraging spatio-temporal regularities with the stU-Net. 2021. ⟨hal-03128610⟩

Collections

CENTRALESUPELEC
142 Consultations
87 Téléchargements

Partager

Gmail Facebook X LinkedIn More