Contrast-enhanced brain MRI synthesis with deep learning: key input modalities and asymptotic performance - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Contrast-enhanced brain MRI synthesis with deep learning: key input modalities and asymptotic performance

Abstract

Contrast-enhanced medical images offer vital insights for the accurate diagnosis, characterization and treatment of tumors, and are routinely used worldwide. Acquiring such images requires to inject the patient intravenously with a gadolinium-based contrast agent (GBCA). Although GBCAs are considered safe, recent concerns about their accumulation in the body tilted the medical consensus towards a more parsimonious usage. Focusing on the case of brain magnetic resonance imaging, this paper proposes a deep learning method that synthesizes virtual contrast-enhanced T1 images as if they had been acquired after the injection of a standard 0.100 mmol/kg dose of GBCA, taking as inputs complementary imaging modalities obtained either after a reduced injection at 0.025 mmol/kg or without any GBCA involved. The method achieves a competitive structural similarity index of 94.2%. Its asymptotic performance is estimated, and the most important input modalities are identified.
Fichier principal
Vignette du fichier
ISBI_2021__VCE.pdf (1.99 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03128023 , version 1 (01-02-2021)

Identifiers

  • HAL Id : hal-03128023 , version 1

Cite

Alexandre Bône, Samy Ammari, Jean-Philippe Lamarque, Mickael Elhaik, Émilie Chouzenoux, et al.. Contrast-enhanced brain MRI synthesis with deep learning: key input modalities and asymptotic performance. ISBI 2021 - International Symposium on Biomedical Imaging, Apr 2021, Nice / Virtual, France. ⟨hal-03128023⟩
253 View
400 Download

Share

Gmail Mastodon Facebook X LinkedIn More