Can Deep Learning Replace Gadolinium in Neuro-Oncology?: A Reader Study.

Journal: Investigative radiology
Published Date:

Abstract

MATERIALS AND METHODS: This monocentric retrospective study leveraged 200 multiparametric brain MRIs acquired between November 2019 and February 2020 at Gustave Roussy Cancer Campus (Villejuif, France). A total of 145 patients were included: 107 formed the training sample (55 ± 14 years, 58 women) and 38 the separate test sample (62 ± 12 years, 22 women). Patients had glioma, brain metastases, meningioma, or no enhancing lesion. T1, T2-FLAIR, diffusion-weighted imaging, low-dose, and standard-dose postcontrast T1 sequences were acquired. A deep network was trained to process the precontrast and low-dose sequences to predict "virtual" surrogate images for contrast-enhanced T1. Once trained, the deep learning method was evaluated on the test sample. The discrepancies between the predicted virtual images and the standard-dose MRIs were qualitatively and quantitatively evaluated using both automated voxel-wise metrics and a reader study, where 2 radiologists graded image qualities and marked all visible enhancing lesions.

Authors

  • Samy Ammari
    Service de Radiologie, Gustave-Roussy, Université Paris-Saclay, Villejuif, France.
  • Alexandre Bône
    Guerbet Research, Villepinte.
  • Corinne Balleyguier
    Department of Radiology, Gustave Roussy Cancer Campus, Villejuif, France; Université Paris-Saclay, Paris, France.
  • Eric Moulton
    Guerbet Research, Villepinte.
  • Emilie Chouzenoux
    Center for Visual Computing, CentraleSupelec, INRIA Saclay, Gif-sur-Yvette, 91190, France.
  • Andreas Volk
  • Yves Menu
    From the Imaging Department, Gustave Roussy Cancer Campus, Université Paris-Saclay, Villejuif.
  • François Bidault
    Department of Radiology, Institut Gustave Roussy, 94800 Villejuif, France; Laboratoire d'Imagerie Biomédicale Multimodale Paris-Saclay. BIOMAPS, UMR 1281. Université Paris-Saclay, Inserm, CNRS, CEA, 94800 Villejuif, France.
  • François Nicolas
    Guerbet Research, Villepinte.
  • Philippe Robert
    Centre mémoire de ressources et de recherche, CHU Nice, 10 rue Molière, 06100 Nice, France; Pôle Réhabilitation autonomie vieillissement, CHU de Nice, 4 avenue de la Reine-Victoria, 06003 Nice, France; Centre d'innovation et d'usages en santé, université de Nice Sophia-Antipolis, CHU de Nice, 98 boulevard Édouard-Herriot, 06000 Nice, France.
  • Marc-Michel Rohe
  • Nathalie Lassau
    Laboratoire d'Imagerie Biomédicale Multimodale Paris-Saclay, BIOMAPS, UMR 1281, Université Paris-Saclay, Inserm, CNRS, CEA, 94800 Villejuif, France; Department of Imaging, Institut Gustave Roussy, Université Paris-Saclay. 94800 Villejuif, France.