Clinical impact of an explainable machine learning with amino acid PET imaging: application to the diagnosis of aggressive glioma.

Journal: European journal of nuclear medicine and molecular imaging
PMID:

Abstract

PURPOSE: Radiomics-based machine learning (ML) models of amino acid positron emission tomography (PET) images have shown efficiency in glioma prediction tasks. However, their clinical impact on physician interpretation remains limited. This study investigated whether an explainable radiomics model modifies nuclear physicians' assessment of glioma aggressiveness at diagnosis.

Authors

  • Shamimeh Ahrari
    IADI, U1254, Inserm, Université de Lorraine, Nancy, France. shamimeh.ahrari@univ-lorraine.fr.
  • Timothée Zaragori
    IADI, U1254, Inserm, Université de Lorraine, Nancy, France.
  • Adeline Zinsz
    Department of Nuclear Medicine, Centre Hospitalier Régional Universitaire de Nancy, Nancy, France.
  • Gabriela Hossu
    INSERM U1254, IADI, Université de Lorraine, 54511 Vandoeuvre-les-Nancy, France; CIC-IT, CHRU Nancy, Université de Lorraine, 54000 Nancy, France.
  • Julien Oster
  • Bastien Allard
    Department of Nuclear Medicine, Centre Hospitalier de Valence, Valence, France.
  • Laure Al Mansour
    Department of Nuclear Medicine, Hospices Civils de Lyon, Lyon, France.
  • Darejan Bessac
    Department of Nuclear Medicine and Molecular Imaging, ICANS, Strasbourg, France.
  • Sami Boumedine
    Department of Nuclear Medicine, Centre Antoine Lacassagne, Nice, France.
  • Caroline Bund
    MNMS Platform, University Hospitals of Strasbourg, Strasbourg 67098, France.
  • Nicolas De Leiris
    Department of Nuclear Medicine, Centre Hospitalier Universitaire Grenoble Alpes, Grenoble, France.
  • Anthime Flaus
    Department of Nuclear Medicine, Hospices Civils de Lyon, Lyon, France.
  • Eric Guedj
  • Aurélie Kas
    Nuclear Medicine Department, Groupe Hospitalier Pitié-Salpêtrière C. Foix, APHP, Paris, France.
  • Nathalie Keromnes
    Department of Nuclear Medicine, Centre Hospitalier Régional Universitaire de Brest, INSERM, UMR 1304, GETBO, University of Western Brittany (UBO), Brest, France.
  • Kevin Kiraz
    Department of Nuclear Medicine, Centre Hospitalier Universitaire Grenoble Alpes, Grenoble, France.
  • Fiene Marie Kuijper
    Department of Nuclear Medicine, Groupe Hospitalier Pitié-Salpêtrière, Assistance Publique-Hôpitaux de Paris (AP-HP), Paris, France.
  • Valentine Maitre
    Department of Nuclear Medicine, Timone Hospital, Marseille, France.
  • Solène Querellou
    Department of Nuclear Medicine, Centre Hospitalier Régional Universitaire de Brest, INSERM, UMR 1304, GETBO, University of Western Brittany (UBO), Brest, France.
  • Guilhem Stien
    Department of Nuclear Medicine, Centre Hospitalier Régional Universitaire de Nancy, Nancy, France.
  • Olivier Humbert
    Department of Nuclear Medicine, Centre Georges-François Leclerc, Dijon, France.
  • Laetitia Imbert
    CHRU-Nancy, Department of Nuclear Medicine & Nancyclotep imaging platform, Université de Lorraine, Nancy, France. l.imbert@chru-nancy.fr.
  • Antoine Verger
    CHRU-Nancy, Department of Nuclear Medicine & Nancyclotep imaging platform, Université de Lorraine, Nancy, France.