Deep learning for lung disease segmentation on CT: Which reconstruction kernel should be used?

Journal: Diagnostic and interventional imaging
Published Date: Oct 19, 2021

Abstract

PURPOSE: The purpose of this study was to determine whether a single reconstruction kernel or both high and low frequency kernels should be used for training deep learning models for the segmentation of diffuse lung disease on chest computed tomography (CT).

Authors

  • Trieu-Nghi Hoang-Thi
    Radiology Department, Hopital Cochin - AP-HP. Centre Université de Paris, 27 Rue du Faubourg Saint-Jacques, Paris 75014, France.
  • Maria Vakalopoulou
    Ecole CentraleSupelec, 91190, Gif-sur-Yvette, France.
  • Stergios Christodoulidis
  • Nikos Paragios
    TheraPanacea, Paris, France.
  • Marie-Pierre Revel
    Department of Radiology (G.C., S.D., M.P.R.) and Respiratory Medicine and National Cystic Reference Center (P.R.B.), Groupe Hospitalier Cochin-Hotel Dieu, AP-HP, Université Paris Descartes, 27 Rue du Faubourg Saint-Jacques, 75014 Paris, France; Center for Visual Computing, Ecole CentraleSupelec, Grande Voie des Vignes, Chatenay Malabry, France (G.C., E.I.Z., N.P.); U1016 Inserm, Institut Cochin, Paris, France (G.C., P.R.B., C.M., M.P.R.); Radiology Department (S.B.) and Pulmonary Department (R.C.), Hôpital Arnaud de Villeneuve, CHU de Montpellier, Université de Montpellier, Montpellier, France; ERN-Lung CF Network, France (P.R.B., C.M.); and TheraPanacea, Paris-Biotech-Santé, Paris, France (N.P.).
  • Guillaume Chassagnon
    Department of Radiology, Hopital Cochin, APHP, 75014 Paris, France; Université Paris Cité, 75006 Paris, France.

Keywords

External Resources

Popular Topics
Recent Journals