A deep learning-based algorithm improves radiology residents' diagnoses of acute pulmonary embolism on CT pulmonary angiograms.

Journal: European journal of radiology
Published Date:

Abstract

PURPOSE: To compare radiology residents' diagnostic performances to detect pulmonary emboli (PEs) on CT pulmonary angiographies (CTPAs) with deep-learning (DL)-based algorithm support and without.

Authors

  • Alexandre Vallée
    Paris-Descartes University.
  • Raphaelle Quint
    Department of Radiology, Hôpital Pitié-Salpétrière, Assistance Publique-Hôpitaux de Paris, 75013, Paris, France.
  • Anne Laure Brun
    Department of Medical Imaging, Hôpital Foch. 40 rue Worth 92150 Suresnes, France. Electronic address: al.brun@hopital-foch.com.
  • François Mellot
    Department of Medical Imaging, Hôpital Foch. 40 rue Worth 92150 Suresnes, France. Electronic address: f.mellot@hopital-foch.org.
  • Philippe A Grenier
    From the Department of Clinical Research and Innovation, Hôpital Foch, 40 rue Worth, Suresnes 92150, France.