PGMI assessment in mammography: AI software versus human readers.

Journal: Radiography (London, England : 1995)
Published Date: Jul 5, 2025

Abstract

INTRODUCTION: The aim of this study was to evaluate human inter-reader agreement of parameters included in PGMI (perfect-good-moderate-inadequate) classification of screening mammograms and explore the role of artificial intelligence (AI) as an alternative reader.

Authors

  • T Santner
    Medical University of Innsbruck, Fritz-Pregl-Strasse 3, 6020, Innsbruck, Austria. Electronic address: tina.santner@student.i-med.ac.at.
  • C Ruppert
    Department of Diagnostic and Interventional Radiology, University Hospital Zürich, Zürich, Switzerland.
  • S Gianolini
    MSS Medical Software Solutions GmbH, Holzwiesstrasse 48, 8703, Erlenbach, Switzerland. Electronic address: stefano@gianolini.ch.
  • J-G Stalheim
    Evidia, Kaigaten 5, 5015, Bergen, Norway. Electronic address: johanne.gro.stalheim@evidia.no.
  • S Frei
    Way to Women Sàrl, Chemin du Pré de l'Epine 7, 1261, Le Vaud, Switzerland. Electronic address: w4women@outlook.com.
  • M Hondl
    Klinik Ottakring, Montleartstraße 37, 1160, Wien, Austria. Electronic address: michaela.hondl-adametz@gesundheitsverbund.at.
  • V Fröhlich
    University of Applied Sciences Wiener Neustadt, Johannes Gutenberg Strasse 3, 2700, Wiener Neustadt, Austria. Electronic address: vanessa.froehlich@fhwn.ac.at.
  • S Hofvind
    Cancer Registry of Norway, Norwegian Institute of Public Health, Ullernchausseen 64, 0379, Oslo, Norway. Electronic address: solveig.hofvind@kreftregisteret.no.
  • G Widmann
    Medical University of Innsbruck, Department of Radiology, Anichstrasse 35, 6020, Innsbruck, Austria. Electronic address: gerlig.widmann@i-med.ac.at.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals