Open-source Large Language Models can Generate Labels from Radiology Reports for Training Convolutional Neural Networks.

Journal: Academic radiology
Published Date: Jan 6, 2025

Abstract

RATIONALE AND OBJECTIVES: Training Convolutional Neural Networks (CNN) requires large datasets with labeled data, which can be very labor-intensive to prepare. Radiology reports contain a lot of potentially useful information for such tasks. However, they are often unstructured and cannot be directly used for training. The recent progress in large language models (LLMs) might introduce a new useful tool in interpreting radiology reports. This study aims to explore the use of the LLM to classify radiology reports and generate labels. These labels will be utilized then to train a CNN to detect ankle fractures to evaluate the effectiveness of using automatically generated labels.

Authors

  • Fares Al Mohamad
    Department of Radiology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Charitéplatz 1, 10117 Berlin, Germany (F.A.M., L.D., F.D., L.R., K.D., H.H., L.X., F.B.). Electronic address: fares.al-mohamad@charite.de.
  • Leonhard Donle
    Department of Radiology, Charite - Universitatsmedizin Berlin, Berlin, Germany.
  • Felix Dorfner
    Department of Radiology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Charitéplatz 1, 10117 Berlin, Germany (F.A.M., L.D., F.D., L.R., K.D., H.H., L.X., F.B.); Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital and Harvard Medical School, 149 13th St, Charlestown, MA 02129 (F.D.).
  • Laura Romanescu
    Department of Radiology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Charitéplatz 1, 10117 Berlin, Germany (F.A.M., L.D., F.D., L.R., K.D., H.H., L.X., F.B.).
  • Kristin Drechsler
    Department of Radiology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Charitéplatz 1, 10117 Berlin, Germany (F.A.M., L.D., F.D., L.R., K.D., H.H., L.X., F.B.).
  • Mike P Wattjes
    Department of Radiology & Nuclear Medicine, Neuroscience Campus Amsterdam, VUmc MS Center Amsterdam, VU University Medical Center Amsterdam, Amsterdam, The Netherlands.
  • Jawed Nawabi
    Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg Eppendorf, Hamburg, Germany. jawed.nawabi@charite.de.
  • Marcus R Makowski
    School of Medicine and Health, Department of Diagnostic and Interventional Radiology, Klinikum rechts der Isar, TUM University Hospital, Technical University of Munich, Munich, Germany.
  • Hartmut Häntze
    Department of Radiology, Charite - Universitatsmedizin Berlin, Berlin, Germany.
  • Lisa Adams
    Department of Radiology, Charité - Universitätsmedizin Berlin, Hindenburgdamm 30, 12203, Berlin, Germany.
  • Lina Xu
    Emergency Department, Beichen Hospital, Tianjin, China.
  • Felix Busch
    Institute for Diagnostic and Interventional Radiology, TUM School of Medicine and Health, TUM University Hospital Rechts der Isar, Technical University of Munich, Munich, Germany.
  • Aymen Meddeb
    Charité-Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Klinik für Radiologie, Hindenburgdamm 30, 12203 Berlin, Germany.
  • Keno Kyrill Bressem
    Department of Radiology and Nuclear Medicine, German Heart Center Munich, Lazarettstraße 36, 80636 Munich, Germany (K.K.B.).

Keywords

External Resources

Popular Topics
Recent Journals