Highly accurate classification of chest radiographic reports using a deep learning natural language model pre-trained on 3.8 million text reports.

Journal: Bioinformatics (Oxford, England)
Published Date:

Abstract

MOTIVATION: The development of deep, bidirectional transformers such as Bidirectional Encoder Representations from Transformers (BERT) led to an outperformance of several Natural Language Processing (NLP) benchmarks. Especially in radiology, large amounts of free-text data are generated in daily clinical workflow. These report texts could be of particular use for the generation of labels in machine learning, especially for image classification. However, as report texts are mostly unstructured, advanced NLP methods are needed to enable accurate text classification. While neural networks can be used for this purpose, they must first be trained on large amounts of manually labelled data to achieve good results. In contrast, BERT models can be pre-trained on unlabelled data and then only require fine tuning on a small amount of manually labelled data to achieve even better results.

Authors

  • Keno K Bressem
    School of Medicine and Health, Institute for Cardiovascular Radiology and Nuclear Medicine, German Heart Center Munich, TUM University Hospital, Technical University of Munich, Munich, Germany.
  • Lisa C Adams
    School of Medicine and Health, Department of Diagnostic and Interventional Radiology, Klinikum rechts der Isar, TUM University Hospital, Technical University of Munich, Munich, Germany.
  • Robert A Gaudin
    Department of Oral- and Maxillofacial Surgery, Charité, Berlin 12203, Germany.
  • Daniel Tröltzsch
    Department of Oral- and Maxillofacial Surgery, Charité, Berlin 12203, Germany.
  • Bernd Hamm
    Department of Diagnostic and Interventional Radiology, Charité -Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany.
  • 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.
  • Chan-Yong Schüle
    Department of Radiology, Charité, Berlin 12203, Germany.
  • Janis L Vahldiek
    Charité Universitätsmedizin Berlin, Campus Benjamin Franklin, Hindenburgdamm 30, 12203, Berlin, Germany.
  • Stefan M Niehues
    Charité Universitätsmedizin Berlin, Campus Benjamin Franklin, Hindenburgdamm 30, 12203, Berlin, Germany.