Artificial Intelligence for Clinical Interpretation of Bedside Chest Radiographs.

Journal: Radiology
Published Date: Dec 6, 2022

Abstract

Background Supine chest radiography for bedridden patients in intensive care units (ICUs) is one of the most frequently ordered imaging studies worldwide. Purpose To evaluate the diagnostic performance of a neural network-based model that is trained on structured semiquantitative radiologic reports of bedside chest radiographs. Materials and Methods For this retrospective single-center study, children and adults in the ICU of a university hospital who had been imaged using bedside chest radiography from January 2009 to December 2020 were reported by using a structured and itemized template. Ninety-eight radiologists rated the radiographs semiquantitatively for the severity of disease patterns. These data were used to train a neural network to identify cardiomegaly, pulmonary congestion, pleural effusion, pulmonary opacities, and atelectasis. A held-out internal test set (100 radiographs from 100 patients) that was assessed independently by an expert panel of six radiologists provided the ground truth. Individual assessments by each of these six radiologists, by two nonradiologist physicians in the ICU, and by the neural network were compared with the ground truth. Separately, the nonradiologist physicians assessed the images without and with preliminary readings provided by the neural network. The weighted Cohen κ coefficient was used to measure agreement between the readers and the ground truth. Results A total of 193 566 radiographs in 45 016 patients (mean age, 66 years ± 16 [SD]; 61% men) were included and divided into training ( = 122 294; 64%), validation ( = 31 243; 16%), and test ( = 40 029; 20%) sets. The neural network exhibited higher agreement with a majority vote of the expert panel (κ = 0.86) than each individual radiologist compared with the majority vote of the expert panel (κ = 0.81 to ≤0.84). When the neural network provided preliminary readings, the reports of the nonradiologist physicians improved considerably (aided vs unaided, κ = 0.87 vs 0.79, respectively; < .001). Conclusion A neural network trained with structured semiquantitative bedside chest radiography reports allowed nonradiologist physicians improved interpretations compared with the consensus reading of expert radiologists. © RSNA, 2022 See also the editorial by Wielpütz in this issue.

Authors

  • Firas Khader
    Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany.
  • Tianyu Han
    Physics of Molecular Imaging Systems, Experimental Molecular Imaging, RWTH Aachen University, Aachen, Germany. tianyu.han@pmi.rwth-aachen.de.
  • Gustav Müller-Franzes
    From the Department of Diagnostic and Interventional Radiology (F.K., G.M.F., L.H., P.S., S.K., E.B., M.S.H., F.P., M.Z., C.K., P.B., S.N., D.T.), Department of Medicine III (J.K., K.H.), and Clinic for Surgical Intensive Medicine and Intermediate Care (G.M.), University Hospital Aachen, Pauwelsstrasse 30, 52064 Aachen, Germany; Physics of Molecular Imaging Systems, Experimental Molecular Imaging (T.H., V.S.), and Institute of Imaging and Computer Vision (J.S.), RWTH Aachen University, Aachen, Germany; Department of Inner Medicine, Luisenhospital Aachen, Aachen, Germany (L.N.); and Ocumeda AG, Erlen, Switzerland (C.H.).
  • Luisa Huck
    From the Department of Diagnostic and Interventional Radiology (F.K., G.M.F., L.H., P.S., S.K., E.B., M.S.H., F.P., M.Z., C.K., P.B., S.N., D.T.), Department of Medicine III (J.K., K.H.), and Clinic for Surgical Intensive Medicine and Intermediate Care (G.M.), University Hospital Aachen, Pauwelsstrasse 30, 52064 Aachen, Germany; Physics of Molecular Imaging Systems, Experimental Molecular Imaging (T.H., V.S.), and Institute of Imaging and Computer Vision (J.S.), RWTH Aachen University, Aachen, Germany; Department of Inner Medicine, Luisenhospital Aachen, Aachen, Germany (L.N.); and Ocumeda AG, Erlen, Switzerland (C.H.).
  • Philipp Schad
    Department of Diagnostic and Interventional Radiology, RWTH Aachen University Hospital, Pauwelsstraße 30, 52072, Aachen, Germany.
  • Sebastian Keil
    Department of Diagnostic and Interventional Radiology, Aachen University Hospital, Pauwels Street 30, 52074, Aachen, Germany.
  • Emona Barzakova
    From the Department of Diagnostic and Interventional Radiology (F.K., G.M.F., L.H., P.S., S.K., E.B., M.S.H., F.P., M.Z., C.K., P.B., S.N., D.T.), Department of Medicine III (J.K., K.H.), and Clinic for Surgical Intensive Medicine and Intermediate Care (G.M.), University Hospital Aachen, Pauwelsstrasse 30, 52064 Aachen, Germany; Physics of Molecular Imaging Systems, Experimental Molecular Imaging (T.H., V.S.), and Institute of Imaging and Computer Vision (J.S.), RWTH Aachen University, Aachen, Germany; Department of Inner Medicine, Luisenhospital Aachen, Aachen, Germany (L.N.); and Ocumeda AG, Erlen, Switzerland (C.H.).
  • Maximilian Schulze-Hagen
    Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany.
  • Federico Pedersoli
    Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany.
  • Volkmar Schulz
    Physics of Molecular Imaging Systems, Experimental Molecular Imaging, RWTH Aachen University, Aachen, Germany. schulz@pmi.rwth-aachen.de.
  • Markus Zimmermann
    Klinik für Chirurgie, Universitätsklinikum Schleswig-Holstein, Campus Lübeck, Deutschland.
  • Lina Nebelung
    From the Department of Diagnostic and Interventional Radiology (F.K., G.M.F., L.H., P.S., S.K., E.B., M.S.H., F.P., M.Z., C.K., P.B., S.N., D.T.), Department of Medicine III (J.K., K.H.), and Clinic for Surgical Intensive Medicine and Intermediate Care (G.M.), University Hospital Aachen, Pauwelsstrasse 30, 52064 Aachen, Germany; Physics of Molecular Imaging Systems, Experimental Molecular Imaging (T.H., V.S.), and Institute of Imaging and Computer Vision (J.S.), RWTH Aachen University, Aachen, Germany; Department of Inner Medicine, Luisenhospital Aachen, Aachen, Germany (L.N.); and Ocumeda AG, Erlen, Switzerland (C.H.).
  • Jakob Kather
    From the Department of Diagnostic and Interventional Radiology (F.K., G.M.F., L.H., P.S., S.K., E.B., M.S.H., F.P., M.Z., C.K., P.B., S.N., D.T.), Department of Medicine III (J.K., K.H.), and Clinic for Surgical Intensive Medicine and Intermediate Care (G.M.), University Hospital Aachen, Pauwelsstrasse 30, 52064 Aachen, Germany; Physics of Molecular Imaging Systems, Experimental Molecular Imaging (T.H., V.S.), and Institute of Imaging and Computer Vision (J.S.), RWTH Aachen University, Aachen, Germany; Department of Inner Medicine, Luisenhospital Aachen, Aachen, Germany (L.N.); and Ocumeda AG, Erlen, Switzerland (C.H.).
  • Karim Hamesch
    From the Department of Diagnostic and Interventional Radiology (F.K., G.M.F., L.H., P.S., S.K., E.B., M.S.H., F.P., M.Z., C.K., P.B., S.N., D.T.), Department of Medicine III (J.K., K.H.), and Clinic for Surgical Intensive Medicine and Intermediate Care (G.M.), University Hospital Aachen, Pauwelsstrasse 30, 52064 Aachen, Germany; Physics of Molecular Imaging Systems, Experimental Molecular Imaging (T.H., V.S.), and Institute of Imaging and Computer Vision (J.S.), RWTH Aachen University, Aachen, Germany; Department of Inner Medicine, Luisenhospital Aachen, Aachen, Germany (L.N.); and Ocumeda AG, Erlen, Switzerland (C.H.).
  • Christoph Haarburger
    From the Departments of Diagnostic and Interventional Radiology (D.T., S.S., H.S., C.K.) and Institute of Imaging and Computer Vision (C.H., D.M.), RWTH Aachen University, Aachen, Pauwelsstr 30, 52074 Aachen, Germany.
  • Gernot Marx
    Department of Intensive Care and Intermediate Care, University Hospital RWTH Aachen, Aachen, Germany.
  • Johannes Stegmaier
    Institute for Applied Computer Science, Karlsruhe Institute of Technology, Eggenstein-Leopoldshafen, Germany.
  • Christiane Kuhl
    Department of Diagnostic and Interventional Radiology, University Hospital Düsseldorf, Düsseldorf, Germany (J.S., D.B.A., S.N.); Institute of Computer Vision and Imaging, RWTH University Aachen, Pauwelsstrasse 30, 52072 Aachen, Germany (J.S., D.M.); Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany (D.T., M.P., F.M., C.K., S.N.); and Faculty of Mathematics and Natural Sciences, Institute of Informatics, Heinrich Heine University Düsseldorf, Düsseldorf, Germany (S.C.).
  • Philipp Bruners
    Department of Diagnostic and Interventional Radiology, RWTH Aachen University Hospital, Pauwelsstraße 30, 52072, Aachen, Germany.
  • Sven Nebelung
    Department of Diagnostic and Interventional Radiology, University Hospital Düsseldorf, Düsseldorf, Germany (J.S., D.B.A., S.N.); Institute of Computer Vision and Imaging, RWTH University Aachen, Pauwelsstrasse 30, 52072 Aachen, Germany (J.S., D.M.); Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany (D.T., M.P., F.M., C.K., S.N.); and Faculty of Mathematics and Natural Sciences, Institute of Informatics, Heinrich Heine University Düsseldorf, Düsseldorf, Germany (S.C.).
  • Daniel Truhn
    Department of Diagnostic and Interventional Radiology, University Hospital Düsseldorf, Düsseldorf, Germany (J.S., D.B.A., S.N.); Institute of Computer Vision and Imaging, RWTH University Aachen, Pauwelsstrasse 30, 52072 Aachen, Germany (J.S., D.M.); Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany (D.T., M.P., F.M., C.K., S.N.); and Faculty of Mathematics and Natural Sciences, Institute of Informatics, Heinrich Heine University Düsseldorf, Düsseldorf, Germany (S.C.).

Keywords

External Resources

Popular Topics
Recent Journals