Deep Learning to Classify Radiology Free-Text Reports.

Journal: Radiology
Published Date: Nov 13, 2017

Abstract

Purpose To evaluate the performance of a deep learning convolutional neural network (CNN) model compared with a traditional natural language processing (NLP) model in extracting pulmonary embolism (PE) findings from thoracic computed tomography (CT) reports from two institutions. Materials and Methods Contrast material-enhanced CT examinations of the chest performed between January 1, 1998, and January 1, 2016, were selected. Annotations by two human radiologists were made for three categories: the presence, chronicity, and location of PE. Classification of performance of a CNN model with an unsupervised learning algorithm for obtaining vector representations of words was compared with the open-source application PeFinder. Sensitivity, specificity, accuracy, and F1 scores for both the CNN model and PeFinder in the internal and external validation sets were determined. Results The CNN model demonstrated an accuracy of 99% and an area under the curve value of 0.97. For internal validation report data, the CNN model had a statistically significant larger F1 score (0.938) than did PeFinder (0.867) when classifying findings as either PE positive or PE negative, but no significant difference in sensitivity, specificity, or accuracy was found. For external validation report data, no statistical difference between the performance of the CNN model and PeFinder was found. Conclusion A deep learning CNN model can classify radiology free-text reports with accuracy equivalent to or beyond that of an existing traditional NLP model. RSNA, 2017 Online supplemental material is available for this article.

Authors

  • Matthew C Chen
    Department of Radiology, Stanford University, Stanford, CA, United States. Electronic address: rubin@stanford.edu.
  • Robyn L Ball
    From the Department of Radiology, Stanford University School of Medicine, Stanford University Medical Center, 725 Welch Rd, Room 1675, Stanford, Calif 94305-5913 (M.C.C., N.M., D.B.L., C.P.L., M.P.L.); Stanford Center for Biomedical Informatics Research, Stanford University, Stanford, Calif (R.L.B., L.Y.); Department of Bioinformatics, University of Utah Medical Center, Salt Lake City, Utah (B.E.C.); and Department of Radiology, Duke University Medical Center, Durham, NC (T.J.A.).
  • Lingyao Yang
    From the Department of Radiology, Stanford University School of Medicine, Stanford University Medical Center, 725 Welch Rd, Room 1675, Stanford, Calif 94305-5913 (M.C.C., N.M., D.B.L., C.P.L., M.P.L.); Stanford Center for Biomedical Informatics Research, Stanford University, Stanford, Calif (R.L.B., L.Y.); Department of Bioinformatics, University of Utah Medical Center, Salt Lake City, Utah (B.E.C.); and Department of Radiology, Duke University Medical Center, Durham, NC (T.J.A.).
  • Nathaniel Moradzadeh
    From the Department of Radiology, Stanford University School of Medicine, Stanford University Medical Center, 725 Welch Rd, Room 1675, Stanford, Calif 94305-5913 (M.C.C., N.M., D.B.L., C.P.L., M.P.L.); Stanford Center for Biomedical Informatics Research, Stanford University, Stanford, Calif (R.L.B., L.Y.); Department of Bioinformatics, University of Utah Medical Center, Salt Lake City, Utah (B.E.C.); and Department of Radiology, Duke University Medical Center, Durham, NC (T.J.A.).
  • Brian E Chapman
    University of Utah, Department of Radiology, 729 Arapeen Drive, Salt Lake City, UT 84108, United States. Electronic address: brian.chapman@utah.edu.
  • David B Larson
    Department of Radiology, Warren Alpert Medical School, Brown University, 593 Eddy St, Providence, RI 02903 (I.P.); Department of Diagnostic Imaging, Rhode Island Hospital, Providence, RI (I.P.); Visiana, Hørsholm, Denmark (H.H.T.); Department of Radiology, Stanford University, Palo Alto, Calif (S.S.H., D.B.L.); and Department of Radiology, Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School, Boston, Mass (J.K.C.).
  • Curtis P Langlotz
    Stanford University, University Medical Line, Stanford, CA, 94305, US.
  • Timothy J Amrhein
    3 Department of Radiology, Duke University Medical Center, Durham, NC.
  • Matthew P Lungren

Keywords

External Resources

Popular Topics
Recent Journals