Comparative effectiveness of convolutional neural network (CNN) and recurrent neural network (RNN) architectures for radiology text report classification.

Journal: Artificial intelligence in medicine
Published Date: Nov 23, 2018

Abstract

This paper explores cutting-edge deep learning methods for information extraction from medical imaging free text reports at a multi-institutional scale and compares them to the state-of-the-art domain-specific rule-based system - PEFinder and traditional machine learning methods - SVM and Adaboost. We proposed two distinct deep learning models - (i) CNN Word - Glove, and (ii) Domain phrase attention-based hierarchical recurrent neural network (DPA-HNN), for synthesizing information on pulmonary emboli (PE) from over 7370 clinical thoracic computed tomography (CT) free-text radiology reports collected from four major healthcare centers. Our proposed DPA-HNN model encodes domain-dependent phrases into an attention mechanism and represents a radiology report through a hierarchical RNN structure composed of word-level, sentence-level and document-level representations. Experimental results suggest that the performance of the deep learning models that are trained on a single institutional dataset, are better than rule-based PEFinder on our multi-institutional test sets. The best F1 score for the presence of PE in an adult patient population was 0.99 (DPA-HNN) and for a pediatrics population was 0.99 (HNN) which shows that the deep learning models being trained on adult data, demonstrated generalizability to pediatrics population with comparable accuracy. Our work suggests feasibility of broader usage of neural network models in automated classification of multi-institutional imaging text reports for a variety of applications including evaluation of imaging utilization, imaging yield, clinical decision support tools, and as part of automated classification of large corpus for medical imaging deep learning work.

Authors

  • Imon Banerjee
    Mayo Clinic, Department of Radiology, Scottsdale, AZ, USA.
  • Yuan Ling
  • Matthew C Chen
    Department of Radiology, Stanford University, Stanford, CA, United States. Electronic address: rubin@stanford.edu.
  • Sadid A Hasan
    Philips Research North America, New York, United States.
  • Curtis P Langlotz
    Stanford University, University Medical Line, Stanford, CA, 94305, US.
  • 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 Chapman
    Department of Bioinformatics, University of Utah Medical Center, UT, USA.
  • Timothy Amrhein
    Department of Neuroradiology, Duke University School of Medicine, NC, USA.
  • David Mong
    Department of Radiology, Children Hospital Colorado, CO, USA.
  • Daniel L Rubin
    Department of Biomedical Data Science, Stanford University School of Medicine Medical School Office Building, Stanford CA 94305-5479.
  • Oladimeji Farri
    Philips Research North America, New York, United States.
  • Matthew P Lungren

Keywords

External Resources

Popular Topics
Recent Journals