What Does Deep Learning See? Insights From a Classifier Trained to Predict Contrast Enhancement Phase From CT Images.

Journal: AJR. American journal of roentgenology
Published Date: Nov 7, 2018

Abstract

OBJECTIVE: Deep learning has shown great promise for improving medical image classification tasks. However, knowing what aspects of an image the deep learning system uses or, in a manner of speaking, sees to make its prediction is difficult.

Authors

  • Kenneth A Philbrick
    1 Department of Radiology, Radiology Informatics Laboratory, Mayo Clinic, 3507 17th Ave NW, Rochester, MN 55901.
  • Kotaro Yoshida
    1 Department of Radiology, Radiology Informatics Laboratory, Mayo Clinic, 3507 17th Ave NW, Rochester, MN 55901.
  • Dai Inoue
    1 Department of Radiology, Radiology Informatics Laboratory, Mayo Clinic, 3507 17th Ave NW, Rochester, MN 55901.
  • Zeynettin Akkus
    From the Department of Radiology, Mayo Clinic, 200 First St SW, Rochester, MN 55905.
  • Timothy L Kline
    Department of Radiology, Mayo Clinic, Rochester, Minn.
  • Alexander D Weston
    Radiology Informatics Laboratory, Department of Radiology, Mayo Clinic, Rochester, Minnesota.
  • Panagiotis Korfiatis
    From the Department of Radiology, Mayo Clinic, 200 First St SW, Rochester, MN 55905.
  • Naoki Takahashi
    1 Department of Radiology, Radiology Informatics Laboratory, Mayo Clinic, 3507 17th Ave NW, Rochester, MN 55901.
  • Bradley J Erickson
    Department of Radiology, Radiology Informatics Lab, Mayo Clinic, Rochester, MN 55905, United States.

Keywords

External Resources

Popular Topics
Recent Journals