Effect of augmented datasets on deep convolutional neural networks applied to chest radiographs.

Journal: Clinical radiology
Published Date: Jun 10, 2019

Abstract

AIM: To evaluate the effect of augmented training datasets in a deep convolutional neural network (DCNN) used for detecting abnormal chest radiographs.

Authors

  • R Ogawa
    Department of Radiology, Saiseikai Matsuyama Hospital, 880-2, Yamanishicho, Matsuyama-shi, Ehime, 791-8026, Japan. Electronic address: qq8y7cvd@tiara.ocn.ne.jp.
  • T Kido
    Department of Radiology, Ehime University Graduate School of Medicine Shitsukawa, Toon-city, Ehime 791-0295, Japan.
  • T Mochizuki
    Department of Radiology, Ehime University Graduate School of Medicine Shitsukawa, Toon-city, Ehime 791-0295, Japan.

Keywords

External Resources

Popular Topics
Recent Journals