Dynamic contrast-enhanced computed tomography diagnosis of primary liver cancers using transfer learning of pretrained convolutional neural networks: Is registration of multiphasic images necessary?

Journal: International journal of computer assisted radiology and surgery
Published Date: May 3, 2019

Abstract

PURPOSE: To evaluate the effect of image registration on the diagnostic performance of transfer learning (TL) using pretrained convolutional neural networks (CNNs) and three-phasic dynamic contrast-enhanced computed tomography (DCE-CT) for primary liver cancers.

Authors

  • Akira Yamada
    Department of Radiology, Shinshu University School of Medicine, Japan.
  • Kazuki Oyama
    Department of Radiology, Shinshu University School of Medicine, 3-1-1 Asahi, Matsumoto, Nagano, 390-8621, Japan.
  • Sachie Fujita
    Department of Radiology, Shinshu University School of Medicine, 3-1-1 Asahi, Matsumoto, Nagano, 390-8621, Japan.
  • Eriko Yoshizawa
    Department of Radiology, Shinshu University School of Medicine, 3-1-1 Asahi, Matsumoto, Nagano, 390-8621, Japan.
  • Fumihito Ichinohe
    Department of Radiology, Shinshu University School of Medicine, Matsumoto, Japan.
  • Daisuke Komatsu
    Department of Radiology, Shinshu University School of Medicine, 3-1-1 Asahi, Matsumoto, Nagano, 390-8621, Japan.
  • Yasunari Fujinaga
    Department of Radiology, Shinshu University School of Medicine, Matsumoto, Japan.

Keywords

External Resources

Popular Topics
Recent Journals