A Fundamental Study Assessing the Diagnostic Performance of Deep Learning for a Brain Metastasis Detection Task.

Journal: Magnetic resonance in medical sciences : MRMS : an official journal of Japan Society of Magnetic Resonance in Medicine
Published Date: Jul 26, 2019

Abstract

PURPOSE: Increased use of deep convolutional neural networks (DCNNs) in medical imaging diagnosis requires determinate evaluation of diagnostic performance. We performed the fundamental investigation of diagnostic performance of DCNNs using the detection task of brain metastasis.

Authors

  • Tomoyuki Noguchi
    Department of Radiology, National Center for Global Health and Medicine, 1-21-1 Toyama, Shinjuku-ku, Tokyo, 162-8655, Japan. tnogucci@radiol.med.kyushu-u.ac.jp.
  • Fumiya Uchiyama
    Department of Radiology, National Center for Global Health and Medicine, 1-21-1 Toyama, Shinjuku-ku, Tokyo, 162-8655, Japan.
  • Yusuke Kawata
    Department of Radiology, National Center for Global Health and Medicine, 1-21-1 Toyama, Shinjuku-ku, Tokyo, 162-8655, Japan.
  • Akihiro Machitori
    Department of Radiology, National Center for Global Health and Medicine, 1-21-1 Toyama, Shinjuku-ku, Tokyo, 162-8655, Japan.
  • Yoshitaka Shida
    Department of Radiology, National Center for Global Health and Medicine, 1-21-1 Toyama, Shinjuku-ku, Tokyo, 162-8655, Japan.
  • Takashi Okafuji
    Department of Radiology, National Center for Global Health and Medicine, 1-21-1 Toyama, Shinjuku-ku, Tokyo, 162-8655, Japan.
  • Kota Yokoyama
    Department of Radiology, National Center for Global Health and Medicine, 1-21-1 Toyama, Shinjuku-ku, Tokyo, 162-8655, Japan.
  • Yosuke Inaba
    Biostatistics Section, Department of Data Science, Center for Clinical Sciences, National Center for Global Health and Medicine.
  • Tsuyoshi Tajima
    Department of Radiology, National Center for Global Health and Medicine, 1-21-1 Toyama, Shinjuku-ku, Tokyo, 162-8655, Japan.

Keywords

External Resources

Popular Topics
Recent Journals