AI approach of cycle-consistent generative adversarial networks to synthesize PET images to train computer-aided diagnosis algorithm for dementia.

Journal: Annals of nuclear medicine
Published Date: Apr 20, 2020

Abstract

OBJECTIVE: An artificial intelligence (AI)-based algorithm typically requires a considerable amount of training data; however, few training images are available for dementia with Lewy bodies and frontotemporal lobar degeneration. Therefore, this study aims to present the potential of cycle-consistent generative adversarial networks (CycleGAN) to obtain enough number of training images for AI-based computer-aided diagnosis (CAD) algorithms for diagnosing dementia.

Authors

  • Yuichi Kimura
    Graduate School of Biology-Oriented Science and Technology, Kindai University, Wakayama, Japan. ukimura@ieee.org.
  • Aya Watanabe
    Graduate School of Biology-Oriented Science and Technology, Kindai University, Wakayama, Japan.
  • Takahiro Yamada
    Division of Positron Emission Tomography, Institute of Advanced Clinical Medicine, Kindai University, Osaka, Japan.
  • Shogo Watanabe
    Department of Human Health Sciences, Graduate School of Medicine, Kyoto University, Kyoto, Japan.
  • Takashi Nagaoka
    Graduate School of Biology-Oriented Science and Technology, Kindai University, Wakayama, Japan.
  • Mitsutaka Nemoto
    The University of Tokyo Hospital.
  • Koichi Miyazaki
    Department of Radiology, Faculty of Medicine, Kindai University, Osaka, Japan.
  • Kohei Hanaoka
    Division of Positron Emission Tomography, Institute of Advanced Clinical Medicine, Kindai University, Osaka, Japan.
  • Hayato Kaida
    Division of Positron Emission Tomography, Institute of Advanced Clinical Medicine, Kindai University, Osaka, Japan.
  • Kazunari Ishii
    Division of Positron Emission Tomography, Institute of Advanced Clinical Medicine, Kindai University, Osaka, Japan.

Keywords

External Resources

Popular Topics
Recent Journals