Domain transformation using semi-supervised CycleGAN for improving performance of classifying thyroid tissue images.

Journal: International journal of computer assisted radiology and surgery
Published Date:

Abstract

PURPOSE: A large number of research has been conducted on the classification of medical images using deep learning. The thyroid tissue images can be also classified by cancer types. Deep learning requires a large amount of data, but every medical institution cannot collect sufficient number of data for deep learning. In that case, we can consider a case where a classifier trained at a certain medical institution that has a sufficient number of data is reused at other institutions. However, when using data from multiple institutions, it is necessary to unify the feature distribution because the feature of the data differs due to differences in data acquisition conditions.

Authors

  • Yoshihito Ichiuji
    Graduate School of Sciences and Technology for Innovation, Yamaguchi University, Yamaguchi, Japan.
  • Shingo Mabu
    Graduate School of Science and Engineering, Yamaguchi University, Tokiwadai 2-16-1, Ube, Yamaguchi, 755-8611, Japan. mabu@yamaguchi-u.ac.jp.
  • Satomi Hatta
    Division of Molecular Pathology, Department of Pathological Sciences, University of Fukui, 23-3 Matsuoka-Shimoaizuki, Eiheiji, Fukui, 910-1193, Japan.
  • Kunihiro Inai
    Division of Molecular Pathology, Department of Pathological Sciences, University of Fukui, 23-3 Matsuoka-Shimoaizuki, Eiheiji, Fukui, 910-1193, Japan. kinai@u-fukui.ac.jp.
  • Shohei Higuchi
    Division of Molecular Pathology, Department of Pathological Sciences, University of Fukui, 23-3, Matsuoka-shimoaizuki, Eiheiji-cho, Yoshida-gun, Fukui, 910-1193, Japan.
  • Shoji Kido
    Graduate School of Medicine, Yamaguchi University, Tokiwadai 2-16-1, Ube, Yamaguchi, 755-8611, Japan.