Urine cell image recognition using a deep-learning model for an automated slide evaluation system.

Journal: BJU international
Published Date: Jul 5, 2021

Abstract

OBJECTIVES: To develop a classification system for urine cytology with artificial intelligence (AI) using a convolutional neural network algorithm that classifies urine cell images as negative (benign) or positive (atypical or malignant).

Authors

  • Masatomo Kaneko
    Department of Urology, Kyoto Prefectural University of Medicine, Kyoto, Japan.
  • Keisuke Tsuji
    Department of Urology, Kyoto Prefectural University of Medicine, Kyoto, Japan.
  • Keiichi Masuda
    Corporate R&D Department, KYOCERA Communication Systems Co., Ltd, Kyoto, Japan.
  • Kengo Ueno
    Corporate R&D Department, KYOCERA Communication Systems Co., Ltd, Kyoto, Japan.
  • Kohei Henmi
    Corporate R&D Department, KYOCERA Communication Systems Co., Ltd, Kyoto, Japan.
  • Shota Nakagawa
    Rist, Inc., Impact HUB Tokyo, 2-11-3 Meguro, Meguro-ku, Tokyo, 153-0063, Japan.
  • Ryo Fujita
    AI Research Center, Rist Inc, Kyoto, Japan.
  • Kensho Suzuki
    AI Research Center, Rist Inc, Kyoto, Japan.
  • Yuichi Inoue
    Institute of Neuropsychiatry, 91, Bentencho, Shinjuku-ku, Tokyo, 162-0851, Japan.
  • Satoshi Teramukai
    Department of Biostatistics, Kyoto Prefectural University of Medicine, Kyoto, Japan.
  • Eiichi Konishi
    Department of Surgical Pathology, Kyoto Prefectural University of Medicine, 465 Kajiicho, Kawaramachi-Hirokoji, Kamigyo-ku, Kyoto, 6028566, Japan.
  • Tetsuro Takamatsu
    Department of Pathology and Cell Regulation, Kyoto Prefectural University of Medicine, 465 Kajiicho, Kawaramachi-Hirokoji, Kamigyo-ku, Kyoto, 6028566, Japan. ttakam@koto.kpu-m.ac.jp.
  • Osamu Ukimura
    USC Institute of Urology, Los Angeles, CA, USA.

Keywords

External Resources

Popular Topics
Recent Journals