A Fully Automated Artificial Intelligence System to Assist Pathologists' Diagnosis to Predict Histologically High-grade Urothelial Carcinoma from Digitized Urine Cytology Slides Using Deep Learning.

Journal: European urology oncology
PMID: 38065702

Abstract

BACKGROUND: Urine cytology, although a useful screening method for urothelial carcinoma, lacks sensitivity. As an emerging technology, artificial intelligence (AI) improved image analysis accuracy significantly.

Authors

  • Keisuke Tsuji
    Department of Urology, Kyoto Prefectural University of Medicine, Kyoto, Japan.
  • Masatomo Kaneko
    Department of Urology, Kyoto Prefectural University of Medicine, Kyoto, Japan.
  • Yuki Harada
    Department of Urology, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan.
  • Atsuko Fujihara
    Department of Urology, Kyoto Prefectural University of Medicine, Kyoto, Japan.
  • Kengo Ueno
    Corporate R&D Department, KYOCERA Communication Systems Co., Ltd, Kyoto, Japan.
  • Masaya Nakanishi
    KYOCERA Communication Systems Co., Ltd, 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.
  • Go Horiguchi
    Department of Biostatistics, Kyoto Prefectural University of Medicine, Kyoto, Japan.
  • Satoshi Teramukai
    Department of Biostatistics, Kyoto Prefectural University of Medicine, Kyoto, Japan.
  • Toshiko Ito-Ihara
    Department of Clinical and Translational Research Center, Kyoto Prefectural University of Medicine, Kyoto, Japan.
  • Osamu Ukimura
    USC Institute of Urology, Los Angeles, CA, USA.

Keywords

External Resources

Popular Topics
Recent Journals