Self-Supervised Learning for Feature Extraction from Glomerular Images and Disease Classification with Minimal Annotations.

Journal: Journal of the American Society of Nephrology : JASN
PMID: 40029749

Abstract

BACKGROUND: Deep learning has great potential in digital kidney pathology. However, its effectiveness depends heavily on the availability of extensively labeled datasets, which are often limited because of the specialized knowledge and time required for their creation. This limitation hinders the widespread application of deep learning for the analysis of kidney biopsy images.

Authors

  • Masatoshi Abe
    Department of Pathology, Osaka University Graduate School of Medicine, Osaka, Japan.
  • Hirohiko Niioka
    Graduate School of Engineering Science, Osaka University, 1-3 Machikane-Yama, Toyonaka, Osaka, 560-8531, Japan.
  • Ayumi Matsumoto
    Department of Nephrology, Graduate School of Medicine, Osaka University, Osaka, Japan.
  • Yusuke Katsuma
    Department of Nephrology, Graduate School of Medicine, Osaka University, Osaka, Japan.
  • Atsuhiro Imai
    Department of Nephrology, Graduate School of Medicine, Osaka University, Osaka, Japan.
  • Hiroki Okushima
    Department of Nephrology, Graduate School of Medicine, Osaka University, Osaka, Japan.
  • Shingo Ozaki
    Department of Nephrology, Hyogo Prefectural Nishinomiya Hospital, Nishinomiya, Japan.
  • Naohiko Fujii
    Department of Nephrology, Hyogo Prefectural Nishinomiya Hospital, Nishinomiya, Japan.
  • Kazumasa Oka
    Department of Pathology, Hyogo Prefectural Nishinomiya Hospital, Nishinomiya, Japan.
  • Yusuke Sakaguchi
    Department of Inter-Organ Communication Research in Kidney Diseases, Osaka University Graduate School of Medicine, Suita, Japan.
  • Kazunori Inoue
    Department of Nephrology, Graduate School of Medicine, Osaka University, Osaka, Japan.
  • Yoshitaka Isaka
    Department of Nephrology, Osaka University Graduate School of Medicine, Suita, Japan.
  • Isao Matsui
    Department of Nephrology, Graduate School of Medicine, Osaka University, Osaka, Japan.

Keywords

External Resources

Popular Topics
Recent Journals