Staining, magnification, and algorithmic conditions for highly accurate cell detection and cell classification by deep learning.

Journal: American journal of clinical pathology
PMID: 38134350

Abstract

OBJECTIVES: Research into cytodiagnosis has seen an active exploration of cell detection and classification using deep learning models. We aimed to clarify the challenges of magnification, staining methods, and false positives in creating general purpose deep learning-based cytology models.

Authors

  • Katsuhide Ikeda
    Pathophysiology Sciences, Department of Integrated Health Sciences, Nagoya University Graduate School of Medicine, Nagoya, Japan.
  • Nanako Sakabe
    Pathophysiology Sciences, Department of Integrated Health Sciences, Nagoya University Graduate School of Medicine, Nagoya, Japan.
  • Chihiro Ito
    Pathophysiology Sciences, Department of Integrated Health Sciences, Nagoya University Graduate School of Medicine, Nagoya, Japan.
  • Yuka Shimoyama
    Pathophysiology Sciences, Department of Integrated Health Sciences, Nagoya University Graduate School of Medicine, Nagoya, Japan.
  • Kenta Toda
    Pathophysiology Sciences, Department of Integrated Health Sciences, Nagoya University Graduate School of Medicine, Nagoya, Japan.
  • Kenta Fukuda
    Pathophysiology Sciences, Department of Integrated Health Sciences, Nagoya University Graduate School of Medicine, Nagoya, Japan.
  • Yuma Yoshizaki
    Pathophysiology Sciences, Department of Integrated Health Sciences, Nagoya University Graduate School of Medicine, Nagoya, Japan.
  • Shouichi Sato
    Clinical Engineering, Faculty of Medical Sciences, Juntendo University, Urayasu, Japan.
  • Kohzo Nagata
    Pathophysiology Sciences, Department of Integrated Health Sciences, Nagoya University Graduate School of Medicine, Nagoya, Japan.

Keywords

External Resources

Popular Topics
Recent Journals