Accuracy and efficiency of an artificial intelligence tool when counting breast mitoses.

Journal: Diagnostic pathology
PMID: 32622359

Abstract

BACKGROUND: The mitotic count in breast carcinoma is an important prognostic marker. Unfortunately substantial inter- and intra-laboratory variation exists when pathologists manually count mitotic figures. Artificial intelligence (AI) coupled with whole slide imaging offers a potential solution to this problem. The aim of this study was to accordingly critique an AI tool developed to quantify mitotic figures in whole slide images of invasive breast ductal carcinoma.

Authors

  • Liron Pantanowitz
    Department of Pathology, University of Michigan, Ann Arbor, MI, USA.
  • Douglas Hartman
    Department of Pathology, University of Pittsburgh Medical Center Cancer Pavilion, Suite 201, 5150 Centre Ave, Pittsburgh, PA, 15232, USA.
  • Yan Qi
    School of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania.
  • Eun Yoon Cho
    Department of Pathology, Samsung Medical Center, Seoul, South Korea.
  • Beomseok Suh
    Lunit, Seoul, South Korea.
  • Kyunghyun Paeng
    Lunit Inc., Seoul, South Korea.
  • Rajiv Dhir
    Department of Pathology, University of Pittsburgh Medical Center Cancer Pavilion, Suite 201, 5150 Centre Ave, Pittsburgh, PA, 15232, USA.
  • Pamela Michelow
    Cytology Unit, Department of Anatomical Pathology, Faculty of Health Science, National Health Laboratory Service, University of the Witwatersrand, Johannesburg, South Africa.
  • Scott Hazelhurst
    School of Electrical & Information Engineering and Sydney Brenner Institute for Molecular Bioscience, University of the Witwatersrand, Johannesburg, South Africa.
  • Sang Yong Song
    Department of Pathology, Samsung Medical Center, Seoul, South Korea.
  • Soo Youn Cho
    Department of Pathology, Samsung Medical Center, Seoul, South Korea.

Keywords

External Resources

Popular Topics
Recent Journals