Deep learning quantification of percent steatosis in donor liver biopsy frozen sections.

Journal: EBioMedicine
Published Date:

Abstract

BACKGROUND: Pathologist evaluation of donor liver biopsies provides information for accepting or discarding potential donor livers. Due to the urgent nature of the decision process, this is regularly performed using frozen sectioning at the time of biopsy. The percent steatosis in a donor liver biopsy correlates with transplant outcome, however there is significant inter- and intra-observer variability in quantifying steatosis, compounded by frozen section artifact. We hypothesized that a deep learning model could identify and quantify steatosis in donor liver biopsies.

Authors

  • Lulu Sun
    Department of Pathology and Immunology, Washington University School of Medicine, St. Louis, MO, United States.
  • Jon N Marsh
  • Matthew K Matlock
  • Ling Chen
    Division of Biostatistics, Washington University School of Medicine, St. Louis, MO, United States.
  • Joseph P Gaut
  • Elizabeth M Brunt
    Department of Pathology and Immunology, Washington University School of Medicine, St. Louis, MO, United States.
  • S Joshua Swamidass
    Department of Computer Science and Engineering, McKelvey School of Engineering, Washington University in St. Louis, St. Louis, Missouri.
  • Ta-Chiang Liu