Development and validation of a supervised deep learning algorithm for automated whole-slide programmed death-ligand 1 tumour proportion score assessment in non-small cell lung cancer.

Journal: Histopathology
Published Date: Nov 16, 2021

Abstract

AIMS: Immunohistochemical programmed death-ligand 1 (PD-L1) staining to predict responsiveness to immunotherapy in patients with advanced non-small cell lung cancer (NSCLC) has several drawbacks: a robust gold standard is lacking, and there is substantial interobserver and intraobserver variance, with up to 20% discordance around cutoff points. The aim of this study was to develop a new deep learning-based PD-L1 tumour proportion score (TPS) algorithm, trained and validated on a routine diagnostic dataset of digitised PD-L1 (22C3, laboratory-developed test)-stained samples.

Authors

  • Liesbeth M Hondelink
    Department of Pathology, Leiden University Medical Centre, Leiden, The Netherlands.
  • Melek Hüyük
    Department of Pulmonology, Leiden University Medical Centre, Leiden, The Netherlands.
  • Pieter E Postmus
    Department of Pulmonology, Leiden University Medical Centre, Leiden, The Netherlands.
  • Vincent T H B M Smit
    Department of Pathology, Leiden University Medical Centre, Leiden, The Netherlands.
  • Sami Blom
    Biomedicum, Fimmic Oy, Helsinki, Finland.
  • Jan H von der Thüsen
    Department of Pathology and Clinical Bioinformatics, Erasmus University Medical Center, Rotterdam, The Netherlands. Electronic address: j.vonderthusen@erasmusmc.nl.
  • Danielle Cohen
    Department of Pathology, Leiden University Medical Centre, Leiden, The Netherlands.

Keywords

External Resources

Popular Topics
Recent Journals