Deep-learning-based classification of desmoplastic reaction on H&E predicts poor prognosis in oesophageal squamous cell carcinoma.

Journal: Histopathology
Published Date:

Abstract

AIMS: Desmoplastic reaction (DR) categorisation has been shown to be a promising prognostic factor in oesophageal squamous cell carcinoma (ESCC). The usual DR evaluation is performed using semiquantitative scores, which can be subjective. This study aimed to investigate whether a deep-learning classifier could be used for DR classification. We further assessed the prognostic significance of the deep-learning classifier and compared it to that of manual DR reporting and other pathological factors currently used in the clinic.

Authors

  • Keita Kouzu
    Department of Surgery, National Defense Medical College, Saitama, Japan.
  • Ines P Nearchou
    School of Medicine, University of St Andrews, North Haugh, St Andrews, Fife, KY16 9TF, UK.
  • Yoshiki Kajiwara
    Department of Surgery, National Defense Medical College, Saitama, Japan.
  • Hironori Tsujimoto
    Department of Surgery, National Defense Medical College, Tokorozawa, Japan.
  • Kate Lillard
    Indica Labs, Corrales, New Mexico, USA.
  • Yoji Kishi
    Department of Surgery, National Defense Medical College, Saitama, Japan.
  • Hideki Ueno
    Department of Surgery, National Defense Medical College, Saitama, Japan.