Stroma and lymphocytes identified by deep learning are independent predictors for survival in pancreatic cancer

X Xiuxiang Tan M Mika Rosin S Simone Appinger J Julia Campello Deierl K Konrad Reichel M Mariëlle Coolsen L Liselot Valkenburg-van Iersel J Judith de Vos-Geelen E Evelien J. M. de Jong J Jan Bednarsch B Bas Grootkoerkamp M Michail Doukas C Casper van Eijck T Tom Luedde E Edgar Dahl J Jakob Nikolas Kather S Shivan Sivakumar (Department of Immunology and Immunotherapy, School of Infection, Inflammation, and Immunology, College of Medicine and Health, University of Birmingham, Birmingham, United Kingdom) W Wolfram Trudo Knoefel G Georg Wiltberger U Ulf Peter Neumann (From Bielefeld University, Medical School and University Medical Center Ostwestfalen-Lippe, Campus Hospital Lippe, Detmold, Germany (J.H.); the Department of Radiation Oncology, Medical University of Graz, Graz, Austria (T.B.); the Clinical Trials Unit, Faculty of Medicine and Medical Center, University of Freiburg, Freiburg, Germany (C.S.); the Institute of Surgical Pathology, University Medical Center Freiburg, Germany (P.B.); the Department of Surgery, University Medical Center Schleswig-Holstein–Campus Lübeck, Lübeck, Germany (B.K., T.K.); Comprehensive Cancer Center Augsburg, Faculty of Medicine, University of Augsburg, Augsburg, Germany (R.C.); the Department of General and Visceral Surgery, University Medical Center Freiburg, Freiburg, Germany (S.U.); the Department of General, Visceral, and Thoracic Surgery, University Medical Center Hamburg–Eppendorf, Hamburg, Germany (J.R.I.); the Department of Gastrointestinal Surgery, IRCCS San Raffaele Scientific Institute and San Raffaele Vita-Salute Universi...) L Lara R. Heij

Abstract

Abstract Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancers known to humans. However, not all patients fare equally poor survival, and a minority of patients even survives advanced disease for months or years. Thus, there is a clinical need to search corresponding prognostic biomarkers which forecast survival on an individual basis. To dig more information and identify potential biomarkers from PDAC pathological slides, we trained a deep learning (DL) model based U-net-shaped backbone. This DL model can automatically detect tumor, stroma and lymphocytes on whole slide images (WSIs) of PDAC patients. We performed an analysis of 800 PDAC scans, categorizing stroma in percentage (SIP) and lymphocytes in percentage (LIP) into two and three categories, respectively. The presented model achieved remarkable accuracy results with a total accuracy of 94.72%, a mean intersection of union rate of 78.66%, and a mean dice coefficient of 87.74%. Survival analysis revealed that SIP-mediate and LIP-high groups correlated with enhanced median overall survival (OS) across all cohorts. These findings underscore the potential of SIP and LIP as prognostic biomarkers for PDAC and highlight the utility of DL as a tool for PDAC biomarkers detecting on WSIs.

Article Details

Volume / Issue Vol. 15, Issue 1
Published March 19, 2025
ISSN 2045-2322
Publisher Nature Portfolio

Journal Info

Scientific Reports

Nature Portfolio

ISSN: 2045-2322 Open Access Life Sciences

Authors (21)

X

Xiuxiang Tan

M

Mika Rosin

S

Simone Appinger

J

Julia Campello Deierl

K

Konrad Reichel

M

Mariëlle Coolsen

L

Liselot Valkenburg-van Iersel

J

Judith de Vos-Geelen

E

Evelien J. M. de Jong

J

Jan Bednarsch

B

Bas Grootkoerkamp

M

Michail Doukas

C

Casper van Eijck

T

Tom Luedde

E

Edgar Dahl

J

Jakob Nikolas Kather

S

Shivan Sivakumar

Department of Immunology and Immunotherapy, School of Infection, Inflammation, and Immunology, College of Medicine and Health, University of Birmingham, Birmingham, United Kingdom

W

Wolfram Trudo Knoefel

G

Georg Wiltberger

U

Ulf Peter Neumann

From Bielefeld University, Medical School and University Medical Center Ostwestfalen-Lippe, Campus Hospital Lippe, Detmold, Germany (J.H.); the Department of Radiation Oncology, Medical University of Graz, Graz, Austria (T.B.); the Clinical Trials Unit, Faculty of Medicine and Medical Center, University of Freiburg, Freiburg, Germany (C.S.); the Institute of Surgical Pathology, University Medical Center Freiburg, Germany (P.B.); the Department of Surgery, University Medical Center Schleswig-Holstein–Campus Lübeck, Lübeck, Germany (B.K., T.K.); Comprehensive Cancer Center Augsburg, Faculty of Medicine, University of Augsburg, Augsburg, Germany (R.C.); the Department of General and Visceral Surgery, University Medical Center Freiburg, Freiburg, Germany (S.U.); the Department of General, Visceral, and Thoracic Surgery, University Medical Center Hamburg–Eppendorf, Hamburg, Germany (J.R.I.); the Department of Gastrointestinal Surgery, IRCCS San Raffaele Scientific Institute and San Raffaele Vita-Salute Universi...

L

Lara R. Heij