Stroma and lymphocytes identified by deep learning are independent predictors for survival in pancreatic cancer
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.
Authors
- Konrad Reichel (ORCID: https://orcid.org/0009-0001-0506-5511)
- Casper W.F. van Eijck (ORCID: https://orcid.org/0000-0002-1461-6725)
- Tom Luedde (ORCID: https://orcid.org/0000-0002-6288-8821)
- Lara R. Heij (ORCID: https://orcid.org/0000-0002-0602-3356)
- Liselot Valkenburg‐van Iersel (ORCID: https://orcid.org/0000-0003-2925-9908)
- Bas Groot Koerkamp (ORCID: https://orcid.org/0000-0003-1917-6973)
- Judith de Vos‐Geelen (ORCID: https://orcid.org/0000-0003-2578-1766)
- Edgar Dahl (ORCID: https://orcid.org/0000-0002-8439-7994)
- Mika Rosin
- Georg Wiltberger (ORCID: https://orcid.org/0000-0003-2384-3847)
- Evelien J.M. de Jong (ORCID: https://orcid.org/0000-0002-8590-2518)
- Shivan Sivakumar (ORCID: https://orcid.org/0000-0002-5175-2697)
- Jan Bednarsch (ORCID: https://orcid.org/0000-0001-8143-6452)
- Simone Appinger
- Jakob Nikolas Kather (ORCID: https://orcid.org/0000-0002-3730-5348)
- Xiuxiang Tan (ORCID: https://orcid.org/0000-0001-6782-9137)
- Julia Campello Deierl
- Ulf Neumann (ORCID: https://orcid.org/0000-0001-6680-9177)
- Michail Doukas (ORCID: https://orcid.org/0000-0002-8611-840X)
- Wolfram Trudo Knoefel
- Mariëlle Coolsen
Institutions
- Shanghai Jiao Tong University (CN)
- Erasmus MC (NL)
- Maastricht University (NL)
- Düsseldorf University Hospital (DE)
- Essen University Hospital (DE)
- University Hospital Carl Gustav Carus (DE)
- Heinrich Heine University Düsseldorf (DE)
- University of Birmingham (GB)
- RWTH Aachen University (DE)
- Erasmus University Rotterdam (NL)
Publication Details
- Journal
- Scientific Reports
- Published
- 2025-03-19
- DOI
- https://doi.org/10.1038/s41598-025-94362-x
- Citations
- 4
- Primary Topic
- Pancreatic and Hepatic Oncology Research
- Type
- article
- Field-Weighted Citation Impact
- 4.18
Funders
- RWTH Aachen University