Tan Xiuxiang, Rosin Mika, Appinger Simone, Deierl Julia Campello, Reichel Konrad, Coolsen Mariëlle, Valkenburg-van Iersel Liselot, de Vos-Geelen Judith, de Jong Evelien J M, Bednarsch Jan, Grootkoerkamp Bas, Doukas Michail, van Eijck Casper, Luedde Tom, Dahl Edgar, Kather Jakob Nikolas, Sivakumar Shivan, Knoefel Wolfram Trudo, Wiltberger Georg, Neumann Ulf Peter, Heij Lara R
Department of Surgery and Transplantation, University Hospital RWTH Aachen, Pauwelsstrasse 30, 52074, Aachen, Germany.
Research Institute of Pancreatic Diseases, Shanghai Key Laboratory of Translational Research for Pancreatic Neoplasms, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Sci Rep. 2025 Mar 19;15(1):9415. doi: 10.1038/s41598-025-94362-x.
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.
胰腺导管腺癌（PDAC）是人类已知的最致命癌症之一。然而，并非所有患者的生存情况都同样糟糕，少数患者甚至能在疾病晚期存活数月或数年。因此，临床上需要寻找能够预测个体生存情况的相应预后生物标志物。为了从PDAC病理切片中挖掘更多信息并识别潜在的生物标志物，我们训练了一种基于U-net架构的深度学习（DL）模型。该DL模型可以在PDAC患者的全切片图像（WSIs）上自动检测肿瘤、基质和淋巴细胞。我们对800例PDAC扫描进行了分析，将基质百分比（SIP）和淋巴细胞百分比（LIP）分别分为两类和三类。所提出的模型取得了显著的准确率结果，总准确率为94.72%，平均交并比为78.66%，平均骰子系数为87.74%。生存分析显示，SIP介导组和LIP高组在所有队列中均与中位总生存期（OS）延长相关。这些发现强调了SIP和LIP作为PDAC预后生物标志物的潜力，并突出了DL作为一种在WSIs上检测PDAC生物标志物的工具的实用性。
