EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY 4.0

Pathomics Signature for Prognosis and CA19‐9 Interception in Pancreatic Ductal Adenocarcinoma: A Real‐Life, Multi‐Center Study

Qiangda Chen, Zhihang Xu, Yiping Zou, Zhenlai Jiang, Yecheng Li, Taochen He, Hanlin Yin, Jiali Li, Yanfei An, Jiande Han, Yuqi Xie, Wei Gan und 11 weitere

Advanced Science · 2026

DOI: 10.1002/advs.202515952 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Advanced Science, 2026. Verfasst von Qiangda Chen und 22 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pancreatic Surgery, Zhongshan Hospital, Fudan University, Shanghai, China. Hauptthemen laut MEDLINE: Carcinoma, Pancreatic Ductal, Pancreatic Neoplasms, CA-19-9 Antigen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Program of Shanghai Academic Research Leader, National Natural Science Foundation of China, Shanghai Municipal Health Commission.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Histopathological hematoxylin and eosin (H&E) slides contain valuable prognostic information for pancreatic ductal adenocarcinoma (PDAC), yet systematic feature extraction remains challenging. This multi‐center study developed and validated an automated prognostic model using deep learning on digitized whole‐slide images from 873 PDAC patients with surgical resection across three academic centers. The CrossFormer architecture achieved superior performance in external validation (area under the curve [AUC] = 0.774), significantly outperforming ResNet‐18 (AUC = 0.716), ResNet‐50 (AUC = 0.737), and DenseNet‐121 (AUC = 0.729). Gradient‐weighted Class Activation Mapping identified key prognostic features including desmoplastic stroma, high nuclear‐to‐cytoplasmic ratio, tumor necrosis, and immune cell infiltration. The pathomics signature effectively stratified patients into low‐risk and high‐risk groups with significant survival differences ( p < 0.001). Critically, carbohydrate antigen 19‐9 (CA19‐9) retained prognostic value only in low‐risk patients (hazard ratio [HR] = 2.70, p < 0.001) but not in high‐risk patients (HR = 0.998, p = 0.990). High‐risk patients derived substantial benefit from adjuvant chemotherapy (HR = 0.56, p = 0.038), whereas low‐risk patients showed no significant benefit (HR = 0.83, p = 0.562). These findings provide actionable clinical insights: treatment intensification for high‐risk patients and CA19‐9‐guided monitoring for low‐risk patients. This validated, interpretable model transforms routine H&E slides into quantitative prognostic tools, enabling personalized treatment strategies without additional testing costs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Carcinoma, Pancreatic DuctalPancreatic NeoplasmsCA-19-9 AntigenHumansPrognosisDeep LearningFemaleMaleAged

Stichwörter der Autor:innen

deep learningpancreatic cancerpathological characterpathomicsprognosis

Substanzen

CA-19-9 Antigen

Autor:innen und Institutionen

  • Department of Pancreatic Surgery, Zhongshan Hospital, Fudan University, Shanghai, China.
  • Department of Hepatobiliary Pancreatic Surgery, The First Affiliated Hospital of Fujian Medical University, Fuzhou, China.
  • Cancer Center, Zhongshan Hospital, Fudan University, Shanghai, China.
  • Pancreas Center, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, State Key Laboratory of Druggability Evaluation and Systematic Translational Medicine, Tianjin Key…
  • Department of General Surgery, The Second Affiliated Hospital of Soochow University, Suzhou, China.
  • Department of Pathology, Zhongshan Hospital, Fudan University, Shanghai, China.

ORCID-Profile: Ning Pu

Förderung

  • Program of Shanghai Academic Research Leader
  • National Natural Science Foundation of China
  • Shanghai Municipal Health Commission
  • Beijing Xisike Clinical Oncology Research Foundation
  • Shanghai Science and Technology Commission Innovative Pharmaceutical Products Application Demonstration Project
  • Open Research Fund of Key Laboratory of Gastrointestinal Cancer (Fujian Medical University), Ministry of Education (FMUGIC-202301)
  • Fund of Fujian Provincial Key Laboratory of Translational Cancer Medicine
  • Science and Technology Planning Project of Yunnan Province

Zitieren

APA

Chen, Q., Xu, Z., Zou, Y., Jiang, Z., Li, Y., He, T., Yin, H., Li, J., An, Y., Han, J., Xie, Y., Gan, W., Xu, Y., Wang, W., He, J., Wang, H., Wu, W., Ye, Z., Lou, W., …, & Pu, N. (2026). Pathomics Signature for Prognosis and CA19‐9 Interception in Pancreatic Ductal Adenocarcinoma: A Real‐Life, Multi‐Center Study. Advanced Science. https://doi.org/10.1002/advs.202515952

Vancouver

Chen Q, Xu Z, Zou Y, Jiang Z, Li Y, He T, et al. Pathomics Signature for Prognosis and CA19‐9 Interception in Pancreatic Ductal Adenocarcinoma: A Real‐Life, Multi‐Center Study. Advanced Science. 2026. doi:10.1002/advs.202515952

BibTeX
@article{Chen2026,
  author = {Chen, Qiangda and Xu, Zhihang and Zou, Yiping and Jiang, Zhenlai and Li, Yecheng and He, Taochen and Yin, Hanlin and Li, Jiali and An, Yanfei and Han, Jiande and Xie, Yuqi and Gan, Wei and Xu, Yaolin and Wang, Wenquan and He, Junyi and Wang, Haibo and Wu, Wenchuan and Ye, Zhenyu and Lou, Wenhui and Hao, Jihui and Liu, Liang and Yu, Jun and Pu, Ning},
  title = {Pathomics Signature for Prognosis and CA19‐9 Interception in Pancreatic Ductal Adenocarcinoma: A Real‐Life, Multi‐Center Study},
  journal = {Advanced Science},
  year = {2026},
  doi = {10.1002/advs.202515952}
}
Kostenlos starten →