EUVIMEDEUVIMED entdecken
Multizentrische StudieRandomisierte kontrollierte Studie

Postoperative pancreatic fistula risk assessment using digital pathology based analyses at the parenchymal resection margin of the pancreas – Results from the randomized multicenter RECOPANC trial

Ambrus Màlyi, Peter Bronsert, Oliver Schilling, Kim C Honselmann, Louisa Bolm, Szilárd Szanyi, Zoltán Benyó, Martin Werner, Tobias Keck, Ulrich F Wellner, Sylvia Timme, RECOPANC Study group

HPB · 2025-03 · 27 (3) · 393-401

DOI: 10.1016/j.hpb.2024.12.012 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift HPB, 2025-03. Verfasst von Ambrus Màlyi und 11 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Surgical Pathology, Medical Center - University of Freiburg, Germany; Institute of Translational Medicine, Semmelweis University, 1094 …. Hauptthemen laut MEDLINE: Image Interpretation, Computer-Assisted, Margins of Excision, Pancreas, Pancreatectomy. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: Deutsche Forschungsgemeinschaft.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: In pancreatic surgery Postoperative pancreatic fistula (POPF) represents the most dreaded complication, for which pancreatic texture is acknowledged as one of the strongest predictors. No consensual objective reference has been defined to evaluate the pancreas composition. The presented study aimed to mine histology data of the pancreatic tissue composition with AI assist and correlate it with clinic-pathological parameters derived from the RECOPANC study. METHOD: From 320 patients originally included in the RECOPANC multicentric study, after series of exclusions slides of 134 patients were selected of AI-assisted analysis.For each slide tissue training fields were defined. Machine learning was trained to differentiate the tissue compartments: acinar, fibrotic, and adipose tissue, followed by quantification of the tissue area compartments. RESULTS: Relative fibrotic tissue area revealed as the strongest determinant for the prediction of clinically relevant POPF in multivariable analysis (p = 0.027). The AI assessed amount of fibrotic tissue performed significantly better in prediction of fistula development compared to the surgical palpatory assessment of the pancreatic texture. CONCLUSION: The present study is the first correlating AI-assisted quantified pancreatic tissue composition and POPF within a multicentric cohort.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Interpretation, Computer-AssistedMargins of ExcisionPancreasPancreatectomyPancreatic FistulaPancreatic NeoplasmsPostoperative ComplicationsAgedFemaleHumansMaleMiddle AgedFibrosisMachine LearningPredictive Value of TestsRisk AssessmentRisk FactorsTreatment Outcome

Autor:innen und Institutionen

  • Institute for Surgical Pathology, Medical Center - University of Freiburg, Germany; Institute of Translational Medicine, Semmelweis University, 1094 Budapest, Hungary; Core Facility for Histopathology and Digital Pathol…
  • Institute for Surgical Pathology, Medical Center - University of Freiburg, Germany; Core Facility for Histopathology and Digital Pathology, University of Freiburg, Germany; Faculty of Medicine, University of Freiburg, G…
  • Institute for Surgical Pathology, Medical Center - University of Freiburg, Germany; Faculty of Medicine, University of Freiburg, Germany; German Consortium for Translational Cancer Research (DKTK) and German Cancer Rese…
  • Department of Surgery, University Medical Center Schleswig-Holstein, Campus Lübeck, Lübeck, Germany.
  • Institute of Translational Medicine, Semmelweis University, 1094 Budapest, Hungary; Head and Neck Tumors Multidisciplinary Center and the National Tumor Biology Laboratory, National Institute of Oncology, Budapest, Hung…
  • Institute of Translational Medicine, Semmelweis University, 1094 Budapest, Hungary.

Förderung

  • Deutsche Forschungsgemeinschaft

Zitieren

APA

Màlyi, A., Bronsert, P., Schilling, O., Honselmann, K. C., Bolm, L., Szanyi, S., Benyó, Z., Werner, M., Keck, T., Wellner, U. F., Timme, S., & RECOPANC Study group (2025). Postoperative pancreatic fistula risk assessment using digital pathology based analyses at the parenchymal resection margin of the pancreas – Results from the randomized multicenter RECOPANC trial. HPB, 27(3), 393-401. https://doi.org/10.1016/j.hpb.2024.12.012

Vancouver

Màlyi A, Bronsert P, Schilling O, Honselmann KC, Bolm L, Szanyi S, et al. Postoperative pancreatic fistula risk assessment using digital pathology based analyses at the parenchymal resection margin of the pancreas – Results from the randomized multicenter RECOPANC trial. HPB. 2025;27(3):393-401. doi:10.1016/j.hpb.2024.12.012

BibTeX
@article{Mlyi2025,
  author = {Màlyi, Ambrus and Bronsert, Peter and Schilling, Oliver and Honselmann, Kim C and Bolm, Louisa and Szanyi, Szilárd and Benyó, Zoltán and Werner, Martin and Keck, Tobias and Wellner, Ulrich F and Timme, Sylvia and RECOPANC Study group, RECOPANC Study group},
  title = {Postoperative pancreatic fistula risk assessment using digital pathology based analyses at the parenchymal resection margin of the pancreas – Results from the randomized multicenter RECOPANC trial},
  journal = {HPB},
  year = {2025},
  volume = {27},
  number = {3},
  pages = {393--401},
  doi = {10.1016/j.hpb.2024.12.012}
}
Kostenlos starten →