EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY 4.0

Prognostic significance of tumor budding in pancreatic carcinoma: Digitalized image approach evaluation using artificial intelligence.

Sarra Ben Rejeb iD, Jasser Yaacoubi

F1000Research · 2025

DOI: 10.12688/f1000research.146907.3 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift F1000Research, 2025. Verfasst von Sarra Ben Rejeb und 1 weiteren Autor:innen. Beteiligte Einrichtung: Pathology, Security Forces hospital Tunisia, Tunis, Tunisia. Hauptthemen laut MEDLINE: Pancreatic Neoplasms, Artificial Intelligence, Image Processing, Computer-Assisted. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: None.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Pancreatic carcinoma (PC) is a highly malignant and lethal tumor characterized by a dismal prognosis which raised the need to identify other prognostic factors for better patient risk stratification. Tumor budding (TB), defined as isolated single cancer cells or small clusters of up to four cells at the invasive front, is an emerging histoprognostic factor associated with aggressiveness in various malignancies. This study investigated the prognostic significance of tumor budding (TB) in pancreatic carcinoma using artificial intelligence.

Methods

In this retrospective multicenter study, we collected all cases of PC diagnosed (2008-2022). TB was assed using 2 methods: manual on hematoxylin-eosin (HE) slides and semi-automated using QUPATH software. The selected slide for each case was digitalized using NIS software version 4.00 connected to the microscope NIKON (Eclipse Ni-U). The pathological images were then incorporated into QUPATH. The budds were counted using cell count functionality based on the nucleus size and pixel variability, and TB scores were categorized as BUDD1(0-4), BUDD2(5-9) and BUDD3(≥10). We analyzed the association between the TB score and prognostic clinicopathological factors and overall survival.

Results

25 patients were included (mean age:62.3years;male-to-female ratio:2.57). TB was found in 100%of cases and a high TB score (BUDD2-3) was observed in 56%of cases (using QUPATH versus 48% using HE slides); statistical analysis showed no significant difference between the two methods (p=0.589). A high TB score was associated with older age (>72 years), ductal histological subtype and advanced stage (pT>2).53.8% of patients with lymph node metastasis or advanced stage had high TB score. Multivariate analysis revealed that TB score was strongly and independently associated with overall survival (OS), with a hazard ratio of 2.35.

Conclusion

TB is an additional prognostic factor in PC, and using artificial intelligence via QUPATH software offers a promising and accessible tool for pathologists to evaluate TB and to improve risk stratification in patients with PC.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Pancreatic NeoplasmsArtificial IntelligenceImage Processing, Computer-AssistedHumansMaleFemalePrognosisMiddle AgedRetrospective StudiesAged

Stichwörter der Autor:innen

Pancreatic cancer (PC)artificial intelligence.overall survivor (OS)prognosistumor budding (TB)

Autor:innen und Institutionen

  • Pathology, Security Forces hospital Tunisia, Tunis, Tunisia.

ORCID-Profile: Sarra Ben Rejeb

Förderung

  • None

Zitieren

APA

Ben Rejeb, S., & Yaacoubi, J. (2025). Prognostic significance of tumor budding in pancreatic carcinoma: Digitalized image approach evaluation using artificial intelligence. F1000Research. https://doi.org/10.12688/f1000research.146907.3

Vancouver

Ben Rejeb S, Yaacoubi J. Prognostic significance of tumor budding in pancreatic carcinoma: Digitalized image approach evaluation using artificial intelligence. F1000Research. 2025. doi:10.12688/f1000research.146907.3

BibTeX
@article{BenRejeb2025,
  author = {Ben Rejeb, Sarra and Yaacoubi, Jasser},
  title = {Prognostic significance of tumor budding in pancreatic carcinoma: Digitalized image approach evaluation using artificial intelligence},
  journal = {F1000Research},
  year = {2025},
  doi = {10.12688/f1000research.146907.3}
}
Kostenlos starten →