Practical implementation of AI in a non‐academic, non‐commercial Pathology laboratory: Real world experience and lessons learned
Histopathology · 2025-11 · 87 (5) · 635-646
DOI: 10.1111/his.15481 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Histopathology, online erschienen am 17.06.2025. Verfasst von Frederik Deman und 6 weiteren Autor:innen. Beteiligte Einrichtung: PA2, Department of Pathology, Ziekenhuis aan de Stroom (ZAS), Antwerp, Belgium. Hauptthemen laut MEDLINE: Artificial Intelligence, Prostatic Neoplasms, Pathology, Clinical. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Aims
As pathology departments transition towards digital workflows, the integration of artificial intelligence (AI) is anticipated to become increasingly common. This study aimed to describe the real‐world implementation and impact of AI integration in routine pathological diagnostics, specifically focusing on prostate biopsy evaluations at the Department of Pathology, ZAS Hospitals, Antwerp. Methods and Results An AI tool for analysing prostate biopsies was integrated into the department's daily workflow by embedding it into existing laboratory information and reporting systems. Following a short adaptation period, the use of AI led to measurable improvements. Most notably, there was a reduction in the number of immunohistochemical tests required, indicating more confident primary diagnoses. Additionally, a significant decrease in turnaround times for biopsy evaluations was observed, highlighting improved efficiency. The implementation process was closely monitored, and practical insights were gathered to guide future AI deployments in pathology.
Conclusions
The first‐year experience of integrating AI into daily pathological practice demonstrated tangible benefits in diagnostic efficiency and workflow optimization. However, the process also revealed several challenges related to real‐world deployment, including adaptation by staff and system integration hurdles. The lessons learned provide valuable guidance for other institutions considering similar AI implementations, reinforcing the importance of strategic planning, training and system compatibility in successful adoption.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- PA2, Department of Pathology, Ziekenhuis aan de Stroom (ZAS), Antwerp, Belgium.
- Department of Diagnostic Sciences, Faculty of Medicine and Health Sciences, University of Ghent, Ghent, Belgium.
- Centre for Oncological Research (CORE), MIPPRO, Faculty of Medicine, Antwerp University, Antwerp, Belgium.
- Department of Mathematics, University of Antwerp, Antwerp, Belgium.
- Division of Research, Peter Mac Callum Cancer Centre, Melbourne, Australia.
- Department of Pathology, University Hospital Ghent, Ghent, Belgium.
ORCID-Profile: Frederik Deman, Glenn Broeckx, Jakob Raymaekers, Roberto Salgado, Amélie Dendooven
Zitieren
APA
Deman, F., Broeckx, G., Declercq, S., Degotte, Q., Raymaekers, J., Salgado, R., & Dendooven, A. (2025). Practical implementation of AI in a non‐academic, non‐commercial Pathology laboratory: Real world experience and lessons learned. Histopathology, 87(5), 635-646. https://doi.org/10.1111/his.15481
Vancouver
Deman F, Broeckx G, Declercq S, Degotte Q, Raymaekers J, Salgado R, et al. Practical implementation of AI in a non‐academic, non‐commercial Pathology laboratory: Real world experience and lessons learned. Histopathology. 2025;87(5):635-646. doi:10.1111/his.15481
BibTeX
@article{Deman2025,
author = {Deman, Frederik and Broeckx, Glenn and Declercq, Sabine and Degotte, Quentin and Raymaekers, Jakob and Salgado, Roberto and Dendooven, Amélie},
title = {Practical implementation of AI in a non‐academic, non‐commercial Pathology laboratory: Real world experience and lessons learned},
journal = {Histopathology},
year = {2025},
volume = {87},
number = {5},
pages = {635--646},
doi = {10.1111/his.15481}
}
EUVIMED