Digital Pathology and Artificial Intelligence Applied to Nonclinical Toxicology Pathology—The Current State, Challenges, and Future Directions
Toxicologic Pathology · 2025-08 · 53 (6) · 516-535
DOI: 10.1177/01926233251340622 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Toxicologic Pathology, online erschienen am 03.06.2025. Verfasst von Gabriele Pohlmeyer-Esch und 7 weiteren Autor:innen. Beteiligte Einrichtung: Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach, Germany. Hauptthemen laut MEDLINE: Artificial Intelligence, Toxicology, Pathology, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Boehringer Ingelheim.
Abstract (Originalsprache)
Advancements in digital pathology and artificial intelligence (AI) have enormous transformative potential for nonclinical toxicologic pathology and are already changing the ways in which pathologists work. However, due to the rapid evolution of digital pathology and AI, the toxicologic pathology community would benefit from an update on these advancements, which can be used to aid drug development. Here we identify key articles published on the use of digital pathology and AI in the field and provide current regulatory statuses and guidelines. For digital pathology, we outline the requirements for equipment, validation processes, workflows, and archiving. Challenges to achieve system interoperability and to establish harmonization through Digital Imaging and Communications in Medicine compatibility are also discussed. For AI, we highlight considerations for model development, including the determination of ground truth, problems that may arise due to bias, and how the accuracy and precision of AI algorithms can be assessed. Finally, we discuss the challenges and potential for AI-assisted toxicologic pathology, picturing a future where technology and scientific expertise work hand-in-hand to improve the quality and efficiency of nonclinical drug safety evaluation. This publication is a deliverable of the European Innovative Medicines Initiative 2 Joint Undertaking, “Bigpicture.”
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach, Germany.
- Drug Safety Research and Development, Pfizer Inc, Groton, Connecticut, USA.
- Novartis Pharma AG, Basel, Switzerland.
- Boehringer Ingelheim Inc., Ridgefield, Connecticut, USA.
- Deciphex Ltd., Dublin, Ireland.
- Janssen Pharmaceutica NV, Beerse, Belgium.
ORCID-Profile: Gabriele Pohlmeyer-Esch, Charles Halsey, Julie Boisclair, Sripad Ram, Sarah Kirschner-Kitz, Brian Knight, Pierre Moulin, Anna-Lena Frisk
Förderung
- Boehringer Ingelheim
Zitieren
APA
Pohlmeyer-Esch, G., Halsey, C., Boisclair, J., Ram, S., Kirschner-Kitz, S., Knight, B., Moulin, P., & Frisk, A. L. (2025). Digital Pathology and Artificial Intelligence Applied to Nonclinical Toxicology Pathology—The Current State, Challenges, and Future Directions. Toxicologic Pathology, 53(6), 516-535. https://doi.org/10.1177/01926233251340622
Vancouver
Pohlmeyer-Esch G, Halsey C, Boisclair J, Ram S, Kirschner-Kitz S, Knight B, et al. Digital Pathology and Artificial Intelligence Applied to Nonclinical Toxicology Pathology—The Current State, Challenges, and Future Directions. Toxicologic Pathology. 2025;53(6):516-535. doi:10.1177/01926233251340622
BibTeX
@article{PohlmeyerEsch2025,
author = {Pohlmeyer-Esch, Gabriele and Halsey, Charles and Boisclair, Julie and Ram, Sripad and Kirschner-Kitz, Sarah and Knight, Brian and Moulin, Pierre and Frisk, Anna-Lena},
title = {Digital Pathology and Artificial Intelligence Applied to Nonclinical Toxicology Pathology—The Current State, Challenges, and Future Directions},
journal = {Toxicologic Pathology},
year = {2025},
volume = {53},
number = {6},
pages = {516--535},
doi = {10.1177/01926233251340622}
}
EUVIMED