Building a nonclinical pathology laboratory of the future for pharmaceutical research excellence

• Published in: Drug discovery today Vol. 28; no. 10; p. 103747
• Main Authors: Rudmann, D.G., Bertrand, L., Zuraw, A., Deiters, J., Staup, M., Rivenson, Y., Kuklyte, J.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.10.2023
• Subjects: Artificial intelligence; Decision support; Deep learning; Digital microscopy; Drug development; Good Laboratory Practice; Nonclinical; Pathology; Toxicology; Virtual staining; Deep learning; Pathology; Toxicology; Good Laboratory Practice; Digital microscopy; Drug development; Artificial intelligence; Virtual staining; Decision support; Nonclinical
• ISSN: 1359-6446; 1878-5832
• DOI: 10.1016/j.drudis.2023.103747

•The nonclinical pathology laboratory (NPL) has been largely unchanged in the last 50 years.•Digitization and automation are driving NPL operational efficiency and scientific innovation.•Deep learning artificial intelligence (AI) is positioned to impact the entire NPL workflow.•Digital image warehousing enables efficient training and utilization of staff.•Large-scale production should be aligned closely with technology, regulations and intended use. We describe a roadmap for a fully digital artificial intelligence (AI)-augmented nonclinical pathology laboratory across three continents. Underpinning the design are Good Laboratory Practice (GLP)-validated laboratory information management systems (LIMS), whole slide-scanners (WSS), image management systems (IMS), and a digital microscope intended for use by the nonclinical pathologist. Digital diagnostics are supported by tools that include AI-based virtual staining and deep learning-based decision support. Implemented during the COVID-19 pandemic, the initial digitized workflow largely mitigated disruption of pivotal nonclinical studies required to support pharmaceutical clinical testing. We believe that this digital transformation of our nonclinical pathology laboratories will promote efficiency and innovation in the future and enhance the quality and speed of drug development decision making.