Toxicologic pathology is transitioning from analog to digital methods. This transition seems inevitable due to a host of ongoing social and medical technological forces. Of these, artificial intelligence (AI) and in particular machine learning (ML) are globally disruptive, rapidly growing sectors of technology whose impact on the long-established field of histopathology is quickly being realized. The development of increasing numbers of algorithms, peering ever deeper into the histopathological space, has demonstrated to the scientific community that AI pathology platforms are now poised to truly impact the future of precision and personalized medicine. However, as with all great technological advances, there are implementation and adoption challenges. This review aims to define common and relevant AI and ML terminology, describe data generation and interpretation, outline current and potential future business cases, discuss validation and regulatory hurdles, and most importantly, propose how overcoming the challenges of this burgeoning technology may shape toxicologic pathology for years to come, enabling pathologists to contribute even more effectively to answering scientific questions and solving global health issues. [Box: see text]
The approach undertaken to deliver a Good Laboratory Practice (GLP) validation of whole slide images (WSIs) and the associated workflow for the digital primary evaluation and peer review of a GLP-compliant rodent inhalation toxicity study is described. The contract research organization (CRO) undertook validation of the slide scanner, scanner software, and associated database software. This provided a GLP validated environment within the database software for the primary histopathologic evaluation using WSI and viewed with the database software web viewer. The CRO also validated a cloud-based digital pathology platform that supported the upload and transfer of WSI and metadata to a cache within the sponsor's local area network. The sponsor undertook a separate GLP validation of the same cloud-based digital pathology platform to cover the download and review of the WSI. The establishment of a fit-for-purpose GLP-compliant workflow for WSI and successful deployment for the digital primary evaluation and peer review of a large GLP toxicology study enabled flexibility in accelerated global working and potential future reuse of digitized data for advanced artificial intelligence and machine learning image analysis.
In Tg-rasH2 carcinogenicity mouse models, a positive control group is treated with a carcinogen such as urethane or N-nitroso-N-methylurea to test study validity based on the presence of the expected proliferative lesions in the transgenic mice. We hypothesized that artificial intelligence–based deep learning (DL) could provide decision support for the toxicologic pathologist by screening for the proliferative changes, verifying the expected pattern for the positive control groups. Whole slide images (WSIs) of the lungs, thymus, and stomach from positive control groups were used for supervised training of a convolutional neural network (CNN). A single pathologist annotated WSIs of normal and abnormal tissue regions for training the CNN-based supervised classifier using INHAND criteria. The algorithm was evaluated using a subset of tissue regions that were not used for training and then additional tissues were evaluated blindly by 2 independent pathologists. A binary output (proliferative classes present or not) from the pathologists was compared to that of the CNN classifier. The CNN model grouped proliferative lesion positive and negative animals at high concordance with the pathologists. This process simulated a workflow for review of these studies, whereby a DL algorithm could provide decision support for the pathologists in a nonclinical study.
Digital tissue image analysis is a computational method for analyzing whole-slide images and extracting large, complex, and quantitative data sets. However, as with any analysis method, the quality of generated results is dependent on a well-designed quality control system for the entire digital pathology workflow. Such system requires clear procedural controls, appropriate user training, and involvement of specialists to oversee key steps of the workflow. The toxicologic pathologist is responsible for reporting data obtained by digital image analysis and therefore needs to ensure that it is correct. To accomplish that, they must understand the main parameters of the quality control system and should play an integral part in its conception and implementation. This manuscript describes the most common digital tissue image analysis end points and potential sources of analysis errors. In addition, it outlines recommended approaches for ensuring quality and correctness of results for both classical and machine-learning based image analysis solutions, as adapted from a recently proposed Food and Drug Administration regulatory framework for modifications to artificial intelligence/machine learning-based software as a medical device. These approaches are beneficial for any type of toxicopathologic study which uses the described end points and can be adjusted based on the intended use of the image analysis solution.
Complex in vitro models (CIVMs) offer the potential to increase the clinical relevance of preclinical efficacy and toxicity assessments and reduce the reliance on animals in drug development. The European Society of Toxicologic Pathology (ESTP) and Society for Toxicologic Pathology (STP) are collaborating to highlight the role of pathologists in the development and use of CIVM. Pathologists are trained in comparative animal medicine which enhances their understanding of mechanisms of human and animal diseases, thus allowing them to bridge between animal models and humans. This skill set is important for CIVM development, validation, and data interpretation. Ideally, diverse teams of scientists, including engineers, biologists, pathologists, and others, should collaboratively develop and characterize novel CIVM, and collectively assess their precise use cases (context of use). Implementing a morphological CIVM evaluation should be essential in this process. This requires robust histological technique workflows, image analysis techniques, and needs correlation with translational biomarkers. In this review, we demonstrate how such tissue technologies and analytics support the development and use of CIVM for drug efficacy and safety evaluations. We encourage the scientific community to explore similar options for their projects and to engage with health authorities on the use of CIVM in benefit-risk assessment.
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 tosupportpharmaceutical 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.