Toxicologic pathology is the study of the molecular, cellular, tissue, and organ response of the living organism when exposed to chemicals or other agents (e.g., biologic therapeutics). It is one of the most significant endpoints in drug development and is considered an important factor in decision-making for drug attrition.
Toxicologic pathologists play a crucial role in drug discovery and safety assessments due to their skills in informational interpretation from a broad range of disciplines. This is particularly relevant for the various applications pathological data can be integrated into, such as identifying therapeutic targets, evaluating drug efficacy and mechanisms of toxicity, and validating animal models.
The work of a toxicologic pathologist is often meticulous and repetitive. Identifying changes in numerous slides of similar tissue sections is crucial for analyzing a toxin or identifying a safety concern. However, this tedious work is a target for biases, including inter- and intra-observer bias and miscalculations. Digitization and AI-assisted image analysis can significantly influence these aspects.
The potential applications and benefits of AI-assisted image analysis are extensive. To list some examples, AI can…
Whole slide imaging (WSI) for digitizing cell or tissue samples allows data to be shared online. A cloud-based AI solution, such as the Aiforia® Platform, further enhances this collaboration, allowing multiple users to work together in real time from anywhere in the world.
Many regular background lesions, which need to be identified as such, are sex and age-dependent and further influenced by species and strain. A cloud-based AI platform makes it possible to compare lesions across studies, species, and databases for educational, diagnostic, or research purposes. It also enables easier tracking of the progression of a complex lesion through drug trials.
There is also a push to minimize animal use in research and testing with an increased focus on high-throughput screening assays. As automated image analysis of WSIs becomes more common in nonclinical toxicology studies, AI will follow suit.
"If we had not had access to Aiforia, this analysis would have been much more time-consuming. It would be a lot harder; you could even say it would have been impossible to count these individual cells."
– Miika Vuorimaa, Research Scientist at Orion Pharma
Read the full case study →
Artificial intelligence is perfect for completing repetitive, detailed tasks quickly and accurately, beyond the abilities of human pathologists. However, AI will not replace all human tasks but rather assist and augment human efficiency. A collaborative effort between the pathologist and AI model is more effective than either alone.
Pathologists provide cognitive reasoning and an understanding of various fields. Although a model can compute and analyze the images, it is ultimately the pathologist’s responsibility to evaluate the findings. A combination of emerging technology and the creativity of toxicologic pathologists is transforming the field from an analog past to a digital and efficient future.
Quantifying the number of cells in the bone marrow from a histologic section with the help of AI can generate an accurate estimate of bone marrow density to confirm bone marrow proliferation changes, such as hyper or hypocellularity.
Supporting toxicologic pathologists and scientists, Aiforia’s AI applications assist decision-making and automate repetitive tasks in study evaluation. An efficient study-centric workflow with many image analysis options standardizes and reduces variability in study reviews. Compliance with Good Laboratory Practices and integrations with any existing laboratory infrastructure unlock the full benefits of a digitized workflow.
Examples of Aiforia's applications for toxicopathology include:
Learn more by booking a demo with one of our experts.
References
Haschek, W. et al. (2013). Haschek and Rousseaux's Handbook of Toxicologic Pathology. Academic Press. https://doi.org/10.1016/B978-0-12-415759-0.00094-7
Rudmann, D. (2020, March 4). Applying deep learning AI in toxicologic pathology. Pharma Manufacturing. https://www.pharmamanufacturing.com/production/automation-control/article/11298581/applying-deep-learning-ai-in-toxicologic-pathology
Turner, O. et al. (2019, October 23). Society of Toxicologic Pathology Digital Pathology and Image Analysis Special Interest Group Article*: Opinion on the Application of Artificial Intelligence and Machine Learning to Digital Toxicologic Pathology. Toxicologic Pathology, 48(2), 277-294. https://doi.org/10.1177/0192623319881401
ScienceDirect. (2021). Toxicologic Pathology. https://www.sciencedirect.com/topics/pharmacology-toxicology-and-pharmaceutical-science/toxicologic-pathology