AI-based bone marrow screening
Screening For Bone Marrow Cellularity Changes in Cynomolgus Macaques in Toxicology Safety Studies Using Artificial Intelligence Models
Mark A. Smith, Thomas Westerling-Bui, Angela Wilcox, Julie Schwartz
Toxicology studies examine all components of possible therapies and their effects on patient bodies. Compounds used for immunotherapy and chemotherapy lie within an extensive list of possible harming factors for hematolymphoid organs such as bone marrow. The importance of bone marrow cells in organ regeneration makes the study of these compounds critical in toxicology safety studies.
Artificial intelligence (AI) has the potential to aid pathologists as a diagnostic tool. A study was conducted to evaluate the ability of deep-learning AI models through whole slide image analysis of hematopoietic bone marrow cells from sternebrae of cynomolgus macaques. A pathologist was able to develop the easy-use AI model alone, training it to enumerate cells in bone marrow, from which a cell density value was calculated for objective measure of bone marrow cellularity in tissue sections.
The AI model’s cell count is comparable to counts by veterinary pathologists, both groups claiming low error rates. The AI model offers an advantage over the study pathologist by providing objective data such as the area and cell count of the entire bone marrow section compared to a subjective severity score provided by a pathologist.
The AI model is being trained further to recognise different cells within bone marrow for a holistic view of bone marrow cellularity and additional training will reduce the number of false positives. Similar studies are being conducted in various pathology and toxicology fields to increase efficiency and accuracy throughout research as a whole.
One of the great potential benefits is the ability to develop and deploy AI models for various analytical or study-specific needs in toxicology studies. Due to the nature of AI model generation for image analysis, continuous improvement of the AI model with new training data is extremely practical.
Read the article here.
Quality Control strategies in toxicologic pathology
Developing a Qualification and Verification Strategy for Digital Tissue Image Analysis in Toxicological Pathology
Aleksandra Zuraw, Michael Staup, Robert Klopfleisch, Famke Aeffner, Danielle Brown, Thomas Westerling-Bui, Daniel Rudmann
Digital tissue image analysis is a powerful 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. This requires clear procedural controls, appropriate user training, and involvement of specialists to oversee key steps of the workflow. Hence, toxicologic pathologists play a key role in the conception and implementation of a quality control (QC) system.
Researchers from Charles River Laboratories outline the most common digital tissue image analysis end points and potential sources of analysis error. They also recommend approaches for ensuring quality and correctness of results for both classical and machine-learning based image analysis solutions. Digital tissue image analysis can increase efficiency, improve consistency, and enable assessments that are not possible or practical via manual evaluation. However, as the image analysis technology changes and advances, the need for method qualification and algorithm QC continues regardless of the analysis strategy.
In selecting an appropriate QC strategy, it is important to be cognizant of the intended use of the results. It falls to the reporting pathologist to understand the methods used for study evaluation, their limitations, presence of underlying assumptions and resulting biases, and how they can be avoided or minimized. Ultimately, data should only be extracted from samples that completed the QC process and met predetermined performance criteria to ensure high-quality data generation.
Read the article here.
Deep learning in DSS-induced colitis
Proof of Concept for a Deep Learning Algorithm for Identification and Quantification of key microscopic features in the Murine model of DSS-induced colitis
Agathe Bedard, Thomas Westerling-Bui, Aleksandra Zuraw
Inflammatory bowel disease (IBD) is a complex disease encompassing Crohn’s disease and ulcerative colitis leading to life-threatening complications and decreased quality of life. A well known method for rapid candidate compound screening is the dextran sulfate sodium (DSS) colitis model in mice. DSS is administered into the drinking water of mice resulting in colon ulceration and inflammation, similar to IBD effects. Toxicopathology safety tests in DSS models often rely on microscopic scoring, a subjective and time-consuming task.
The authors’s goal was to examine if deep learning artificial intelligence (AI) could be used to identify acute inflammation in H&E stained sections in a consistent and quantitative manner. An AI model was trained using 20x whole slide images of the entire colon to detect key microscopic features in the mouse model of DSS colitis (entire colon tissue, the muscle and mucosa layers, and two categories within the mucosa).
The trained model was able to segment, with a high level of concordance, the different tissue compartments in the mice. This proof-of-concept work shows promise to increase efficiency and decrease variability of microscopic scoring of DSS colitis, when screening candidate compounds for IBD.
This image analysis approach could be used as a tool to increase efficiency, provide quantitative data, as well as decrease variability, subjectivity and time, as part of screening of candidate compounds for IBD treatment candidates.
Read the article here.