Artificial Intelligence-Based Quantification of Epithelial Proliferation in Mammary Glands of Rats and Oviducts of Göttingen Minipigs

Abstract

Quantitative assessment of proliferation can be an important endpoint in toxicologic pathology. Traditionally, cell proliferation is quantified by labor-intensive manual counting of positive and negative cells after immunohistochemical staining for proliferation markers (eg, Ki67, bromo-2′-deoxyuridine, or proliferating cell nuclear antigen). Currently, there is a lot of interest in replacing manual evaluation of histology end points with image analysis tools based on artificial intelligence. The aim of the present study was to explore if a commercially available image analysis software can be used to quantify epithelial proliferative activity in rat mammary gland and minipig oviduct. First, algorithms based on artificial intelligence were trained to detect epithelium in each tissue. Areas of BrdU- or Ki67-positive nuclei and negative nuclei were subsequently quantified with threshold analysis. Artificial intelligence-based and manually counted labelling indices were strongly correlated and equally well detected the estrous cycle influence on proliferation in mammary gland and oviduct epithelium, as well as the dramatically increased proliferation in rat mammary glands after treatment with estradiol and progesterone. In conclusion, quantification of epithelial proliferation in two reproductive tissues can be achieved in a reliable fashion using image analysis software based on artificial intelligence, thus avoiding time- and labor-intensive manual counting, requiring trained operators.

Whole-slide imaging, tissue image analysis, and artificial intelligence in veterinary pathology: An updated introduction and review

“…In several papers published on the quantification of the exclusively nuclear biomarker Ki-67, instead of enumerating each Ki-67-positive nucleus, the analysis was based on quantifying the total Ki-67-stained area and dividing this measurement by an average nuclear size to generate cell-based data points (ie, number of Ki-67-positive nuclei). 65,78…”

“…Utilization of image analysis tools in support of toxicologic pathology in non-GLP fashion is becoming more commonplace. 65,9,106,113 For both drug-development companies and CROs, over time digital whole-slide imaging enables the creation of easily accessible digital slide databases, eliminating time-consuming slide-retrieval from physical storage archives. These databases also allow for creation of content-based image retrieval systems, further expanding upon the utility of databases beyond digital archiving and simple keyword searches.…”

Special Issue on Digital Pathology, Tissue Image Analysis, Artificial Intelligence, and Machine Learning: Approximation of the Effect of Novel Technologies on Toxicologic Pathology

“…12 Aside from these examples of the overarching use of AIbased morphometric assessments to entire studies, this special issue incorporates specific image analysis use-cases relevant for toxicologic pathology, many of which utilized AI-based tools. These include proprietary in-house built solutions, such as AI models built to count ovarian follicles, 13 or to quantify changes within retinal layer morphology, 14 and detection of endothelial tip cells in the oxygen-induced retinopathy model, 15 as well the utilization of commercially available application for spermatogenic staging, 16 analysis of rodent cardiomyocytes, 17 to support scoring of dextran sulfate sodium-induced colitis mouse model histology, 18 enumeration of cynomolgus bone marrow histology, 19 quantitative evaluation of hepatocellular cell hypertrophy in rats, 20 quantitate cell proliferation via common immunohistochemical biomarkers, 21 and for verification of changes observed in the Tg-rasH2 mouse used in carcinogenicity studies. 22 A fluorescence-based image analysis use-case (commercial software) is provided by Wilson et al 23 As novel applications at the periphery of the breadand-butter imaging work of a toxicologic pathologist are continuously emerging, Rousselle et al introduce a digital 3D topographic microscopy technique called scanning optical microscopy to evaluate re-endothelialization of vascular lumen after endovascular procedures.…”

Mini Review: The Last Mile—Opportunities and Challenges for Machine Learning in Digital Toxicologic Pathology

“…Examples include spermatogenic staging, 9 evaluating the number and phenotype of cells in bone marrow histology 5 (Figure 1B), and quantification of immunohistochemical markers. 10 The ML applications could also support the technical staff creating the digital whole-slide images (WSI). As is the case for glass slides, the quality control of WSI is an important best practice but is time-consuming and manual.…”

“…The ML algorithms that can standardize and automate these quantitative changes would be beneficial to the pathology workflow. Examples include those described in this digital pathology special issue such as mammary gland epithelial proliferation, 10 hepatocellular hypertrophy, 13 and, in our own experience, an automated method for measuring nerve fiber axonal-G ratio (Figure 1F).…”