Development and Validation of an Image Analysis System for the Measurement of Cell Proliferation in Mammary Glands of Rats

Abstract

Reliable detection and measurement of cell proliferation are essential in the preclinical assessment of carcinogenic risk of therapeutics. In this context, the assessment of mitogenic potential on mammary glands is crucial in the preclinical safety evaluation of novel insulins. The existing manual counting is time-consuming and subject to operator bias. To standardize the processes, make it faster, and resistant to errors, we developed a semiautomated image analysis system (CEPA software, which is open-source) for counting of proliferating cells in photomicrographs of mammary gland sections of rats labeled with Ki-67. We validated the software and met the predefined targets for specificity, accuracy, and reproducibility. In comparison to manual counting, the respective mean differences in absolute labeling indices (LIs) for CEPA software were 3.12% for user 1 and 3.05% for user 2. The respective regression analysis revealed a good correlation between the CEPA software user and manual counting. Moreover, the CEPA software showed enhanced reproducibility between independent users. The interuser variability is centered around 0 and the absolute difference was about 0.53% LI. Based on validation data, our software has superiority to the manual counting and is a valid and reliable tool for the routine analysis of cell proliferation in mammary glands from rats exposed to insulin analogs.

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

“…8,9 Our findings are also in concordance with a recent study in rat mammary gland tissue, where a user-developed software was used for quantification of the Ki67+ LI. 14 In that study, an algorithm was developed for identification of glandular tissue, but the authors describe that this algorithm often misclassified adipose tissue or connective tissue as glandular tissue. Therefore, it was necessary to visually inspect all the classified areas and when needed, manually correct the algorithm classification.…”

“…32 Furthermore, in the recent mammary gland study discussed above, it was in fact the area of positive and negative nuclei which was quantified, which subsequently was divided by a constant value for the average area per nucleus. 14…”

“…11 In the field of toxicologic pathology there are only few studies where cell proliferation in animal tissues has been quantified with DIA and compared to manual counting, 14,15 and a recent study with rat mammary gland utilized user-developed software. 14 Such tools can be shared in the scientific community, but it might not be easy to adapt such software to a different type of analysis, and often high-level programming skills are required for users to be able to work with such systems. There are also multiple commercially available software packages available for DIA, some of which include analysis modules based on AI.…”

Quantitative Image Analysis for Tissue Biomarker Use: A White Paper From the Digital Pathology Association

“…Traditionally, safety studies evaluate changes based on histochemical stains (such as H&E and Masson trichrome), and several studies have demonstrated the feasibility of automated scoring in murine studies of liver fibrosis, 30 , 31 quantification of hepatic lipid droplets and steatosis, 32 , 33 heart ischemic injury, 34 lung fibrosis, 35 , 36 kidney injury, 37 and pancreatic toxicity. 38 Biomarker studies that rely on IHC and QIA have been successfully deployed, for example, to quantify proliferative Ki-67 cells in rodent mammary glands 39 and endometrium 40 to study reproductive toxicity. Other studies have similarly utilized image analysis to examine processes relevant to several pathologies such as caspases in cell death, 41 T-cell and B-cell markers in inflammation, 42 and collagen deposition related to fibrosis.…”

Developing a Qualification and Verification Strategy for Digital Tissue Image Analysis in Toxicological Pathology

“…If positive nuclear staining is the objective, individual biomarker positive nuclei could be quantified or an average nuclear count could be calculated using biomarker-positive area divided by the average nuclear area. 23…”