Artificial Intelligence in Toxicological Pathology: Quantitative Evaluation of Compound-Induced Follicular Cell Hypertrophy in Rat Thyroid Gland Using Deep Learning Models

Abstract

Digital pathology has recently been more broadly deployed, fueling artificial intelligence (AI) application development and more systematic use of image analysis. Here, two different AI models were developed to evaluate follicular cell hypertrophy in hematoxylin and eosin-stained whole-slide-images of rat thyroid gland, using commercial AI-based-software. In the first, mean cytoplasmic area measuring approach (MCA approach), mean cytoplasmic area was calculated via several sequential deep learning (DL)-based algorithms including segmentation in microanatomical structures (separation of colloid and stroma from thyroid follicular epithelium), nuclear detection, and area measurements. With our additional second, hypertrophy area fraction predicting approach (HAF approach), we present for the first time DL-based direct detection of the histopathological change follicular cell hypertrophy in the thyroid gland with similar results. For multiple studies, increased output parameters (mean cytoplasmic area and hypertrophic area fraction) were shown in groups given different hypertrophy-inducing reference compounds in comparison to control groups. Quantitative results correlated with the gold standard of board-certified veterinary pathologists’ diagnoses and gradings as well as thyroid hormone dependent gene expressions. Accuracy and repeatability of diagnoses and grading by pathologists are expected to be improved by additional evaluation of mean cytoplasmic area or direct detection of hypertrophy, combined with standard histopathological observations.