Deep learning-based image-analysis algorithm for classification and quantification of multiple histopathological lesions in rat liver

Abstract

Artificial intelligence (AI)-based image analysis is increasingly being used for preclinical safety-assessment studies in the pharmaceutical industry. In this paper, we present an AI-based solution for preclinical toxicology studies. We trained a set of algorithms to learn and quantify multiple typical histopathological findings in whole slide images (WSIs) of the livers of young Sprague Dawley rats by using a U-Net-based deep learning network. The trained algorithms were validated using 255 liver WSIs to detect, classify, and quantify seven types of histopathological findings (including vacuolation, bile duct hyperplasia, and single-cell necrosis) in the liver. The algorithms showed consistently good performance in detecting abnormal areas. Approximately 75% of all specimens could be classified as true positive or true negative. In general, findings with clear boundaries with the surrounding normal structures, such as vacuolation and single-cell necrosis, were accurately detected with high statistical scores. The results of quantitative analyses and classification of the diagnosis based on the threshold values between "no findings" and "abnormal findings" correlated well with diagnoses made by professional pathologists. However, the scores for findings ambiguous boundaries, such as hepatocellular hypertrophy, were poor. These results suggest that deep learning-based algorithms can detect, classify, and quantify multiple findings simultaneously on rat liver WSIs. Thus, it can be a useful supportive tool for a histopathological evaluation, especially for primary screening in rat toxicity studies.

Toxicological Characteristics of Bacterial Nanocellulose in an In Vivo Experiment—Part 1: The Systemic Effects

“…It should be noted that the authors of the works [46,47] did not consider the morphological changes in the liver tissue they identified as significant signs of toxic effects. This opinion may be based on the fact that the spontaneous appearance of a certain number of vacuoles in the periportal region of rat liver tissue occurs quite often in healthy animals of a given species, sex, and age [48] which apparently does not go beyond the physiological norm.…”

The Use of Artificial Intelligence in the Liver Histopathology Field: A Systematic Review

“…An AI-based solution for preclinical toxicology studies was proposed by Shimazaki et al [76], in which multiple U-Net-based DL networks were trained to classify and quantify simultaneously different histopathological findings including spontaneous and drug-induced hepatocyte vacuolization, single-cell necrosis, bile duct hyperplasia, hepatocellular hypertrophy, microgranuloma, and extramedullary hematopoiesis on H&E-stained rat livers acquired using WSI systems. Model training was executed using 92 digitized WSIs of livers treated with various compounds during toxicity studies, while the test dataset included 59 WSIs, and the pathologist validation dataset included 255 WSIs.…”

Deep Learning-based Modeling for Preclinical Drug Safety Assessment

“…Nevertheless, existing works have primarily focused on narrow tasks, with models trained and evaluated on small cohorts [17][18][19][20][21][22][23][24][25][26] . Considering the diversity of lesions induced by compound administration and the range of protocols used by contract research organizations, the current paradigm of developing task-specific models poses challenges to widespread adoption.…”