Abstract
INTRODUCTION: We are currently developing a cell classification system intended for routine histopathology. During observation, cells of interest are added to a deep learning (DL) network, which after training classifies the remaining cells of interest with high and immediately validatable accuracy. In this study, we identify the optimal histological microsection thickness for this process and describe in high detail the morphological differences introduced by variation in microsection thickness. METHOD: From HE-stained digitized sections of liver cut manually at 5 thicknesses and on an automated microtome (DS), hepatocytes and non-hepatocytes were manually annotated and loaded into a DL convolutional neural network (ResNet). The network was trained at different settings to identify the thickness with optimal relation between number of training cells and validation accuracy. To shed interpretable light on the impact of thickness, exhaustive morphological details of the annotated cells were quantified and the differences between hepatocytes and non-hepatocytes were analyzed with random forest. RESULTS: Classifying hepatocytes from DS sections clearly resulted in highest validation accuracy with least number of cells and for the remaining thicknesses a trend towards thin sections being more efficient was observed. Random forest analysis generally identified variations in nuclear granularity as the most important features in distinguishing cells. In DS and the thinner tissue sections, nuclear granularity features were more distinguished. CONCLUSION: Microsections cut with DS in particular and thin sections in general are better suited for the intended cell classification system.