Automatic calculation and visualization of nuclear density in whole slide images of hepatic histological sections

Abstract

An automatic method for estimating the density of cell nuclei in whole slide images (WSI's) of hepatic histological sections is presented. The method can be applied to hematoxylin-eosin (H&E) stained sections with slight histological atypism, such as early well-differentiated hepatocellular carcinoma (ewHCC). It is shown that measured nuclear density is affected by the nuclear size due to fragments of nuclei. This size-dependent problem has been solved by estimating the standard nuclear area for each image patch. The method extracts typical nuclei, which are used to automatically adjust the parameters, including the standard nuclear area. The method is robust for variations in contrast, color, and nuclear size. 40 image patches sampled from 20 WSI's of surgical sections were used for accuracy evaluation. The mean absolute percentage error of estimated nuclear densities was 8.2%. It was also confirmed that the distributions of nuclear density were successfully estimated and visualized for all 20 WSI's. The computation time for a WSI of typical surgical section (754 mm2, about 1,280,000 nuclei) was about 57 minutes on a PC.