The impact of stain variation and colour normalisation on tissue stain intensity and automated nuclear counting: a...

Variation in H&E staining is often a confounder when comparing data in multi-site studies, and impacts on the generalisability of AI models. In this paper, slides containing serial sections of control liver tissue were sent out to eight clinical laboratories in England to stain over a two-week period. H&E staining optical density was quantified from the WSIs to measure the level of stain variation present within, and between, the eight laboratories. The laboratories used similar staining instruments and reagents, but their H&E stain durations varied. Intra-laboratory consistency was high (9-12% variation) but inter-laboratory variation was higher (maximum median difference of 31%) and the eight laboratories were statistically significantly different (p < 0.001). In addition, multiple colour-normalisation algorithms were applied to the image data using a range of target images. An automated nuclear count was then applied as an indicator of the impact of colour normalisation on the dataset and compared with pathologist manual 'ground truth' count. From three representative labs, the manual 'ground truth' nuclear counts ranged between 129 and 249, and the automated nuclear counts ranged between 152 and 621. Colour normalisation did improve inter-laboratory automated count variation (QCD) from 10% to 5%, but the results varied, particularly depending upon target image selection. The results from this work suggest that colour normalisation may improve consistency between slides but has the potential to be a confounder in its own right.