Digital pathology evaluation of complement C4d component deposition in the kidney allograft biopsies is a useful tool to improve reproducibility of the scoring

Abstract

Complement C4d component deposition in kidney allograft biopsies is an established marker of antibody-mediated rejection. In the Banff 07 classification of renal allograft pathology, semi-quantitative evaluation of the proportion of C4d-positive peritubular capilaries (PTC) is used. We aimed to explore the potential of digital pathology tools to obtain quantitative and reproducible measure of C4d deposition in the renal allograft tissue.34 routine kidney allograft biopsies immunohistochemically stained for C4d were included in the study and were evaluated by a qualified pathologist twice, recording an approximate percentage of positive PTC and glomerular area. The same slides were scanned by Aperio ScanScope scanner. Two layers of annotations were created: layer of glomeruli and the remaining non-glomerular area. Image analysis was performed with Aperio Positive Pixel Count algorithm to quantify the proportion of C4d-positive pixels in the area analysed. The percentage of positive (defined as 2+ and 3+) pixels in glomeruli and non-glomerular area was obtained and compared to the percentage of C4d-positive PTC and C4d-positive area of glomeruli recorded by the pathologist. The correlation of digital and manual C4d-positive area scoring in glomeruli was very high (r= 0.89, p<0.0001), while the correlation for non-glomerular (digital) and PTC (manual) area was moderate (r=0.60, p<0.001). The correlation between digital and manual evaluation of C4d in non-glomerular area after exclusion of C4d-positive arterioles from analysis did not improve substantially (r = 0.59, p < 0.001). Reproducibility of digital and manual results was evaluated. For C4d deposition in PTC, agreement between the first and the second digital C4d evaluation (after re-drawing annotations) was perfect (κ=0.96, CI 0.91÷1.00) while agreement between two subsequent manual C4d scorings was substantial (κ = 0.67, CI 0.47 ÷ 0.88). Similarly, for C4d deposition in the glomeruli, agreement of digital evaluation was perfect (κ=1) while for manual scorings it was substantial (κ = 0.76, CI 0.64 ÷ 0.88). Digital evaluation of C4d deposition in allograft kidney correlates with pathologist's scoring and exceeds the latter in reproducibilty. Therefore, it provides a useful tool to control for intraobserver and interobserver variability and may serve as quality assurance measure for allograft pathology diagnosis and research.

Figure 1

Automated image analysis in glomerular tissue. Manually selected glomeruli were analysed with Aperio Positive Pixel Count algorithm. Different colors indicate the intensity level of C4d positive pixels (red – 3+, orange - 2+, yellow – 1+ ).

Figure 2

Automated image analysis in non-glomerular area. Glomeruli were excluded from this annotation layer. C4d positive peritubular capillaries are marked with orange (2+ intensity pixels) or red (3+ intensity pixels) colors.

Figure 3

A plot of manual and automated evaluation of C4d deposition in glomeruli.

Figure 4

A plot of manual and automated evaluation of C4d in the non–glomerular area (one outlier case (Banff class IA) at 14% automated score can be noted).