Hermsen, Meyke

AbstractBackgroundComputer‐assisted scoring is gaining prominence in the evaluation of renal histology; however, much of the focus has been on identifying larger objects such as glomeruli. Total inflammation impacts graft outcome, and its quantification requires tools to identify objects at the cellular level or smaller. The goal of the current study was to use CD45 stained slides coupled with image analysis tools to quantify the amount of non‐glomerular inflammation within the cortex.MethodsSixty renal transplant whole slide images were used for digital image analysis. Multiple thresholding methods using pixel intensity and object size were used to identify inflammation in the cortex. Additionally, convolutional neural networks were used to separate glomeruli from other objects in the cortex. This combined measure of inflammation was then correlated with rescored Banff total inflammation classification and outcomes.ResultsIdentification of glomeruli on biopsies had high fidelity (mean pixelwise dice coefficient of .858). Continuous total inflammation scores correlated well with Banff rescoring (maximum Pearson correlation .824). A separate set of thresholds resulted in a significant correlation with alloimmune graft loss.ConclusionsAutomated scoring of inflammation showed a high correlation with Banff scoring. Digital image analysis provides a powerful tool for analysis of renal pathology, not only because it is reproducible and can be automated, but also because it provides much more granular data for studies.

Significance Statement Histopathologic assessment of kidney tissue currently relies on manual scoring or traditional image-processing techniques to quantify and classify tissue features, time-consuming approaches that have limited reproducibility. The authors present an alternative approach, featuring a convolutional neural network for multiclass segmentation of kidney tissue in sections stained by periodic acid–Schiff. Their findings demonstrate applicability of convolutional neural networks for tissue from multiple centers, for biopsies and nephrectomy samples, and for the analysis of both healthy and pathologic tissues. In addition, they validated the network’s results with components from the Banff classification system. Their convolutional neural network may have utility for quantitative studies involving kidney histopathology across centers and potential for application in routine diagnostics. Background The development of deep neural networks is facilitating more advanced digital analysis of histopathologic images. We trained a convolutional neural network for multiclass segmentation of digitized kidney tissue sections stained with periodic acid–Schiff (PAS). Methods We trained the network using multiclass annotations from 40 whole-slide images of stained kidney transplant biopsies and applied it to four independent data sets. We assessed multiclass segmentation performance by calculating Dice coefficients for ten tissue classes on ten transplant biopsies from the Radboud University Medical Center in Nijmegen, The Netherlands, and on ten transplant biopsies from an external center for validation. We also fully segmented 15 nephrectomy samples and calculated the network’s glomerular detection rates and compared network-based measures with visually scored histologic components (Banff classification) in 82 kidney transplant biopsies. Results The weighted mean Dice coefficients of all classes were 0.80 and 0.84 in ten kidney transplant biopsies from the Radboud center and the external center, respectively. The best segmented class was “glomeruli” in both data sets (Dice coefficients, 0.95 and 0.94, respectively), followed by “tubuli combined” and “interstitium.” The network detected 92.7% of all glomeruli in nephrectomy samples, with 10.4% false positives. In whole transplant biopsies, the mean intraclass correlation coefficient for glomerular counting performed by pathologists versus the network was 0.94. We found significant correlations between visually scored histologic components and network-based measures. Conclusions This study presents the first convolutional neural network for multiclass segmentation of PAS-stained nephrectomy samples and transplant biopsies. Our network may have utility for quantitative studies involving kidney histopathology across centers and provide opportunities for deep learning applications in routine diagnostics.