TY - JOUR
T1 - Convolutional Neural Networks for the Evaluation of Chronic and Inflammatory Lesions in Kidney Transplant Biopsies
AU - Hermsen, Meyke
AU - Ciompi, Francesco
AU - Adefidipe, Adeyemi
AU - Denic, Aleksandar
AU - Dendooven, Amélie
AU - Smith, Byron H.
AU - van Midden, Dominique
AU - Bräsen, Jan Hinrich
AU - Kers, Jesper
AU - Stegall, Mark D.
AU - Bándi, Péter
AU - Nguyen, Tri
AU - Swiderska-Chadaj, Zaneta
AU - Smeets, Bart
AU - Hilbrands, Luuk B.
AU - van der Laak, Jeroen A.W.M.
N1 - Publisher Copyright:
© 2022 American Society for Investigative Pathology
PY - 2022/10
Y1 - 2022/10
N2 - In kidney transplant biopsies, both inflammation and chronic changes are important features that predict long-term graft survival. Quantitative scoring of these features is important for transplant diagnostics and kidney research. However, visual scoring is poorly reproducible and labor intensive. The goal of this study was to investigate the potential of convolutional neural networks (CNNs) to quantify inflammation and chronic features in kidney transplant biopsies. A structure segmentation CNN and a lymphocyte detection CNN were applied on 125 whole-slide image pairs of periodic acid–Schiff– and CD3-stained slides. The CNN results were used to quantify healthy and sclerotic glomeruli, interstitial fibrosis, tubular atrophy, and inflammation within both nonatrophic and atrophic tubuli, and in areas of interstitial fibrosis. The computed tissue features showed high correlation with Banff lesion scores of five pathologists (A.A., A.Dend., J.H.B., J.K., and T.N.). Analyses on a small subset showed a moderate correlation toward higher CD3+ cell density within scarred regions and higher CD3+ cell count inside atrophic tubuli correlated with long-term change of estimated glomerular filtration rate. The presented CNNs are valid tools to yield objective quantitative information on glomeruli number, fibrotic tissue, and inflammation within scarred and non-scarred kidney parenchyma in a reproducible manner. CNNs have the potential to improve kidney transplant diagnostics and will benefit the community as a novel method to generate surrogate end points for large-scale clinical studies.
AB - In kidney transplant biopsies, both inflammation and chronic changes are important features that predict long-term graft survival. Quantitative scoring of these features is important for transplant diagnostics and kidney research. However, visual scoring is poorly reproducible and labor intensive. The goal of this study was to investigate the potential of convolutional neural networks (CNNs) to quantify inflammation and chronic features in kidney transplant biopsies. A structure segmentation CNN and a lymphocyte detection CNN were applied on 125 whole-slide image pairs of periodic acid–Schiff– and CD3-stained slides. The CNN results were used to quantify healthy and sclerotic glomeruli, interstitial fibrosis, tubular atrophy, and inflammation within both nonatrophic and atrophic tubuli, and in areas of interstitial fibrosis. The computed tissue features showed high correlation with Banff lesion scores of five pathologists (A.A., A.Dend., J.H.B., J.K., and T.N.). Analyses on a small subset showed a moderate correlation toward higher CD3+ cell density within scarred regions and higher CD3+ cell count inside atrophic tubuli correlated with long-term change of estimated glomerular filtration rate. The presented CNNs are valid tools to yield objective quantitative information on glomeruli number, fibrotic tissue, and inflammation within scarred and non-scarred kidney parenchyma in a reproducible manner. CNNs have the potential to improve kidney transplant diagnostics and will benefit the community as a novel method to generate surrogate end points for large-scale clinical studies.
UR - http://www.scopus.com/inward/record.url?scp=85139187298&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85139187298&partnerID=8YFLogxK
U2 - 10.1016/j.ajpath.2022.06.009
DO - 10.1016/j.ajpath.2022.06.009
M3 - Article
C2 - 35843265
AN - SCOPUS:85139187298
SN - 0002-9440
VL - 192
SP - 1418
EP - 1432
JO - American Journal of Pathology
JF - American Journal of Pathology
IS - 10
ER -