TY - JOUR
T1 - Deep Learning-Based Histopathologic Assessment of Kidney Tissue
AU - Hermsen, Meyke
AU - de Bel, Thomas
AU - den Boer, Marjolijn
AU - Steenbergen, Eric J.
AU - Kers, Jesper
AU - Florquin, Sandrine
AU - Roelofs, Joris J. T. H.
AU - Stegall, Mark D.
AU - Alexander, Mariam P.
AU - Smith, Byron H.
AU - Smeets, Bart
AU - Hilbrands, Luuk B.
AU - van der Laak, Jeroen A. W. M.
PY - 2019/1/1
Y1 - 2019/1/1
N2 - 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.
AB - 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.
UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85072791755&origin=inward
UR - https://www.ncbi.nlm.nih.gov/pubmed/31488607
U2 - https://doi.org/10.1681/ASN.2019020144
DO - https://doi.org/10.1681/ASN.2019020144
M3 - Article
C2 - 31488607
SN - 1046-6673
VL - 30
SP - 1968
EP - 1979
JO - Journal of the American Society of Nephrology
JF - Journal of the American Society of Nephrology
IS - 10
ER -