Format

Send to

Choose Destination
J Am Soc Nephrol. 2019 Oct;30(10):1968-1979. doi: 10.1681/ASN.2019020144. Epub 2019 Sep 5.

Deep Learning-Based Histopathologic Assessment of Kidney Tissue.

Author information

1
Departments of Pathology and.
2
Department of Pathology, Amsterdam Infection & Immunity, Amsterdam Cardiovascular Sciences, Amsterdam UMC, and.
3
Center for Analytical Sciences Amsterdam, Van 't Hoff Institute for Molecular Sciences, University of Amsterdam, Amsterdam, The Netherlands.
4
The Ragon Institute of the Massachusetts General Hospital, Massachusetts Institute of Technology and Harvard University, Cambridge, Massachusetts.
5
Divisions of Transplantation surgery.
6
William J. von Liebig Center for Transplantation and Clinical Regeneration, Mayo Clinic, Rochester, Minnesota; and.
7
Pathology, and.
8
Biomedical Statistics and Informatics, and.
9
Nephrology, Radboud University Medical Center, Nijmegen, The Netherlands.
10
Departments of Pathology and jeroen.vanderlaak@radboudumc.nl.
11
Center for Medical Image Science and Visualization, Linköping University, Linköping, Sweden.

Abstract

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.

KEYWORDS:

Banff classification; deep learning; histopathology; kidney transplantation

Comment in

PMID:
31488607
DOI:
10.1681/ASN.2019020144

Supplemental Content

Full text links

Icon for HighWire
Loading ...
Support Center