Darshana Govind1, Jan U Becker2, Jeffrey Miecznikowski3, Avi Z Rosenberg4, Julien Dang5, Pierre Louis Tharaux5, Rabi Yacoub6, Friedrich Thaiss7, Peter F Hoyer8, David Manthey9, Brendon Lutnick1, Amber M Worral1, Imtiaz Mohammad1, Vighnesh Walavalkar10, John E Tomaszewski1, Kuang-Yu Jen11, Pinaki Sarder12. 1. Department of Pathology and Anatomical Sciences, University at Buffalo, Buffalo, New York. 2. Institute of Pathology, University Hospital of Cologne, Cologne, Germany. 3. Department of Biostatistics, University at Buffalo, Buffalo, New York. 4. Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, Maryland. 5. Paris Cardiovascular Center, Paris, France. 6. Department of Internal Medicine, University at Buffalo, Buffalo, New York. 7. Third Medical Department of Clinical Medicine, University Hospital Hamburg Eppendorf, Hamburg, Germany. 8. Pediatric Nephrology, University Hospital Essen, Essen, Germany. 9. Kitware Incorporated, Clifton Park, New York. 10. Department of Pathology, University of California San Francisco, San Francisco, California. 11. Department of Pathology and Laboratory Medicine, University of California, Sacramento, California. 12. Department of Pathology and Anatomical Sciences, University at Buffalo, Buffalo, New York pinakisa@buffalo.edu.
Abstract
BACKGROUND: Podocyte depletion precedes progressive glomerular damage in several kidney diseases. However, the current standard of visual detection and quantification of podocyte nuclei from brightfield microscopy images is laborious and imprecise. METHODS: We have developed PodoSighter, an online cloud-based tool, to automatically identify and quantify podocyte nuclei from giga-pixel brightfield whole-slide images (WSIs) using deep learning. Ground-truth to train the tool used immunohistochemically or immunofluorescence-labeled images from a multi-institutional cohort of 122 histologic sections from mouse, rat, and human kidneys. To demonstrate the generalizability of our tool in investigating podocyte loss in clinically relevant samples, we tested it in rodent models of glomerular diseases, including diabetic kidney disease, crescentic GN, and dose-dependent direct podocyte toxicity and depletion, and in human biopsies from steroid-resistant nephrotic syndrome and from human autopsy tissues. RESULTS: The optimal model yielded high sensitivity/specificity of 0.80/0.80, 0.81/0.86, and 0.80/0.91, in mouse, rat, and human images, respectively, from periodic acid-Schiff-stained WSIs. Furthermore, the podocyte nuclear morphometrics extracted using PodoSighter were informative in identifying diseased glomeruli. We have made PodoSighter freely available to the general public as turnkey plugins in a cloud-based web application for end users. CONCLUSIONS: Our study demonstrates an automated computational approach to detect and quantify podocyte nuclei in standard histologically stained WSIs, facilitating podocyte research, and enabling possible future clinical applications.
BACKGROUND: Podocyte depletion precedes progressive glomerular damage in several kidney diseases. However, the current standard of visual detection and quantification of podocyte nuclei from brightfield microscopy images is laborious and imprecise. METHODS: We have developed PodoSighter, an online cloud-based tool, to automatically identify and quantify podocyte nuclei from giga-pixel brightfield whole-slide images (WSIs) using deep learning. Ground-truth to train the tool used immunohistochemically or immunofluorescence-labeled images from a multi-institutional cohort of 122 histologic sections from mouse, rat, and human kidneys. To demonstrate the generalizability of our tool in investigating podocyte loss in clinically relevant samples, we tested it in rodent models of glomerular diseases, including diabetic kidney disease, crescentic GN, and dose-dependent direct podocyte toxicity and depletion, and in human biopsies from steroid-resistant nephrotic syndrome and from human autopsy tissues. RESULTS: The optimal model yielded high sensitivity/specificity of 0.80/0.80, 0.81/0.86, and 0.80/0.91, in mouse, rat, and human images, respectively, from periodic acid-Schiff-stained WSIs. Furthermore, the podocyte nuclear morphometrics extracted using PodoSighter were informative in identifying diseased glomeruli. We have made PodoSighter freely available to the general public as turnkey plugins in a cloud-based web application for end users. CONCLUSIONS: Our study demonstrates an automated computational approach to detect and quantify podocyte nuclei in standard histologically stained WSIs, facilitating podocyte research, and enabling possible future clinical applications.
Authors: Jennifer A Schaub; Christopher L O'Connor; Jian Shi; Roger C Wiggins; Kerby Shedden; Jeffrey B Hodgin; Markus Bitzer Journal: J Clin Pathol Date: 2021-01-11 Impact factor: 4.463
Authors: David A Van Valen; Takamasa Kudo; Keara M Lane; Derek N Macklin; Nicolas T Quach; Mialy M DeFelice; Inbal Maayan; Yu Tanouchi; Euan A Ashley; Markus W Covert Journal: PLoS Comput Biol Date: 2016-11-04 Impact factor: 4.475
Authors: Roman D Büllow; Jon N Marsh; S Joshua Swamidass; Joseph P Gaut; Peter Boor Journal: Curr Opin Nephrol Hypertens Date: 2022-02-14 Impact factor: 3.416
Authors: Brendon Lutnick; David Manthey; Jan U Becker; Brandon Ginley; Katharina Moos; Jonathan E Zuckerman; Luis Rodrigues; Alexander J Gallan; Laura Barisoni; Charles E Alpers; Xiaoxin X Wang; Komuraiah Myakala; Bryce A Jones; Moshe Levi; Jeffrey B Kopp; Teruhiko Yoshida; Jarcy Zee; Seung Seok Han; Sanjay Jain; Avi Z Rosenberg; Kuang Yu Jen; Pinaki Sarder Journal: Commun Med (Lond) Date: 2022-08-19