Meyke Hermsen1, Thomas de Bel1, Marjolijn den Boer1, Eric J Steenbergen1, Jesper Kers2,3,4, Sandrine Florquin2, Joris J T H Roelofs2, Mark D Stegall5,6, Mariam P Alexander6,7, Byron H Smith6,8, Bart Smeets1, Luuk B Hilbrands9, Jeroen A W M van der Laak10,11. 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.
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.
Authors: Geert Litjens; Thijs Kooi; Babak Ehteshami Bejnordi; Arnaud Arindra Adiyoso Setio; Francesco Ciompi; Mohsen Ghafoorian; Jeroen A W M van der Laak; Bram van Ginneken; Clara I Sánchez Journal: Med Image Anal Date: 2017-07-26 Impact factor: 8.545
Authors: John D Bukowy; Alex Dayton; Dustin Cloutier; Anna D Manis; Alexander Staruschenko; Julian H Lombard; Leah C Solberg Woods; Daniel A Beard; Allen W Cowley Journal: J Am Soc Nephrol Date: 2018-06-19 Impact factor: 10.121
Authors: L C Racusen; K Solez; R B Colvin; S M Bonsib; M C Castro; T Cavallo; B P Croker; A J Demetris; C B Drachenberg; A B Fogo; P Furness; L W Gaber; I W Gibson; D Glotz; J C Goldberg; J Grande; P F Halloran; H E Hansen; B Hartley; P J Hayry; C M Hill; E O Hoffman; L G Hunsicker; A S Lindblad; Y Yamaguchi Journal: Kidney Int Date: 1999-02 Impact factor: 10.612
Authors: David Tellez; Maschenka Balkenhol; Irene Otte-Holler; Rob van de Loo; Rob Vogels; Peter Bult; Carla Wauters; Willem Vreuls; Suzanne Mol; Nico Karssemeijer; Geert Litjens; Jeroen van der Laak; Francesco Ciompi Journal: IEEE Trans Med Imaging Date: 2018-03-28 Impact factor: 10.048
Authors: Marcin Klapczynski; Gerard D Gagne; Sherry J Morgan; Kelly J Larson; Bruce E Leroy; Eric A Blomme; Bryan F Cox; Eugene W Shek Journal: J Pathol Inform Date: 2012-04-28
Authors: A Loupy; M Haas; K Solez; L Racusen; D Glotz; D Seron; B J Nankivell; R B Colvin; M Afrouzian; E Akalin; N Alachkar; S Bagnasco; J U Becker; L Cornell; C Drachenberg; D Dragun; H de Kort; I W Gibson; E S Kraus; C Lefaucheur; C Legendre; H Liapis; T Muthukumar; V Nickeleit; B Orandi; W Park; M Rabant; P Randhawa; E F Reed; C Roufosse; S V Seshan; B Sis; H K Singh; C Schinstock; A Tambur; A Zeevi; M Mengel Journal: Am J Transplant Date: 2017-01 Impact factor: 8.086
Authors: Geert Litjens; Clara I Sánchez; Nadya Timofeeva; Meyke Hermsen; Iris Nagtegaal; Iringo Kovacs; Christina Hulsbergen-van de Kaa; Peter Bult; Bram van Ginneken; Jeroen van der Laak Journal: Sci Rep Date: 2016-05-23 Impact factor: 4.379
Authors: Aleksandar Denic; Hisham Elsherbiny; Aidan F Mullan; Bradley C Leibovich; R Houston Thompson; Luisa Ricaurte Archila; Ramya Narasimhan; Walter K Kremers; Mariam P Alexander; John C Lieske; Lilach O Lerman; Andrew D Rule Journal: J Am Soc Nephrol Date: 2020-09-16 Impact factor: 10.121
Authors: Naim Issa; Camden L Lopez; Aleksandar Denic; Sandra J Taler; Joseph J Larson; Walter K Kremers; Luisa Ricaurte; Massini A Merzkani; Mariam Priya Alexander; Harini A Chakkera; Mark D Stegall; Joshua J Augustine; Andrew D Rule Journal: J Am Soc Nephrol Date: 2020-01-23 Impact factor: 10.121
Authors: Alton B Farris; Juan Vizcarra; Mohamed Amgad; Lee A D Cooper; David Gutman; Julien Hogan Journal: Histopathology Date: 2021-03-08 Impact factor: 5.087
Authors: Nassim Bouteldja; Barbara M Klinkhammer; Roman D Bülow; Patrick Droste; Simon W Otten; Saskia Freifrau von Stillfried; Julia Moellmann; Susan M Sheehan; Ron Korstanje; Sylvia Menzel; Peter Bankhead; Matthias Mietsch; Charis Drummer; Michael Lehrke; Rafael Kramann; Jürgen Floege; Peter Boor; Dorit Merhof Journal: J Am Soc Nephrol Date: 2020-11-05 Impact factor: 10.121