Brandon Ginley1, Kuang-Yu Jen2, Seung Seok Han3, Luís Rodrigues4,5, Sanjay Jain6, Agnes B Fogo7, Jonathan Zuckerman8, Vighnesh Walavalkar9, Jeffrey C Miecznikowski10, Yumeng Wen11, Felicia Yen2, Donghwan Yun3, Kyung Chul Moon12, Avi Rosenberg13, Chirag Parikh11, Pinaki Sarder14,15. 1. Departments of Pathology and Anatomical Sciences, University at Buffalo - The State University of New York, Buffalo, New York. 2. Department of Pathology and Laboratory Medicine, University of California at Davis, Sacramento, California. 3. Department of Internal Medicine, Seoul National University College of Medicine, Seoul, Korea. 4. University Clinic of Nephrology, Faculty of Medicine, University of Coimbra, Coimbra, Portugal. 5. Nephrology Unit, Coimbra Hospital and University Center, Coimbra, Portugal. 6. Division of Nephrology, Department of Medicine, Washington University School of Medicine, St. Louis, Missouri. 7. Departments of Pathology, Microbiology, and Immunology, and Medicine, Vanderbilt University, Nashville, Tennessee. 8. Department of Pathology and Laboratory Medicine, David Geffen School of Medicine, University of California at Los Angeles, Los Angeles, California. 9. Department of Pathology, University of California at San Francisco, San Francisco, California. 10. Department of Biostatistics, University at Buffalo - The State University of New York, Buffalo, New York. 11. Division of Nephrology, Johns Hopkins University School of Medicine, Baltimore, Maryland. 12. Department of Pathology, Seoul National University College of Medicine, Seoul, Korea. 13. Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, Maryland. 14. Departments of Pathology and Anatomical Sciences, University at Buffalo - The State University of New York, Buffalo, New York pinakisa@buffalo.edu. 15. Department of Biomedical Engineering, University at Buffalo - The State University of New York, Buffalo, New York.
Abstract
BACKGROUND: Interstitial fibrosis, tubular atrophy (IFTA), and glomerulosclerosis are indicators of irrecoverable kidney injury. Modern machine learning (ML) tools have enabled robust, automated identification of image structures that can be comparable with analysis by human experts. ML algorithms were developed and tested for the ability to replicate the detection and quantification of IFTA and glomerulosclerosis that renal pathologists perform. METHODS: A renal pathologist annotated renal biopsy specimens from 116 whole-slide images (WSIs) for IFTA and glomerulosclerosis. A total of 79 WSIs were used for training different configurations of a convolutional neural network (CNN), and 17 and 20 WSIs were used as internal and external testing cases, respectively. The best model was compared against the input of four renal pathologists on 20 new testing slides. Further, for 87 testing biopsy specimens, IFTA and glomerulosclerosis measurements made by pathologists and the CNN were correlated to patient outcome using classic statistical tools. RESULTS: The best average performance across all image classes came from a DeepLab version 2 network trained at 40× magnification. IFTA and glomerulosclerosis percentages derived from this CNN achieved high levels of agreement with four renal pathologists. The pathologist- and CNN-based analyses of IFTA and glomerulosclerosis showed statistically significant and equivalent correlation with all patient-outcome variables. CONCLUSIONS: ML algorithms can be trained to replicate the IFTA and glomerulosclerosis assessment performed by renal pathologists. This suggests computational methods may be able to provide a standardized approach to evaluate the extent of chronic kidney injury in situations in which renal-pathologist time is restricted or unavailable.
BACKGROUND: Interstitial fibrosis, tubular atrophy (IFTA), and glomerulosclerosis are indicators of irrecoverable kidney injury. Modern machine learning (ML) tools have enabled robust, automated identification of image structures that can be comparable with analysis by human experts. ML algorithms were developed and tested for the ability to replicate the detection and quantification of IFTA and glomerulosclerosis that renal pathologists perform. METHODS: A renal pathologist annotated renal biopsy specimens from 116 whole-slide images (WSIs) for IFTA and glomerulosclerosis. A total of 79 WSIs were used for training different configurations of a convolutional neural network (CNN), and 17 and 20 WSIs were used as internal and external testing cases, respectively. The best model was compared against the input of four renal pathologists on 20 new testing slides. Further, for 87 testing biopsy specimens, IFTA and glomerulosclerosis measurements made by pathologists and the CNN were correlated to patient outcome using classic statistical tools. RESULTS: The best average performance across all image classes came from a DeepLab version 2 network trained at 40× magnification. IFTA and glomerulosclerosis percentages derived from this CNN achieved high levels of agreement with four renal pathologists. The pathologist- and CNN-based analyses of IFTA and glomerulosclerosis showed statistically significant and equivalent correlation with all patient-outcome variables. CONCLUSIONS: ML algorithms can be trained to replicate the IFTA and glomerulosclerosis assessment performed by renal pathologists. This suggests computational methods may be able to provide a standardized approach to evaluate the extent of chronic kidney injury in situations in which renal-pathologist time is restricted or unavailable.
Authors: Yasemin Ozluk; Paula L Blanco; Michael Mengel; Kim Solez; Philip F Halloran; Banu Sis Journal: Clin Transplant Date: 2011-09-29 Impact factor: 2.863
Authors: Meyke Hermsen; Thomas de Bel; Marjolijn den Boer; Eric J Steenbergen; Jesper Kers; Sandrine Florquin; Joris J T H Roelofs; Mark D Stegall; Mariam P Alexander; Byron H Smith; Bart Smeets; Luuk B Hilbrands; Jeroen A W M van der Laak Journal: J Am Soc Nephrol Date: 2019-09-05 Impact factor: 10.121
Authors: Ian S D Roberts; H Terence Cook; Stéphan Troyanov; Charles E Alpers; Alessandro Amore; Jonathan Barratt; Francois Berthoux; Stephen Bonsib; Jan A Bruijn; Daniel C Cattran; Rosanna Coppo; Vivette D'Agati; Giuseppe D'Amico; Steven Emancipator; Francesco Emma; John Feehally; Franco Ferrario; Fernando C Fervenza; Sandrine Florquin; Agnes Fogo; Colin C Geddes; Hermann-Josef Groene; Mark Haas; Andrew M Herzenberg; Prue A Hill; Ronald J Hogg; Stephen I Hsu; J Charles Jennette; Kensuke Joh; Bruce A Julian; Tetsuya Kawamura; Fernand M Lai; Lei-Shi Li; Philip K T Li; Zhi-Hong Liu; Bruce Mackinnon; Sergio Mezzano; F Paolo Schena; Yasuhiko Tomino; Patrick D Walker; Haiyan Wang; Jan J Weening; Nori Yoshikawa; Hong Zhang Journal: Kidney Int Date: 2009-07-01 Impact factor: 10.612
Authors: Jan J Weening; Vivette D D'Agati; Melvin M Schwartz; Surya V Seshan; Charles E Alpers; Gerald B Appel; James E Balow; Jan A Bruijn; Terence Cook; Franco Ferrario; Agnes B Fogo; Ellen M Ginzler; Lee Hebert; Gary Hill; Prue Hill; J Charles Jennette; Norella C Kong; Philippe Lesavre; Michael Lockshin; Lai-Meng Looi; Hirofumi Makino; Luiz A Moura; Michio Nagata Journal: Kidney Int Date: 2004-02 Impact factor: 10.612
Authors: Anand Srivastava; Ragnar Palsson; Arnaud D Kaze; Margaret E Chen; Polly Palacios; Venkata Sabbisetti; Rebecca A Betensky; Theodore I Steinman; Ravi I Thadhani; Gearoid M McMahon; Isaac E Stillman; Helmut G Rennke; Sushrut S Waikar Journal: J Am Soc Nephrol Date: 2018-06-04 Impact factor: 10.121
Authors: Elise Marechal; Adrien Jaugey; Georges Tarris; Michel Paindavoine; Jean Seibel; Laurent Martin; Mathilde Funes de la Vega; Thomas Crepin; Didier Ducloux; Gilbert Zanetta; Sophie Felix; Pierre Henri Bonnot; Florian Bardet; Luc Cormier; Jean-Michel Rebibou; Mathieu Legendre Journal: Clin J Am Soc Nephrol Date: 2021-12-03 Impact factor: 8.237
Authors: Aleksandar Denic; Marija Bogojevic; Aidan F Mullan; Moldovan Sabov; Muhammad S Asghar; Sanjeev Sethi; Maxwell L Smith; Fernando C Fervenza; Richard J Glassock; Musab S Hommos; Andrew D Rule Journal: J Am Soc Nephrol Date: 2022-08-03 Impact factor: 14.978
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: Xiang Li; Richard C Davis; Yuemei Xu; Zehan Wang; Nao Souma; Gina Sotolongo; Jonathan Bell; Matthew Ellis; David Howell; Xiling Shen; Kyle J Lafata; Laura Barisoni Journal: J Med Imaging (Bellingham) Date: 2021-12-20
Authors: Adam D Morris; Daniel L D Freitas; Kássio M G Lima; Lauren Floyd; Mark E Brady; Ajay P Dhaygude; Anthony W Rowbottom; Francis L Martin Journal: Molecules Date: 2022-04-02 Impact factor: 4.411
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