Brandon Ginley1, Brendon Lutnick1, Kuang-Yu Jen2, Agnes B Fogo3, Sanjay Jain4, Avi Rosenberg5, Vighnesh Walavalkar6, Gregory Wilding7, John E Tomaszewski1,8, Rabi Yacoub9, Giovanni Maria Rossi5,10, Pinaki Sarder11,7,12. 1. Departments of Pathology and Anatomical Sciences. 2. Department of Pathology and Laboratory Medicine, University of California, Davis Medical Center, Sacramento, California. 3. Departments of Pathology, Microbiology, and Immunology and Medicine, Vanderbilt University, Nashville, Tennessee. 4. Division of Nephrology, Department of Medicine, Washington University School of Medicine, St. Louis, Missouri. 5. Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, Maryland. 6. Department of Pathology, University of California San Francisco, San Francisco, California; and. 7. Biostatistics. 8. Biomedical Informatics, and. 9. Division of Nephrology, Department of Medicine, University at Buffalo-The State University of New York, Buffalo, New York. 10. U.O. Nefrologia, Azienda Ospedaliero-Universitaria di Parma, Dipartimento di Medicina e Chirurgia, Università di Parma. 11. Departments of Pathology and Anatomical Sciences, pinakisa@buffalo.edu. 12. Biomedical Engineering, and.
Abstract
BACKGROUND: Pathologists use visual classification of glomerular lesions to assess samples from patients with diabetic nephropathy (DN). The results may vary among pathologists. Digital algorithms may reduce this variability and provide more consistent image structure interpretation. METHODS: We developed a digital pipeline to classify renal biopsies from patients with DN. We combined traditional image analysis with modern machine learning to efficiently capture important structures, minimize manual effort and supervision, and enforce biologic prior information onto our model. To computationally quantify glomerular structure despite its complexity, we simplified it to three components consisting of nuclei, capillary lumina and Bowman spaces; and Periodic Acid-Schiff positive structures. We detected glomerular boundaries and nuclei from whole slide images using convolutional neural networks, and the remaining glomerular structures using an unsupervised technique developed expressly for this purpose. We defined a set of digital features which quantify the structural progression of DN, and a recurrent network architecture which processes these features into a classification. RESULTS: Our digital classification agreed with a senior pathologist whose classifications were used as ground truth with moderate Cohen's kappa κ = 0.55 and 95% confidence interval [0.50, 0.60]. Two other renal pathologists agreed with the digital classification with κ1 = 0.68, 95% interval [0.50, 0.86] and κ2 = 0.48, 95% interval [0.32, 0.64]. Our results suggest computational approaches are comparable to human visual classification methods, and can offer improved precision in clinical decision workflows. We detected glomerular boundaries from whole slide images with 0.93±0.04 balanced accuracy, glomerular nuclei with 0.94 sensitivity and 0.93 specificity, and glomerular structural components with 0.95 sensitivity and 0.99 specificity. CONCLUSIONS: Computationally derived, histologic image features hold significant diagnostic information that may augment clinical diagnostics.
BACKGROUND: Pathologists use visual classification of glomerular lesions to assess samples from patients with diabetic nephropathy (DN). The results may vary among pathologists. Digital algorithms may reduce this variability and provide more consistent image structure interpretation. METHODS: We developed a digital pipeline to classify renal biopsies from patients with DN. We combined traditional image analysis with modern machine learning to efficiently capture important structures, minimize manual effort and supervision, and enforce biologic prior information onto our model. To computationally quantify glomerular structure despite its complexity, we simplified it to three components consisting of nuclei, capillary lumina and Bowman spaces; and Periodic Acid-Schiff positive structures. We detected glomerular boundaries and nuclei from whole slide images using convolutional neural networks, and the remaining glomerular structures using an unsupervised technique developed expressly for this purpose. We defined a set of digital features which quantify the structural progression of DN, and a recurrent network architecture which processes these features into a classification. RESULTS: Our digital classification agreed with a senior pathologist whose classifications were used as ground truth with moderate Cohen's kappa κ = 0.55 and 95% confidence interval [0.50, 0.60]. Two other renal pathologists agreed with the digital classification with κ1 = 0.68, 95% interval [0.50, 0.86] and κ2 = 0.48, 95% interval [0.32, 0.64]. Our results suggest computational approaches are comparable to human visual classification methods, and can offer improved precision in clinical decision workflows. We detected glomerular boundaries from whole slide images with 0.93±0.04 balanced accuracy, glomerular nuclei with 0.94 sensitivity and 0.93 specificity, and glomerular structural components with 0.95 sensitivity and 0.99 specificity. CONCLUSIONS: Computationally derived, histologic image features hold significant diagnostic information that may augment clinical diagnostics.
Authors: Liang-Chieh Chen; George Papandreou; Iasonas Kokkinos; Kevin Murphy; Alan L Yuille Journal: IEEE Trans Pattern Anal Mach Intell Date: 2017-04-27 Impact factor: 6.226
Authors: Brendon Lutnick; Brandon Ginley; Darshana Govind; Sean D McGarry; Peter S LaViolette; Rabi Yacoub; Sanjay Jain; John E Tomaszewski; Kuang-Yu Jen; Pinaki Sarder Journal: Nat Mach Intell Date: 2019-02-11
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: Thijs W Cohen Tervaert; Antien L Mooyaart; Kerstin Amann; Arthur H Cohen; H Terence Cook; Cinthia B Drachenberg; Franco Ferrario; Agnes B Fogo; Mark Haas; Emile de Heer; Kensuke Joh; Laure H Noël; Jai Radhakrishnan; Surya V Seshan; Ingeborg M Bajema; Jan A Bruijn Journal: J Am Soc Nephrol Date: 2010-02-18 Impact factor: 10.121
Authors: Nicolas Coudray; Paolo Santiago Ocampo; Theodore Sakellaropoulos; Navneet Narula; Matija Snuderl; David Fenyö; Andre L Moreira; Narges Razavian; Aristotelis Tsirigos Journal: Nat Med Date: 2018-09-17 Impact factor: 53.440
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