Journal Article
. 2019 Mar; 9(1):5123.
doi: 10.1038/s41598-019-41479-5.

A Fully Automated System Using A Convolutional Neural Network to Predict Renal Allograft Rejection: Extra-validation with Giga-pixel Immunostained Slides

Young-Gon Kim 1 Gyuheon Choi 2 Heounjeong Go 3 Yongwon Cho 1 Hyunna Lee 4 A-Reum Lee 4 Beomhee Park 1 Namkug Kim 5 
  • PMID: 30914690
  •     14 References
  •     3 citations


Pathologic diagnoses mainly depend on visual scoring by pathologists, a process that can be time-consuming, laborious, and susceptible to inter- and/or intra-observer variations. This study proposes a novel method to enhance pathologic scoring of renal allograft rejection. A fully automated system using a convolutional neural network (CNN) was developed to identify regions of interest (ROIs) and to detect C4d positive and negative peritubular capillaries (PTCs) in giga-pixel immunostained slides. The performance of faster R-CNN was evaluated using optimal parameters of the novel method to enlarge the size of labeled masks. Fifty and forty pixels of the enlarged size images showed the best performance in detecting C4d positive and negative PTCs, respectively. Additionally, the feasibility of deep-learning-assisted labeling as independent dataset to enhance detection in this model was evaluated. Based on these two CNN methods, a fully automated system for renal allograft rejection was developed. This system was highly reliable, efficient, and effective, making it applicable to real clinical workflow.

The Banff 2017 Kidney Meeting Report: Revised diagnostic criteria for chronic active T cell-mediated rejection, antibody-mediated rejection, and prospects for integrative endpoints for next-generation clinical trials.
M Haas, A Loupy, +26 authors, M Mengel.
Am J Transplant, 2017 Dec 16; 18(2). PMID: 29243394    Free PMC article.
Highly Cited.
Dermatologist-level classification of skin cancer with deep neural networks.
Andre Esteva, Brett Kuprel, +4 authors, Sebastian Thrun.
Nature, 2017 Jan 25; 542(7639). PMID: 28117445    Free PMC article.
Highly Cited.
Digital pathology evaluation of complement C4d component deposition in the kidney allograft biopsies is a useful tool to improve reproducibility of the scoring.
Ernesta Brazdziute, Arvydas Laurinavicius.
Diagn Pathol, 2011 Apr 22; 6 Suppl 1. PMID: 21489200    Free PMC article.
Capillary deposition of complement split product C4d in renal allografts is associated with basement membrane injury in peritubular and glomerular capillaries: a contribution of humoral immunity to chronic allograft rejection.
Heinz Regele, Georg A Böhmig, +6 authors, Markus Exner.
J Am Soc Nephrol, 2002 Aug 23; 13(9). PMID: 12191982
Classification of breast cancer histology images using Convolutional Neural Networks.
Teresa Araújo, Guilherme Aresta, +5 authors, Aurélio Campilho.
PLoS One, 2017 Jun 02; 12(6). PMID: 28570557    Free PMC article.
Highly Cited.
Deep learning for tumor classification in imaging mass spectrometry.
Jens Behrmann, Christian Etmann, +3 authors, Peter Maaß.
Bioinformatics, 2017 Nov 11; 34(7). PMID: 29126286
Automated Gleason grading of prostate cancer tissue microarrays via deep learning.
Eirini Arvaniti, Kim S Fricker, +7 authors, Manfred Claassen.
Sci Rep, 2018 Aug 15; 8(1). PMID: 30104757    Free PMC article.
Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.
Varun Gulshan, Lily Peng, +12 authors, Dale R Webster.
JAMA, 2016 Nov 30; 316(22). PMID: 27898976
Highly Cited.
Banff initiative for quality assurance in transplantation (BIFQUIT): reproducibility of C4d immunohistochemistry in kidney allografts.
M Mengel, S Chan, +4 authors, P Randhawa.
Am J Transplant, 2013 Mar 08; 13(5). PMID: 23464533
Peritubular capillaritis in renal allografts: prevalence, scoring system, reproducibility and clinicopathological correlates.
I W Gibson, W Gwinner, +6 authors, M Mengel.
Am J Transplant, 2008 Feb 12; 8(4). PMID: 18261174
Deep Learning Algorithms for Detection of Lymph Node Metastases From Breast Cancer: Helping Artificial Intelligence Be Seen.
Jeffrey Alan Golden.
JAMA, 2017 Dec 14; 318(22). PMID: 29234791
Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer.
Babak Ehteshami Bejnordi, Mitko Veta, +67 authors, Rui Venâncio.
JAMA, 2017 Dec 14; 318(22). PMID: 29234806    Free PMC article.
Highly Cited.
Banff 2003 meeting report: new diagnostic insights and standards.
Lorraine C Racusen, Philip F Halloran, Kim Solez.
Am J Transplant, 2004 Sep 16; 4(10). PMID: 15367210
Large scale tissue histopathology image classification, segmentation, and visualization via deep convolutional activation features.
Yan Xu, Zhipeng Jia, +4 authors, Eric I-Chao Chang.
BMC Bioinformatics, 2017 May 28; 18(1). PMID: 28549410    Free PMC article.
Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections.
Young-Gon Kim, Sungchul Kim, +6 authors, Namkug Kim.
Sci Rep, 2020 Dec 16; 10(1). PMID: 33318495    Free PMC article.
Comparing intra-observer variation and external variations of a fully automated cephalometric analysis with a cascade convolutional neural net.
In-Hwan Kim, Young-Gon Kim, +2 authors, Namkug Kim.
Sci Rep, 2021 Apr 14; 11(1). PMID: 33846506    Free PMC article.
Artificial intelligence and kidney transplantation.
Nurhan Seyahi, Seyda Gul Ozcan.
World J Transplant, 2021 Jul 29; 11(7). PMID: 34316452    Free PMC article.