Skip to main content
SpringerLink
Log in

Glomerulosclerosis detection with pre-trained CNNs ensemble

  • Original paper
  • Published:
Computational Statistics Aims and scope Submit manuscript

Abstract

Glomerulosclerosis characterizes many conditions of primary kidney disease in advanced stages. Its accurate diagnosis relies on histological analysis of renal cortex biopsy, and it is paramount to guide the appropriate treatment and minimize the chances of the disease progressing to chronic stages. This article presents an ensemble approach composed of five convolutional neural networks (CNNs) - VGG-19, Inception-V3, ResNet-50, DenseNet-201, and EfficientNet-B2 - to detect glomerulosclerosis in glomerulus images. We fine-tuned the CNNs and evaluated several configurations for the fully connected layers. In total, we analyzed 25 different models. These CNNs, individually, demonstrated effectiveness in the task; however, we verified that the union of these five well-known CNNs improved the detection rate while decreasing the standard deviations of current techniques. The experiments were carried out in a data set comprised of 1,028 images, on which we applied data-augmentation techniques in the training set. The proposed CNNs ensemble achieved a near-perfect accuracy of 99.0% and kappa of 98.0%.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Notes

  1. www.davita.com/education/kidney-disease/symptoms/what-is-glomerulosclerosis.

  2. http://pathospotter.uefs.br/

  3. https://keras.io/api/layers/pooling_layers/global_average_pooling2d/.

References

  • Alves E, Souza Filho JB, Kritski AL (2019) An ensemble approach for supporting the respiratory isolation of presumed tuberculosis inpatients. Neurocomputing 331:289–300

    Article  Google Scholar 

  • Araújo IC, Schnitman L, Duarte AA et al (2017) Automated detection of segmental glomerulosclerosis in kidney histopathology. In: XIII Brazilian Congress on Computational Intelligence, p 12

  • Barros GO, Navarro B, Duarte A et al (2017) Pathospotter-k: a computational tool for the automatic identification of glomerular lesions in histological images of kidneys. Sci Rep 7(1):1–8

    Article  Google Scholar 

  • Barros GO, Wanderley DC, Rebouças LO et al (2022) Podnet: ensemble-based classification of podocytopathy on kidney glomerular images. In: VISIGRAPP (5: VISAPP), pp 405–412

  • Bevilacqua V, Pietroleonardo N, Triggiani V et al (2017) An innovative neural network framework to classify blood vessels and tubules based on haralick features evaluated in histological images of kidney biopsy. Neurocomputing 228:143–153. https://doi.org/10.1016/j.neucom.2016.09.091

    Article  Google Scholar 

  • Bueno G, Fernandez-Carrobles MM, Gonzalez-Lopez L et al (2020) Glomerulosclerosis identification in whole slide images using semantic segmentation. Comput Methods Programs Biomed 184(105):273

    Google Scholar 

  • Chagas P, Souza L, Araújo I et al (2020) Classification of glomerular hypercellularity using convolutional features and support vector machine. Artif Intell Med 103(101):808

    Google Scholar 

  • Cohen J (1960) A coefficient of agreement for nominal scales. Educ Psychol Measur 20:37–46

    Article  Google Scholar 

  • Dasarathy BV, Sheela BV (1979) A composite classifier system design: concepts and methodology. Proc IEEE 67(5):708–713

    Article  Google Scholar 

  • Dhaun N, Bellamy C, Cattran D et al (2014) Utility of renal biopsy in the clinical management of renal disease: hematuria should not be missed reply. Kidney Int 86(6):1269–1269. https://doi.org/10.1038/ki.2014.278

    Article  PubMed  Google Scholar 

  • Dietterich TG (2000) Ensemble methods in machine learning. In: multiple classifier systems. MCS 2000. Lecture notes in computer science, vol 1857. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45014-9_1

  • dos Santos WL, de Freitas LA, Duarte AA et al (2022) Computational pathology, new horizons and challenges for anatomical pathology. Surg Exp Pathol 5(1):1–7

    Google Scholar 

  • Ginley B, Lutnick B, Jen KY et al (2019) Computational segmentation and classification of diabetic glomerulosclerosis. J Am Soc Nephrol 30(10):1953–1967

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Ginley BG, Tomaszewski JE, Jen KY, et al (2018) Computational analysis of the structural progression of human glomeruli in diabetic nephropathy. In: Medical Imaging 2018: Digital Pathology, International Society for Optics and Photonics, p 105810A

  • He K, Zhang X, Ren S, et al (2015) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Proceedings of the IEEE conference on computer vision and pattern recognition, p 770–778

  • Heckenauer R, Weber J, Wemmert C, et al (2020) Real-time detection of glomeruli in renal pathology. In: 2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS), IEEE, pp 350–355

  • Hermsen M, de Bel T, Den Boer M et al (2019) Deep learning-based histopathologic assessment of kidney tissue. J Am Soc Nephrol 30(10):1968–1979

    Article  PubMed  PubMed Central  Google Scholar 

  • Huang G, Liu Z, Weinberger KQ (2016) Densely connected convolutional networks. CoRR abs/1608.06993. https://arxiv.org/abs/1608.06993

  • Jeong HJ (2020) Diagnosis of renal transplant rejection: Banff classification and beyond. Kidney Res Clin Pract 39(1):17

    Article  PubMed  PubMed Central  Google Scholar 

  • Kalantari A, Kamsin A, Shamshirband S et al (2018) Computational intelligence approaches for classification of medical data: state-of-the-art, future challenges and research directions. Neurocomputing 276:2–22. https://doi.org/10.1016/j.neucom.2017.01.126

    Article  Google Scholar 

  • Kannan S, Morgan LA, Liang B et al (2019) Segmentation of glomeruli within trichrome images using deep learning. Kidney Int Rep 4(7):955–962. https://doi.org/10.1016/j.ekir.2019.04.008

    Article  PubMed  PubMed Central  Google Scholar 

  • Kolachalama VB, Singh P, Lin CQ et al (2018) Association of pathological fibrosis with renal survival using deep neural networks. Kidney Int Rep 3(2):464–475. https://doi.org/10.1016/j.ekir.2017.11.002

    Article  PubMed  PubMed Central  Google Scholar 

  • Kornblith S, Shlens J, Le QV (2019) Do better imagenet models transfer better? In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 2661–2671

  • Landis JR, Koch GG (1977) The measurement of observer agreement for categorical data. Biometrics 33(1):159–174

    Article  CAS  PubMed  Google Scholar 

  • Marsh JN, Matlock MK, Kudose S et al (2018) Deep learning global glomerulosclerosis in transplant kidney frozen sections. IEEE Trans Med Imaging 37(12):2718–2728

    Article  PubMed  PubMed Central  Google Scholar 

  • Oliveira L, Chagas P, Duarte A et al (2022) PathoSpotter: computational intelligence applied to nephropathology. Springer, Cham, pp 253–272. https://doi.org/10.1007/978-3-031-11570-7_16

    Book  Google Scholar 

  • Piccialli F, Giampaolo F, Salvi A et al (2021) A robust ensemble technique in forecasting workload of local healthcare departments. Neurocomputing 444:69–78

    Article  Google Scholar 

  • Rehem JMC, dos Santos WLC, Duarte AA, et al (2021) Automatic glomerulus detection in renal histological images. In: Medical Imaging 2021: Digital Pathology, SPIE, pp 115–125

  • Risdon RA, Turner DR (2012) Atlas of renal pathology, vol 2. Springer, Berlin

    Google Scholar 

  • Russakovsky O, Deng J, Su H et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vision 115:211–252

    Article  MathSciNet  Google Scholar 

  • Santos JD, de MS Veras R, Silva RR et al (2021) A hybrid of deep and textural features to differentiate glomerulosclerosis and minimal change disease from glomerulus biopsy images. Biomed Signal Process Control 70(103):020. https://doi.org/10.1016/j.bspc.2021.103020

    Article  Google Scholar 

  • Sheehan SM, Korstanje R (2018) Automatic glomerular identification and quantification of histological phenotypes using image analysis and machine learning. Am J Physiol Renal Physiol 315(6):F1644–F1651

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. J Big Data 6(1):1–48

    Article  Google Scholar 

  • Shubham S, Jain N, Gupta V et al (2021) Identify glomeruli in human kidney tissue images using a deep learning approach. Soft Comput. https://doi.org/10.1007/s00500-021-06143-z

    Article  Google Scholar 

  • Silva J, Souza L, Chagas P et al (2022) Boundary-aware glomerulus segmentation: toward one-to-many stain generalization. Comput Med Imaging Graph 100(102):104

    Google Scholar 

  • Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Bengio Y, LeCun Y (eds) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings

  • Szegedy C, Vanhoucke V, Ioffe S, et al (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2818–2826

  • Tajbakhsh N, Shin JY, Gurudu SR et al (2016) Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans Med Imaging 35:1299–1312

    Article  PubMed  Google Scholar 

  • Tan M, Le QV (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, 2019

  • Tieleman T, Hinton G et al (2012) Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA Neural Networks Mach Learn 4:26–31

    Google Scholar 

  • Van der Laak J, Litjens G, Ciompi F (2021) Deep learning in histopathology: the path to the clinic. Nat Med 27(5):775–784. https://doi.org/10.1038/s41591-021-01343-4

    Article  CAS  PubMed  Google Scholar 

  • Yu H, Yang LT, Zhang Q et al (2021) Convolutional neural networks for medical image analysis: state-of-the-art, comparisons, improvement and perspectives. Neurocomputing 444:92–110. https://doi.org/10.1016/j.neucom.2020.04.157

    Article  Google Scholar 

  • Zheng Y, Cassol CA, Jung S et al (2021) Deep-learning-driven quantification of interstitial fibrosis in digitized kidney biopsies. Am J Pathol 191(8):1442–1453. https://doi.org/10.1016/j.ajpath.2021.05.005

    Article  PubMed  PubMed Central  Google Scholar 

  • Zheng Z, Zhang X, Ding J et al (2021) Deep learning-based artificial intelligence system for automatic assessment of glomerular pathological findings in lupus nephritis. Diagnostics. https://doi.org/10.3390/diagnostics11111983

    Article  PubMed  PubMed Central  Google Scholar 

  • Zhou Z (2012) Ensemble methods: foundations and algorithms. CRC Press, Boca Raton

    Book  Google Scholar 

Download references

Acknowledgments

Washington Santos and Luciano Oliveira have research scholarships from Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq), grants 306779/2017 and 308580/2021-4, respectively. Angelo Duarte have a research support from Universidade Estadual de Feira de Santana grant TO 074/2021.

Author information

Authors and Affiliations

  1. Instituto Federal de Educação, Ciência e Tecnologia do Piauí, São Raimundo Nonato, PI, Brazil

    Justino Santos

  2. Curso de Bacharelado em Sistemas de Informação, Universidade Federal do Piauí, Picos, PI, Brazil

    Romuere Silva

  3. Departamento de Ciência da Computação, Universidade Federal da Bahia, Salvador, BA, Brazil

    Luciano Oliveira

  4. Centro de Pesquisas Gonçalo Moniz, Fundação Oswaldo Cruz, Salvador, BA, Brazil

    Washington Santos

  5. Curso de Medicina, Universidade Federal do Delta do Parnaíba, Parnaíba, PI, Brazil

    Nayze Aldeman

  6. Departamento de Tecnologia, Universidade Estadual de Feira de Santana, Feira de Santana, BA, Brazil

    Angelo Duarte

  7. Departamento de Computação, Universidade Federal do Piauí, Teresina, PI, Brazil

    Justino Santos & Rodrigo Veras

Authors
  1. Justino Santos
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Romuere Silva
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Luciano Oliveira
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Washington Santos
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Nayze Aldeman
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Angelo Duarte
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Rodrigo Veras
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Justino Santos.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

This work was conducted in accordance with resolution No. 466/12 of the Brazilian National Health Council. To preserve confidentiality, the images (including those shown in the paper) were separated from other patient’s data. No data presented herein allows patient identification. All the procedures were approved by the Ethics Committee for Research Involving Human subjects of the Gonçalo Moniz Institute from the Oswaldo Cruz Foundation (CPqGM/FIOCRUZ), Protocols No. 188/09 and No. 1817574.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Santos, J., Silva, R., Oliveira, L. et al. Glomerulosclerosis detection with pre-trained CNNs ensemble. Comput Stat 39, 561–581 (2024). https://doi.org/10.1007/s00180-022-01307-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00180-022-01307-3

Keywords

Search

Navigation