Abstract
Glomeruli is a collection of blood vessels present in kidneys of the human body. Since kidneys are one of the most important human body organs, diagnosis of any abnormality becomes very important. This work focuses on the binary classification of normal and scleroses glomeruli using convolutional neural networks from whole slide images (WSI). These images are periodic acid-Schiff (PAS) stained and the glomerulus can be seen as circular areas of dark stains on the slide. The main purpose of this work is to make the diagnoses of the kidney glomeruli fast and accurate since manual detection is quite time-consuming and has many human errors as well. In our work, we have performed the classification of microscopic images to detect the scleroses glomerulus from the kidney. This study deployed, four different types of CNN models and subsequently evaluated, they are AlexNet, Visual Geometry Group-19, GoogleNet, and a customized model. The comparative analysis has been made by considering several parameters such as the number of epochs, optimizers, batch size, and learning rate in which the customized model achieved the accuracy of 97.86%. The results of the proposed work are quite promising. The performances of the models used in this work are compared using various metrics such as accuracy, recall, precision, and F1-score, and the results from each of the models are noted.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Nyengaard JR, Bendtsen TF (1992) Glomerular number and size in relation to age, kidney weight, and body surface in normal man
Bueno G, Gonzalez-Lopez L, Garcia-Rojo M, Laurinavicius A, Deniz O (2020) Data for glomeruli characterization in histopathological images. Data Br 29:105314. https://doi.org/10.1016/j.dib.2020.105314
Kaushik R, Kumar S, Pooling M (2019) Image segmentation using convolutional neural network. Int J Sci Technol Res 8(11). [Online]. Available: www.ijstr.org
Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 234–241
Rizwan I, Haque I, Neubert J (2020) Deep learning approaches to biomedical image segmentation. Inf Med Unlocked 18. https://doi.org/10.1016/j.imu.2020.100297
Jayapandian CP et al (2021) Development and evaluation of deep learning–based segmentation of histologic structures in the kidney cortex with multiple histologic stains. Kidney Int 99(1):86–101. https://doi.org/10.1016/j.kint.2020.07.044
Wang S, Yang DM, Rong R, Zhan X, Xiao G (2019) Pathology image analysis using segmentation deep learning algorithms. Am J Pathol 189(9):1686–1698. https://doi.org/10.1016/j.ajpath.2019.05.007
Bueno G, Fernandez-Carrobles MM, Gonzalez-Lopez L, Deniz O (2020) Glomerulosclerosis identification in whole slide images using semantic segmentation. Comput Methods Programs Biomed 184:105273. https://doi.org/10.1016/j.cmpb.2019.105273
Fu X, Liu T, Xiong Z, Smaill BH, Stiles MK, Zhao J (2018) Segmentation of histological images and fibrosis identification with a convolutional neural network. Comput Biol Med 98:147–158. https://doi.org/10.1016/j.compbiomed.2018.05.015
Kannan S 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
Sun Y, Huang X, Zhou H, Zhang Q (2021) SRPN: similarity-based region proposal networks for nuclei and cells detection in histology images. Med Image Anal 72. https://doi.org/10.1016/j.media.2021.102142
Liu X, Guo Z, Cao J, Tang J (2021) MDC-net: a new convolutional neural network for nucleus segmentation in histopathology images with distance maps and contour information. Comput Biol Med 135. https://doi.org/10.1016/j.compbiomed.2021.104543
Chen X, Duan Q, Wu R, Yang Z (2021) Segmentation of lung computed tomography images based on SegNet in the diagnosis of lung cancer. J Radiat Res Appl Sci 14(1):396–403. https://doi.org/10.1080/16878507.2021.1981753
da Cruz LB et al (2020) Kidney segmentation from computed tomography images using deep neural network. Comput Biol Med 123. https://doi.org/10.1016/j.compbiomed.2020.103906
Heller N et al (2019) The KiTS19 challenge data: 300 kidney tumor cases with clinical context, CT semantic segmentations, and surgical outcomes, pp 1–14 [Online]. Available: http://arxiv.org/abs/1904.00445
Gong Z, Kan L (2021) Segmentation and classification of renal tumors based on convolutional neural network. J Radiat Res Appl Sci 14(1):412–422. https://doi.org/10.1080/16878507.2021.1984150
Manjunath RV, Kwadiki K (2022) Automatic liver and tumour segmentation from CT images using deep learning algorithm. Results Control Optim 6. https://doi.org/10.1016/j.rico.2021.100087
Zhao W, Jiang D, Peña Queralta J, Westerlund T (2020) MSS U-Net: 3D segmentation of kidneys and tumors from CT images with a multi-scale supervised U-Net. Inform Med Unlocked 19. https://doi.org/10.1016/j.imu.2020.100357
Anand V, Gupta S, Koundal D, Nayak SR, Barsocchi P, Bhoi AK (2022) Modified U-NET architecture for segmentation of skin lesion. Sensors 22(3). https://doi.org/10.3390/s22030867
de Bono B, Grenon P, Baldock R, Hunter P (2013) Functional tissue units and their primary tissue motifs in multi-scale physiology. J Biomed Seman 4(1):1–13. https://doi.org/10.1186/2041-1480-4-22
Lee H-C, Aqil AF (2022) Combination of transfer learning methods for kidney glomeruli image classification. Appl Sci 12:1040. https://doi.org/10.3390/app12031040
Varalakshmi P, Saroja S, Ketharaman S, Shimola S (2022) Glomeruli identification in renal biopsy using deep learning approaches. In: 2022 International conference on innovative computing, intelligent communication and smart electrical systems (ICSES), Chennai, India, pp 1–8. https://doi.org/10.1109/ICSES55317.2022.9914279
Gallego J, Swiderska-Chadaj Z, Markiewicz T, Yamashita M, Gabaldon MA, Gertych A (2021) A U-Net based framework to quantify glomerulosclerosis in digitized PAS and H&E stained human tissues. Comput Med Imaging Graph 89:101865. Epub: 2021 Jan 28. PMID: 33548823. https://doi.org/10.1016/j.compmedimag.2021.101865
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Jehangir, B., Nayak, S.R., Wani, S. (2023). Binary Classification of Kidney Glomeruli Using Deep Neural Networks. In: Das, A.K., Nayak, J., Naik, B., Vimal, S., Pelusi, D. (eds) Computational Intelligence in Pattern Recognition. CIPR 2022. Lecture Notes in Networks and Systems, vol 725. Springer, Singapore. https://doi.org/10.1007/978-981-99-3734-9_49
Download citation
DOI: https://doi.org/10.1007/978-981-99-3734-9_49
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-3733-2
Online ISBN: 978-981-99-3734-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)