Abstract
A kidney stone is the crystallization of acid salts and minerals in the kidneys. It is a urinary system disease with a rapidly increasing prevalence. Computed tomography (CT) imaging is preferred for imaging kidney stone disease. This study aims to compare the accuracy capabilities of deep learning models in classifying abdominal CT images. In this paper, we examine the use of pre-trained deep learning models to distinguish between patients with and without kidney stones. A dataset of 681 previously not used before images was obtained from the public hospital in Cyprus and used to train and test five pre-trained models. This study also aims to evaluate and compare deep learning models in kidney stone classification using the multi-criteria decision-making technique. The performance of the various deep learning methods is evaluated using the Preference Ranking Organization Method for Enrichment Evaluation (PROMETHEE) test. The test uses a set of very important conditions for assessment with related weights associated with the kidney stone. The overall result reflects the value of each assessment as well as the overall performance of the model. The PROMETHEE test identified the most suitable deep learning method to be the Inception-V3 algorithm.
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
Alelign, T., Petros, B.: Kidney stone disease: an update on current concepts. Adv. Urol. 2018, 1–12 (2018). https://doi.org/10.1155/2018/3068365
Evan, A.P.: Physiopathology and etiology of stone formation in the kidney and the urinary tract. Pediatr. Nephrol. 25(5), 831–841 (2010). https://doi.org/10.1007/s00467-009-1116-y
Rao, P.N.: Imaging for kidney stones. World J. Urology 22(5), 323–327 (2004). https://doi.org/10.1007/s00345-004-0413-0
Brisbane, W., Bailey, M.R., Sorensen, M.D.: An overview of kidney stone imaging techniques. Nat. Rev. Urol. 13(11), 654 (2016). https://doi.org/10.1038/nrurol.2016.154
Mazurowski, M.A., Buda, M., Saha, A., Bashir, M.R.: Deep learning in radiology: an overview of the concepts and a survey of state of the art with a focus on MRI. J. Magn. Reson. Imaging 49(4), 939–954 (2019). https://doi.org/10.1002/jmri.26534
Tajbakhsh, N., et al.: Convolutional neural networks for medical image analysis: full training or fine-tuning. IEEE Trans. Med. Imaging 35(5), 1299–1312 (2016). https://doi.org/10.1109/TMI.2016.2535302
Ker, J., Wang, L., Rao, J., Lim, T.: Deep learning applications in medical image analysis. IEEE Access 6, 9375–9389 (2017). https://doi.org/10.1109/ACCESS.2017.2788044
Black, K.M., Law, H., Aldoukhi, A., Deng, J., Ghani, K.R.: Deep learning computer vision algorithm for detecting kidney stone composition. BJU Int. 125(6), 920–924 (2020). https://doi.org/10.1111/bju.15035
Lopez, F., et al.: Assessing deep learning methods for the identification of kidney stones in endoscopic images. In: 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 2778–2781 (2021). https://doi.org/10.1109/EMBC46164.2021.9630211
Sabuncu, Ö., Bilgehan, B.: Performance evaluation for various deep learning (DL) methods applied to kidney stone diseases. In: 2021 Int. Conf. Forthcoming Networks Sustainability in AIoT Era (FoNeS-AIoT) IEEE, pp. 1–3 (2021). https://doi.org/10.1109/FoNeS-AIoT54873.2021.00010
Dodge, S., Karam, L.: Human and DNN classification performance on images with quality distortions. ACM Trans. Appl. Percept. 16(2), 1–17 (2019). https://doi.org/10.1145/3306241
Brans, J.-P., De Smet, Y.: PROMETHEE methods. In: Greco, S., Ehrgott, M., Figueira, J.R. (eds.) Multiple Criteria Decision Analysis. ISORMS, vol. 233, pp. 187–219. Springer, New York (2016). https://doi.org/10.1007/978-1-4939-3094-4_6
Saleh, N., Salaheldin, A.M.: A benchmarking platform for selecting optimal retinal diseases diagnosis model based on a multi-criteria decision-making approach. J. Chin. Inst. Eng. 45(1), 27–34 (2022). https://doi.org/10.1080/02533839.2021.1983466
Batur Sir, G.D.: Evaluating treatment modalities in chronic pain treatment by the multi-criteria decision-making procedure. BMC Med. Inform. Decis. Mak. 19(1), 1–9 (2019). https://doi.org/10.1186/s12911-019-0925-6
Mohammed, M.A., et al.: Benchmarking methodology for selection of optimal COVID-19 diagnostic model based on entropy and TOPSIS methods. IEEE Access 8, 99115–99131 (2020). https://doi.org/10.1109/ACCESS.2020.2995597
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 Switzerland AG
About this paper
Cite this paper
Sadıkoğlu, F., Sabuncu, Ö., Bilgehan, B. (2023). A Comparative Analysis of the Different CNN Models Using Fuzzy PROMETHEE for Classification of Kidney Stone. In: Aliev, R.A., Kacprzyk, J., Pedrycz, W., Jamshidi, M., Babanli, M.B., Sadikoglu, F. (eds) 15th International Conference on Applications of Fuzzy Systems, Soft Computing and Artificial Intelligence Tools – ICAFS-2022. ICAFS 2022. Lecture Notes in Networks and Systems, vol 610. Springer, Cham. https://doi.org/10.1007/978-3-031-25252-5_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-25252-5_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25251-8
Online ISBN: 978-3-031-25252-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)