Evaluation of CNN Architectures for Kidney Stone Classification in Ultrasound Image
DOI:
https://doi.org/10.30595/juita.v14i1.28352Keywords:
CNN architectures; image classification; kidney stone; transfer learning; performance evaluation.Abstract
Kidney stone diagnosis requires fast and reliable evaluation, yet ultrasound interpretation still largely depends on clinical expertise. This study evaluates four Convolutional Neural Network (CNN) architectures, VGG16, ResNet50, MobileNetV2, and EfficientNetB0 for classifying kidney ultrasound images into Normal and Stone categories. Using a public dataset of 9,416 images, the models were assessed in terms of predictive performance and computational efficiency. MobileNetV2 achieved perfect classification performance, recording 100% accuracy, precision, recall, and F1-score, while maintaining the smallest parameter size (≈3.6M) and fastest training time (~44 s/epoch). VGG16 and ResNet50 also delivered near perfect accuracy (99.79% and 99.89%) with full recall for Stone cases. In contrast, EfficientNetB0 failed to generalize, yielding only 51.62% accuracy due to severe misclassification of Normal images. These results demonstrate that MobileNetV2 provides the most reliable and efficient solution for ultrasound based kidney stone classification, highlighting its strong potential for practical clinical deployment.
References
[1] C. P. Kovesdy, “Epidemiology of chronic kidney disease: an update 2022,” Kidney International Supplements, vol. 12, no. 1, pp. 7–11, 2022, doi: 10.1016/j.kisu.2021.11.003.
[2] L. Wang, Y. He, C. Han, P. Zhu, Y. Zhou, and R. Tang, “Global burden of chronic kidney disease and risk factors, 1990–2021: an update from the global burden of disease study 2021,” Frontiers in Public Health, vol. 13, no. July, pp. 1–12, 2025, doi: 10.3389/fpubh.2025.1542329.
[3] L. Moftakhar, F. Jafari, M. Ghoddusi Johari, R. Rezaeianzadeh, S. V. Hosseini, and A. Rezaianzadeh, “Prevalence and risk factors of kidney stone disease in population aged 40–70 years old in Kharameh cohort study: a cross-sectional population-based study in southern Iran,” BMC Urology, vol. 22, no. 1, pp. 1–9, 2022, doi: 10.1186/s12894-022-01161-x.
[4] A. Basiri, A. H. Kashi, H. S. Omran, N. Borumandnia, and S. Golshan, “National lifetime prevalence and demographic factors of urolithiasis in Iran,” Urology Journal, vol. 20, no. 2, pp. 102–108, 2023, doi: 10.22037/uj.v20i.7576.
[5] L. Guo, L. Liu, Y. Sun, and L. Xue, “Prevalence and related factors of nephrolithiasis among medical staff in Qingdao, China: a retrospective cross-sectional study,” BMC Nephrology, vol. 25, no. 1, pp. 1–8, 2024, doi: 10.1186/s12882-024-03651-6.
[6] B. Cheraghian, A. Meysam, S. J. Hashemi, and S. A. Hosseini, “Kidney stones and dietary intake in adults: a population-based study in southwest Iran,” BMC Public Health, vol. 24, no. 1, pp. 1–7, 2024, doi: 10.1186/s12889-024-18393-1.
[7] R. Ahmad and B. K. Mohanty, “Chronic kidney disease stage identification using texture analysis of ultrasound images,” Biomedical Signal Processing and Control, vol. 69, no. April, p. 102695, 2021, doi: 10.1016/j.bspc.2021.102695.
[8] S. A. Hannan and P. Pal, “Detection and classification of kidney disease using convolutional neural networks.,” J Neurol Neurorehab Res, vol. 8, no. August, p. 1, 2023, doi: 10.35841/aajnnr-8.2.136.
[9] A. Altalbe and A. R. Javed, “Applying customized convolutional neural network to kidney image volumes for kidney disease detection,” Computer Systems Science and Engineering, vol. 47, no. 2, pp. 2119–2134, 2023, doi: 10.32604/csse.2023.040620.
[10] S. Asif, X. Zheng, and Y. Zhu, “An optimized fusion of deep learning models for kidney stone detection from CT images,” Journal of King Saud University - Computer and Information Sciences, vol. 36, no. 7, p. 102130, 2024, doi: 10.1016/j.jksuci.2024.102130.
[11] K. L. Kohsasih, M. D. Agung Rizky, R. Rosnelly, and W. W. Widjaja, “A deep learning model to detect the brain tumor based on magnetic resonance images,” Jurnal Infotel, vol. 14, no. 3, pp. 203–208, 2022, doi: 10.20895/infotel.v14i3.793.
[12] S. Verma, P. K. Singh, G. Kaur, A. Vashistha, and S. Pansari, “Non-Invasive Kidney Stone Prediction using Machine Learning: An Extensive Review,” Biomedical and Pharmacology Journal, vol. 18, no. March, pp. 45–58, 2025, doi: 10.13005/bpj/3072.
[13] A. Saber, E. Hassan, S. Elbedwehy, W. A. Awad, and T. Z. Emara, “Leveraging ensemble convolutional neural networks and metaheuristic strategies for advanced kidney disease screening and classification,” Scientific Reports, vol. 15, no. 1, pp. 1–15, 2025, doi: 10.1038/s41598-025-93950-1.
[14] G G. Katkar and S. Shinde, “Enhanced chronic kidney disease detection using deep learning: A comparative analysis of CNN and LSTM models.,” Journal of Information Systems Engineering and Management, vol. 10, no. 30s, pp. 316–323, 2025, doi: 10.52783/jisem.v10i30s.4837.
[15] S. N. Almuayqil, S. Abd El-Ghany, A. A. Abd El-Aziz, and M. Elmogy, “KidneyNet: A novel CNN-based technique for the automated diagnosis of chronic kidney diseases from CT scans,” Electronics (Switzerland), vol. 13, no. 24, 2024, doi: 10.3390/electronics13244981.
[16] K. Nagawa, Y. Hara, K. Inoue, Y. Yamagishi, M. Koyama, and H. Shimizu, “Three-dimensional convolutional neural network-based classification of chronic kidney disease severity using kidney MRI,” Scientific Reports, vol. 14, no. 1, pp. 1–10, 2024, doi: 10.1038/s41598-024-66814-3.
[17] A. Pimpalkar, D. K. J. B. Saini, N. Shelke, A. Balodi, G. Rapate, and M. Tolani, “Fine-tuned deep learning models for early detection and classification of kidney conditions in CT imaging,” Scientific Reports, vol. 15, no. 1, pp. 1–20, 2025, doi: 10.1038/s41598-025-94905-2.
[18] D. Alzu’Bi, M. Abdullah, I. Hmeidi, R. Alazab, M. Gharaibeh, and M. El-Heis, “Kidney tumor detection and classification based on deep learning approaches: A new dataset in CT scans,” Journal of Healthcare Engineering, vol. 2022, 2022, doi: 10.1155/2022/3861161.
[19] M. Badawy, A. M. Almars, H. M. Balaha, M. Shehata, M. Qaraad, and M. Elhosseini, “A two-stage renal disease classification based on transfer learning with hyperparameters optimization,” Frontiers in Medicine, vol. 10, 2023, doi: 10.3389/fmed.2023.1106717.
[20] T. Zuo, Y. Zheng, L. He, and T. Chen, “Automated classification of papillarrey nal cell carcinoma and chromophobe renal cell carcinoma based on a small computed tomography imaging dataset using deep learning,” Frontiers in Oncology, vol. 11, no. November, pp. 1–10, 2021, doi: 10.3389/fonc.2021.746750.
[21] E. N. Yildiz, E. Cengil, M. Yildirim, and H. Bingol, “Diagnosis of Chronic Kidney Disease Based on CNN and LSTM,” Acadlore Transactions on AI and Machine Learning, vol. 2, no. 2, pp. 66–74, 2023, doi: 10.56578/ataiml020202.
[22] N. Sulaksono, K. Adi, and R. Isnanto, “Utilization of convolutional neural network in image interpretation techniques for detecting kidney disease,” IAES International Journal of Artificial Intelligence, vol. 14, no. 1, pp. 602–613, 2025, doi: 10.11591/ijai.v14.i1.pp602-613.
[23] J. Jose and S. Sheeja, “Synergistic excellence: CNN-LSTM hybrid model for Improved CKD diagnosis,” SSRG International Journal of Electronics and Communication Engineering, vol. 11, no. 3, pp. 12–23, 2024, doi: 10.14445/23488549/IJECE-V11I3P102.
[24] D. Saif, A. M. Sarhan, and N. M. Elshennawy, “Deep-kidney: an effective deep learning framework for chronic kidney disease prediction,” Health Information Science and Systems, vol. 12, no. 1, pp. 1–22, 2024, doi: 10.1007/s13755-023-00261-8.
[25] S. Tang, C. Jing, Y. Jiang, K. Yang, Z. Huang, and H. Wu, “The effect of image resolution on convolutional neural networks in breast ultrasound,” Heliyon, vol. 9, no. 8, p. e19253, 2023, doi: 10.1016/j.heliyon.2023.e19253.
[26] D. A. Zebari, “Kidney disease segmentation and classification using firefly sigma seeker and magweight rank techniques,” Bioengineering, vol. 12, no. 4, 2025, doi: 10.3390/bioengineering12040350.
[27] A. Larasati, S. Surono, A. Thobirin, and D. A. Dewi, “Performance Analysis of Resampling Techniques for Overcoming Data Imbalance in Multiclass Classification,” Jurnal Informatika, JUITA, vol. 13, no. 1, pp. 57–66, 2025, doi: 10.30595/juita.v13i1.25270.
[28] N. Helmawati and E. Utami, “Analysis for Detecting Banana Leaf Disease Using the CNN Method,” Jurnal Infomatika JUITA, vol. 13, no. 1, pp. 29–36, 2025, doi: 10.30595/juita.v13i1.24514.
[29] M. Momeni, “Kidney Stone Classification and Object Detection.” [Online]. Available: https://www.kaggle.com/datasets/imtkaggleteam/kidney-stone-classification-and-object-detection
[30] G. Maçin, F. Genç, B. Taşcı, S. Dogan, and T. Tuncer, “KidneyNeXt: A lightweight convolutional neural network for multi-class renal tumor classification in computed tomography imaging,” Journal of Clinical Medicine, vol. 14, no. 14, pp. 1–22, 2025, doi: 10.3390/jcm14144929.
[31] K. Kawadkar, “Comparative analysis of vision transformers and convolutional neural networks for medical image classification,” pp. 1–9, 2025, doi: 10.48550/arXiv.2507.21156.
[32] M. Zhang, Z. Ye, E. Yuan, X. Lv, Y. Zhang, and Y. Tan, “Imaging-based deep learning in kidney diseases: recent progress and future prospects,” Insights into Imaging, vol. 15, no. 1, 2024, doi: 10.1186/s13244-024-01636-5
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Zuriati Zuriati, Sriyanto Sriyanto, Agiska Ria Supriyatna, Nurul Qomariyah, Dian Ayu Afifah, Zarnelly Zarnelly
This work is licensed under a Creative Commons Attribution 4.0 International License.
JUITA: Jurnal Informatika is licensed under a Creative Commons Attribution 4.0 International License.
