CKD Detection Using CNN on Ultrasound Images Based on Estimated Glomerular Filtration Rate (EGFR) Values
DOI:
https://doi.org/10.70062/globalhealth.v2i3.227Keywords:
Chronic Kidney Disease (CKD), Convolutional Neural Network (CNN), Estimated Glomerular Filtration Rate (eGFR), Medical Image Classification, UltrasonographyAbstract
Chronic kidney disease (CKD) is a progressive and irreversible decline in kidney function that, if left untreated, can lead to serious complications. Ultrasonography (USG) is a widely used imaging modality for detecting CKD, yet its interpretation remains highly dependent on the radiologist’s expertise. This study aims to develop a CKD detection system using a convolutional neural network (CNN) on kidney ultrasound images based on estimated glomerular filtration rate (eGFR), and to evaluate the system’s performance.
This research employed a research and development (R&D) approach with an experimental design. The dataset consisted of kidney ultrasound images from CKD and non-CKD patients with corresponding eGFR values. The methodology included image preprocessing, CNN model training, and accuracy evaluation using classification metrics. The results demonstrated that the developed CNN model achieved a total accuracy of 97% on internal test data and 95.8% on external validation. The model’s sensitivity reached 100% for the normal category, 91.67% for CKD stage 4, and 90% for CKD stage 5. Specificity exceeded 96% across all categories, with high precision and F1-scores above 94% for all classes.
This system has proven to be effective as a diagnostic support tool for automatically detecting CKD through kidney ultrasound imaging. Its advantages lie not only in accurately classifying CKD from USG images but also in correlating the classification results with patients' eGFR values. This provides more precise clinical information and supports appropriate CKD staging and management planning.
References
Aziza, B. L. (2017). Pemeriksaan struktur dan fungsi ginjal (pp. 1–51).
Christy, D. (2015). Ultrasonographic assessment of renal parenchymal thickness and kidney length in chronic kidney disease patients. Journal of Nephrology and Urology, 22(4), 198–207.
Christy, J., Martadiani, E., & Sitanggang, F. P. (2015). Gambaran ultrasonografi ginjal pada penyakit ginjal kronis berdasarkan stadium di RSUP Sanglah Denpasar. Jurnal Medika Udayana, 9(7), 36–40.
Davidson. (2014). Principles and practice of medicine (22nd ed.). Elsevier.
Dwi, V., Nursanto, D., Risanti, E. D., Dewi, L. M., Listiana, K., & M. D. (2019). The relationship of hypertension and age against the chronic kidney failure in the Hospital of Dr. Harjono S. Ponorogo. Surakarta.
E. S. (2006). Nefrologi klinik (3rd ed.). Bandung.
Gani, N. S. M., Ali, R. H., & Paat, B. (2017). Gambaran ultrasonografi ginjal pada penderita gagal ginjal kronik di Bagian Radiologi FK Unsrat/SMF Radiologi RSUP Prof. Dr. R. D. Kandou Manado periode 1 April–30 September 2015. e-CliniC, 5(2). https://doi.org/10.35790/ecl.5.2.2017.17419
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
Gunawan, D., & Setiawan, H. (2022). Convolutional neural network dalam citra medis. Konstelasi: Konvergensi Teknologi dan Sistem Informasi, 2(2), 376–390. https://doi.org/10.24002/konstelasi.v2i2.5367
Guyton, A. C., & Hall, J. E. (2014). Buku ajar fisiologi kedokteran (12th ed.). Penerbit Buku Kedokteran EGC.
Hansen, K. L., Nielsen, M. B., & Ewertsen, C. (2016). Ultrasonography of the kidney: A pictorial review. Diagnostics, 6(1), 1–16. https://doi.org/10.3390/diagnostics6010002
Lecun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
Limono, A. B., Setyawan, Y., Tabita, H., & Silitonga, H. (2024). Characteristics and quality of life of chronic kidney disease patients undergoing hemodialysis in Surabaya.
Majdawati, A. (2009). Hubungan gambaran ultrasonografi ginjal dengan laju filtrasi glomerulus (GFR) pada penderita gangguan ginjal: Cor-relation between renal ultrasound examination and glomerular filtration rate in renal disease patient. Jurnal Kedokteran Yarsi, 17(1), 74–81.
Nur Qadar, I. L., Aprianto, N. H., Supriyanto, P., & Aris Diartama, A. A. (2023). Teknik pemeriksaan ultrasonografi panggul dengan klinis kista ovarium di Rumah Sakit Umum Daerah Cengkareng. Jurnal Ilmu Kedokteran dan Kesehatan, 10(11), 3141–3147. https://doi.org/10.33024/jikk.v10i11.12722
Rahmayati, E., Sari, G., Apriantoro, N. H., Prayogi, U. D., Irwan, D., Restiyanti, Y., et al. (2021). Gambaran morfologi USG ginjal dengan kreatinin tinggi pada kasus gagal ginjal kronik. Kocenin Series Conference, 1(1), 1–7.
Rawat, W., & Wang, Z. (2017). Deep convolutional neural networks for image classification: A comprehensive review. Neural Computation, 29(9), 2352–2449. https://doi.org/10.1162/neco_a_00990
Rori, B. A. N., Mamesah, Y. P. M., & Timban, J. F. J. (2024). Gambaran ultrasonografi ginjal pada penderita penyakit ginjal kronis dengan hipertensi di RSUP Prof. Dr. R. D. Kandou periode Juli 2022–Juli 2023. e-CliniC, 12(3), 265–270. https://doi.org/10.35790/ecl.v12i3.53469
Sudharson, S., & Kokil, P. (2020). An ensemble of deep neural networks for kidney ultrasound image classification. Computer Methods and Programs in Biomedicine, 197, 105709. https://doi.org/10.1016/j.cmpb.2020.105709
Sugiyono. (2022). Metode penelitian: Kuantitatif, kualitatif dan R&D (2nd ed.). Alfabeta.
Suwitra, K. (2006). Penyakit ginjal kronik. Dalam Sudoyo, dkk. Buku ajar ilmu penyakit dalam (pp. 1–30). Pusat Penerbitan Departemen Penyakit Dalam FKUI.
Tobias, L., Ducournau, A., Rousseau, F., Mercier, G., & Fablet, R. (2016). Convolutional study: Neural network for object recognition on mobile devices. In International Conference on Pattern Recognition (ICPR) (pp. 1–6). IEEE. https://doi.org/10.1109/ICPR.2016.7900181
Ummul Aiman, P., Hasda, S., Masita, M., & Sari, M. E. (2022). Metodologi penelitian kuantitatif. Yayasan Penerbit Muhammad Zaini.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Global Health: Journal of Health Sciences, Public Health and Pharmacy
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
