U-Net segmentation of the kidney on noncontrast CT for kidney stones location: a deep learning model for Mexican patients
DOI:
https://doi.org/10.31349/RevMexFis.72.011101Keywords:
kidney stones, non-contrast computed tomography, image segmentation, U-Net, convolutional neural networks, medical artificial intelligence.Abstract
This work presents the implementation of convolutional neural networks for the automated detection and segmentation of kidney stones in non-contrast computed tomography (CT) medical images from patients of the Mexican Institute of Social Security (IMSS). A U-Net architecture was employed to segment the kidneys and delineate regions of interest in high-resolution CT slices, with ground truth annotations provided by medical specialists. The model was trained and validated on a curated dataset representative of the Mexican population, achieving a Dice similarity coefficient of 0.9808 ± 0.038, an IoU of 0.9623 ± 0.0073, and a validation loss of 0.0040 ± 0.008 in five-fold crossvalidation. The proposed system demonstrated rapid convergence and excellent agreement with manual segmentations, confirming its utility as a reliable diagnostic aid for kidney stone detection in clinical practice.
References
C. D. Scales Jr. et al., Prevalence of kidney stones in the United States, Eur. Urol. 62 (2012) 160. https://doi.org/10.1016/j.eururo.2012.03.052
K. Stamatelou, D. S. Goldfarb, Epidemiology of kidney stones, Healthcare 11 (2023) 424. https://doi.org/10.3390/healthcare11030424
B. J. Young et al., Is the economic impact and utilization of imaging studies for pediatric urolithiasis across the United States increasing?, Urology 94 (2016) 208, https://doi.org/10.1016/j.urology.2016.05.019
J. M. Soucie, M. J. Thun, R. J. Coates, W. Mc-Clellan, H. Austin, Demographic and geographic variability of kidney stones in the United States, Kid- ney Int. 46 (1994) 893, https://doi.org/10.1038/ki.1994.347
A. Chewcharat, G. Curhan, Trends in the prevalence of kidney stones in the United States from 2007 to 2016, Urolithiasis 49 (2021) 27, https://doi.org/10.1007/s00240-020-01210-w
L. Moftakhar et al., 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 Urol. 22 (2022) 205, https://doi.org/10.1186/s12894-022-01161-x
J. Shoag, G. E. Tasian, D. S. Goldfarb, H. Eisner, Brian, The new epidemiology of nephrolithiasis, Adv. Chronic Kidney Dis. 22 (2015) 273, https://doi.org/10.1053/j.ackd.2015.04.004
J. B. Ziemba, B. R. Matlaga, Epidemiology and economics of nephrolithiasis, Investig. Clin. Urol. 58 (2017) 299, https: //doi.org/10.4111/icu.2017.58.5.299
V. Gómez Dos Santos and F. J. Burgos, Litiasis en el origen de insuficiencia renal crónica, Nefrología 25 (2005) 82
V. G. González, Litiasis renal: estudio y manejo endocrinológico, Rev. Med. Clın. Las Condes 24 (2013) 798, https://doi.org/10.1016/S0716-8640(13)70226-8
A. A. Herrera Muñoz et al., Nefrolitiasis: Una revisión actualizada, Rev. Clın. Esc. Med. Univ. Costa Rica 10 (2020) 11
M. Medina-Escobedo, M. Zaidi, E. Real-de León, S. Orozco Rivadeneyra, Prevalencia y factores de riesgo en Yucatán, México, para litiasis urinaria, Salud Publ. Méx. 44 (2002) 541
M. Medina-Escobedo, R. Alcocer-Dzul, J. López-López, J. S. Villanueva, Obesidad como factor de riesgo para alteraciones metabólicas en adultos con litiasis urinaria, Rev. Med. Inst. Mex. Seguro Soc. 53 (2015) 692
Y. L. R. Salazar, E. Gómez Montañez, Litiasis renal: una entidad cada vez más común, Expresiones Médicas 9 (2021) 30
W. Brisbane, M. R. Bailey, M. D. Sorensen, An overview of kidney stone imaging techniques, Nat. Rev. Urol. 13 (2016) 654, https://doi.org/10.1038/nrurol.2016.154
M. Malaki, The comparison of ultrasound and non-contrast helical computerized tomography for children nephrolithiasis detection, Urol. Ann. 6 (2014) 309, https://doi.org/10.4103/0974-7796.140991
A. J. Portis and C. P. Sundaram, Diagnosis and initial management of kidney stones, Am. Fam. Physician 63 (2001) 1329
B. Kayalibay, G. Jensen, P. van der Smagt, CNN-based segmentation of medical imaging data, arXiv 1701.03056 (2017). https://doi.org/10.48550/arXiv.1701.03056
A.W. Salehi, et al., A study of CNN and transfer learning in medical imaging: Advantages, challenges, future scope, Sustainability 15 (2023) 5930, https://doi.org/10.3390/su15075930
D. Li, et al., Deep segmentation networks for segmenting kidneys and detecting kidney stones in unenhanced abdominal CT images, Diagnostics 12 (2022) 1788, https://doi.org/10.3390/diagnostics12081788
D.-H. Jang et al., Kidney, ureter, and urinary bladder segmentation based on non-contrast enhanced computed tomography images using modified U-Net, Sci. Rep. 14 (2024) 15325, https://doi.org/10.1038/s41598-024-66045-6
T. Hatsutani, A. Ichinose, K. Nakamura, Y. Kitamura, Segmentation of Kidney Tumors on Non- Contrast CT Images Using Protuberance Detection Network, Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Interv. (MICCAI) (2023) 13, https://doi.org/10.1007/978-3-031-43990-22
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 L. A. Pérez Martínez, A. Hérnandez Trinidad, T. Córdova Fraga, R. Guzman Cabrera, A. E. López Valencia, M. A. Hernández González
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Authors retain copyright and grant the Revista Mexicana de Física right of first publication with the work simultaneously licensed under a CC BY-NC-ND 4.0 that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
