Deep-learning-based diagnosis and grading of vesicoureteral reflux: A novel approach for improved clinical decision-making

Vesicoureteral reflux and deep learning

Authors

Keywords:

Vesicoureteral reflux, Voiding cystourethrography, Artificial intelligence, Convolutional neural network, Deep learning

Abstract

Background/Aim: Vesicoureteral reflux (VUR) is a condition that causes urine to flow in reverse, from the bladder back into the ureters and occasionally into the kidneys. It becomes a vital cause of urinary tract infections. Conventionally, VUR’s severity is evaluated through imaging via voiding cystourethrography (VCUG). However, there is an unresolved debate regarding the precise timing and type of surgery required, making it crucial to classify VUR grades uniformly and accurately. This study’s primary purpose is to leverage machine learning, particularly convolutional neural network (CNN), to effectively identify and classify VUR in VCUG images. The aspiration is to diminish classification discrepancies between different observers and to create an accessible tool for healthcare practitioners.

Methods: We utilized a dataset of 59 VCUG images with diagnosed VUR sourced from OpenI. These images were independently classified by two seasoned urologists according to the International Reflux Classification System. We utilized TensorFlow, Keras, and Jupyter Notebook for data preparation, segmentation, and model building. The CNN Inception V3 was employed for transfer learning, while data augmentation was used to improve the model’s resilience.

Results: The deep-learning model attained exceptional accuracy rates of 95% and 100% in validation and training, respectively, after six cycles. It effectively categorized VUR grades corresponding to the global classification system. Matplotlib tracked loss and accuracy values, while Python-based statistical analysis assessed the model’s performance using the F1-score.

Conclusion: The study’s model effectively categorized images, including those of vesicoureteral reflux, which has significant implications for treatment decisions. The application of this artificial intelligence model may help reduce interobserver bias. Additionally, it could offer an objective method for surgical planning and treatment outcomes.

Downloads

Download data is not yet available.

References

Cetin N, Gencler A, Kavaz Tufan A. Risk factors for development of urinary tract infection in children with nephrolithiasis. J Paediatr Child Health. 2020;56(1):76-80. DOI: https://doi.org/10.1111/jpc.14495

Weitz M, Schmidt M. To screen or not to screen for vesicoureteral reflux in children with ureteropelvic junction obstruction: a systematic review. Eur J Pediatr. 2017;176(1):1-9. DOI: https://doi.org/10.1007/s00431-016-2818-3

Wadie GM, Moriarty KP. The impact of vesicoureteral reflux treatment on the incidence of urinary tract infection. Pediatr Nephrol. 2012;27(4):529-38. DOI: https://doi.org/10.1007/s00467-011-1809-x

Siomou E, Giapros V, Serbis A, Makrydimas G, Papadopoulou F. Voiding urosonography and voiding cystourethrography in primary vesicoureteral reflux associated with mild prenatal hydronephrosis: a comparative study. Pediatr Radiol. 2020;50(9):1271-6. DOI: https://doi.org/10.1007/s00247-020-04724-y

Baydilli N, Selvi I, Pinarbasi AS, Akinsal EC, Demirturk HC, Tosun H, et al. Additional VCUG-related parameters for predicting the success of endoscopic injection in children with primary vesicoureteral reflux. J Pediatr Urol. 2021;17(1):68.e1-68.e8. DOI: https://doi.org/10.1016/j.jpurol.2020.11.018

Schaeffer AJ, Greenfield SP, Ivanova A, Cui G, Zerin JM, Chow JS, et al. Reliability of grading of vesicoureteral reflux and other findings on voiding cystourethrography. J Pediatr Urol. 2017;13(2):192-8. DOI: https://doi.org/10.1016/j.jpurol.2016.06.020

Çelebi S, Özaydın S, Baştaş CB, Kuzdan Ö, Erdoğan C, Yazıcı M, et al. Reliability of the Grading System for Voiding Cystourethrograms in the Management of Vesicoureteral Reflux: An Interrater Comparison. Adv Urol. 2016;2016:1684190. DOI: https://doi.org/10.1155/2016/1684190

Ilhan HO, Sigirci IO, Serbes G, Aydin N. A fully automated hybrid human sperm detection and classification system based on mobile-net and the performance comparison with conventional methods. Med Biol Eng Comput. 2020;58(5):1047-68. DOI: https://doi.org/10.1007/s11517-019-02101-y

Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, et al. TensorFlow: large-scale machine learning on heterogeneous distributed systems V2 (Version 2). 2016, March 16. http://arxiv.org/abs/1603.04467.

Kluyver T, Ragan-Kelley B, Pérezc F, Granger B, Bussonnier M, Frederic J, et al. Jupyter Notebooks – a publishing format for reproducible computational workflows. In: Loizides F, Schmidt B, eds. Positioning and Power in Academic Publishing: Players, Agents and Agendas. Amsterdam, IOS Press; 2016:87-90. doi: 10.3233/978-1-61499-649-1-87.

Johnson J. Cnn-benchmarks. Accessed 13 March 2023. https://github.com/jcjohnson/cnn-benchmarks/;2023.

Wang S, Summers RM. Machine learning and radiology. Med Image Anal. 2012;16(5):933-51. DOI: https://doi.org/10.1016/j.media.2012.02.005

Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE; 2016:2818-26. DOI: https://doi.org/10.1109/CVPR.2016.308

Kingma DP, Ba J. Adam: a method for stochastic optimization. In: Bengio Y, LeCun Y, eds. Proceedings of the 3rd International Conference on Learning Representations. San Diego, CA: USA; 2015:1-15. https://arxiv.org/abs/1412.6980

Meena J, Hari P. Vesicoureteral reflux and recurrent urinary tract infections. Asian J. Pediatric Nephrol. 2019;2:61-70. DOI: https://doi.org/10.4103/AJPN.AJPN_26_19

De Palma D. Radionuclide Tools in Clinical Management of Febrile UTI in Children. Semin Nucl Med. 2020;50(1):50-5. DOI: https://doi.org/10.1053/j.semnuclmed.2019.10.003

Fazal MI, Patel ME, Tye J, Gupta Y. The past, present and future role of artificial intelligence in imaging. Eur J Radiol. 2018;105:246-50. DOI: https://doi.org/10.1016/j.ejrad.2018.06.020

Batuello JT, Gamito EJ, Crawford ED, Han M, Partin AW, McLeod DG, et al. Artificial neural network model for the assessment of lymph node spread in patients with clinically localized prostate cancer. Urology. 2001;57(3):481-5. DOI: https://doi.org/10.1016/S0090-4295(00)01039-6

Poulakis V, Witzsch U, de Vries R, Emmerlich V, Meves M, Altmannsberger HM, et al. Preoperative neural network using combined magnetic resonance imaging variables, prostate-specific antigen, and Gleason score for predicting prostate cancer biochemical recurrence after radical prostatectomy. Urology. 2004;64(6):1165-70. DOI: https://doi.org/10.1016/j.urology.2004.06.030

Wu S, Chen X, Pan J, Dong W, Diao X, Zhang R, et al. An artificial intelligence system for the detection of bladder cancer via cystoscopy: a multicenter diagnostic study. J Natl Cancer Inst. 2022;114(2):220–7. DOI: https://doi.org/10.1093/jnci/djab179

Fenstermaker M, Tomlins SA, Singh K, Wiens J, Morgan TM. Development and Validation of a Deep-learning Model to Assist with Renal Cell Carcinoma Histopathologic Interpretation. Urology. 2020;144:152-7. DOI: https://doi.org/10.1016/j.urology.2020.05.094

Hobbs KT, Choe N, Aksenov LI, Reyes L, Aquino W, Routh JC, et al. Machine Learning for Urodynamic Detection of Detrusor Overactivity. Urology. 2022;159:247-54. DOI: https://doi.org/10.1016/j.urology.2021.09.027

Katz JE, Abdelrahman L, Nackeeran S, Ezeh U, Visser U, Deane LA. The Development of an Artificial Intelligence Model Based Solely on Computer Tomography Successfully Predicts Which Patients Will Pass Obstructing Ureteral Calculi. Urology. 2023;174:58-63. DOI: https://doi.org/10.1016/j.urology.2023.01.025

Çelik Ö, Aslan AF, Osmanoğlu UÖ, Çetin N, Tokar B. Estimation of renal scarring in children with lower urinary tract dysfunction by utilizing resampling technique and machine learning algorithms. J Surg Med. 2020;4(7):573-7. DOI: https://doi.org/10.28982/josam.691768

Lorenzo AJ, Rickard M, Braga LH, Guo Y, Oliveria JP. Predictive Analytics and Modeling Employing Machine Learning Technology: The Next Step in Data Sharing, Analysis, and Individualized Counseling Explored with a Large, Prospective Prenatal Hydronephrosis Database. Urology. 2019;123:204-9. DOI: https://doi.org/10.1016/j.urology.2018.05.041

Serel A, Ozturk SA, Soyupek S, Serel HB. Deep Learning in Urological Images Using Convolutional Neural Networks: An Artificial Intelligence Study. Turk J Urol. 2022 Jul;48(4):299-302. DOI: https://doi.org/10.5152/tud.2022.22030

Serrano-Durba A, Serrano AJ, Magdalena JR, Martín JD, Soria E, Domínguez C, et al. The use of neural networks for predicting the result of endoscopic treatment for vesico-ureteric reflux. BJU Int. 2004;94:120–2. DOI: https://doi.org/10.1111/j.1464-410X.2004.04912.x

Seckiner I, Seckiner SU, Erturhan S, Erbagci A, Solakhan M, Yagci F. The use of artificial neural networks in decision support in vesicoureteral reflux treatment. Urol Int. 2008;80(3):283-6. doi: 10.1159/000127342. DOI: https://doi.org/10.1159/000127342

Khondker A, Kwong JCC, Yadav P, Chan JYH, Singh A, Skreta M, et al. Multi-institutional Validation of Improved Vesicoureteral Reflux Assessment With Simple and Machine Learning Approaches. J Urol. 2022 Dec;208(6):1314-22. DOI: https://doi.org/10.1097/JU.0000000000002987

Khondker A, Kwong JCC, Rickard M, Skreta M, Keefe DT, Lorenzo AJ, et al. A machine learning-based approach for quantitative grading of vesicoureteral reflux from voiding cystourethrograms: Methods and proof of concept. J Pediatr Urol. 2022 Feb;18(1):78.e1-78.e7. DOI: https://doi.org/10.1016/j.jpurol.2021.10.009

Downloads

Published

2024-01-17

Issue

Section

Research Article

How to Cite

1.
Ergün O, Serel TA, Öztürk SA, Serel HB, Soyupek S, Hoşcan B. Deep-learning-based diagnosis and grading of vesicoureteral reflux: A novel approach for improved clinical decision-making: Vesicoureteral reflux and deep learning. J Surg Med [Internet]. 2024 Jan. 17 [cited 2024 Feb. 21];8(1):12-6. Available from: https://jsurgmed.com/article/view/8020