Abstract
In some patients, the passage of semi-rigid ureteroscopes up the ureter is impossible due to narrow ureteral lumen. We established a neural network to predict the inability of the ureter to accommodate the semi-rigid ureteroscope and the need for active or passive dilatation using non-contrast computed tomography (CT) images. Data were collected retrospectively from two centers of 1989 eligible patients who underwent ureteroscopic lithotripsy with ureteral stones. Patients were categorized into two groups: control and narrow ureter. The network was designed and trained for predicting a narrow ureter during initial ureteroscopic lithotripsy, which integrated multi-scale features of the ureter. The predictive efficacy of neural networks DenseNet3D, ResNet3D, ResNet3D MC, and TimeSformer was compared. Furthermore, a previous ureteroscopy or a history of double-J stent placement, ureteral wall thickness and Hounsfield unit (HU) density of the ureter under the stone were compared. Model performance was assessed based on the accuracy, area under the receiver operating characteristic curve (AUC ROC), etc. The DenseNet3D-based network achieved an AUC ROC score of 0.884 and an accuracy of 85.29%, followed by the ResNet3D-based network, the ResNet3D MC-based network, and the TimeSformer-based network. The DenseNet3D-based network significantly outperformed other candidate predictors. Furthermore, the networks were validated in an external test set. Decision curve analysis showed the clinical utility of the neural network. The neural network provides an individualized preoperative prediction of narrow ureter based on non-contrast CT images, which could be employed as part of a surgical decision-making support system.
Similar content being viewed by others
Change history
16 July 2022
A Correction to this paper has been published: https://doi.org/10.1007/s00240-022-01346-x
Abbreviations
- AUC:
-
Area under the curve
- CT:
-
Computed tomography
- CTU:
-
Computerized tomography urogram
- HU:
-
Hounsfield unit
- ROC:
-
Receiver operating characteristic curve
- SD:
-
Standard deviation
References
Kijvikai K, Haleblian GE, Preminger GM et al (2007) Shock wave lithotripsy or ureteroscopy for the management of proximal ureteral calculi: an old discussion revisited. J Urol 178:1157–1163. https://doi.org/10.1016/j.juro.2007.05.132
Viers BR, Viers LD, Hull NC et al (2015) The Difficult ureter: clinical and radiographic characteristics associated with upper urinary tract access at the time of ureteroscopic stone treatment. Urology 86:878–884. https://doi.org/10.1016/j.urology.2015.08.007
Ambani SN, Faerber GJ, Roberts WW et al (2013) Ureteral stents for impassable ureteroscopy. J Endourol 27:549–553. https://doi.org/10.1089/end.2012.0414
Mogilevkin Y, Sofer M, Margel D et al (2014) Predicting an effective ureteral access sheath insertion: a bicenter prospective study. J Endourol 28:1414–1417. https://doi.org/10.1089/end.2014.0215
Jendeberg J, Thunberg P, Liden M (2021) Differentiation of distal ureteral stones and pelvic phleboliths using a convolutional neural network. Urolithiasis 49:41–49. https://doi.org/10.1007/s00240-020-01180-z
Kobayashi M, Ishioka J, Matsuoka Y et al (2021) Computer-aided diagnosis with a convolutional neural network algorithm for automated detection of urinary tract stones on plain X-ray. BMC Urol 21:102. https://doi.org/10.1186/s12894-021-00874-9
Cummings JM, Boullier JA, Izenberg SD et al (2000) Prediction of spontaneous ureteral calculous passage by an artificial neural network. J Urol 164:326–328. https://doi.org/10.1016/S0022-5347(05)67351-X
Mishra AK, Kumar S, Dorairajan LN et al (2020) Study of ureteral and renal morphometry on the outcome of ureterorenoscopic lithotripsy: The critical role of maximum ureteral wall thickness at the site of ureteral stone impaction. Urology annals 12:212–219. https://doi.org/10.4103/UA.UA_95_19
Bulbul E, Ilki FY, Gultekin MH et al (2021) Ureteral wall thickness is an independent parameter affecting the success of extracorporeal shock wave lithotripsy treatment in ureteral stones above the iliac crest. Int J Clin Pract 75:e14264. https://doi.org/10.1111/ijcp.14264
Kachroo N, Jain R, Maskal S et al (2020) Can CT-based stone impaction markers augment the predictive ability of spontaneous stone passage? J Endourol 35:429–435. https://doi.org/10.1089/end.2020.0645
Guler Y, Erbin A, Kafkasli A et al (2021) Factors affecting success in the treatment of proximal ureteral stones larger than 1 cm with extracorporeal shockwave lithotripsy in adult patients. Urolithiasis 49:51–56. https://doi.org/10.1007/s00240-020-01186-7
Yamashita S, Kohjimoto Y, Iguchi T et al (2020) Ureteral wall volume at ureteral stone site is a critical predictor for shock wave lithotripsy outcomes: comparison with ureteral wall thickness and area. Urolithiasis 48:361–368. https://doi.org/10.1007/s00240-019-01154-w
Yoshida T, Inoue T, Omura N et al (2017) Ureteral wall thickness as a preoperative indicator of impacted stones in patients with ureteral stones undergoing ureteroscopic lithotripsy. Urology 106:45–49. https://doi.org/10.1016/j.urology.2017.04.047
Tran TY, Bamberger JN, Blum KA et al (2019) Predicting the impacted ureteral stone with computed tomography. Urology 130:43–47. https://doi.org/10.1016/j.urology.2019.04.020
Heinrich MP, Oktay O, Bouteldja N (2019) OBELISK-Net: fewer layers to solve 3D multi-organ segmentation with sparse deformable convolutions. Medical Image Anal 54:1–9. https://doi.org/10.1016/j.media.2019.02.006
Rister B, Yi D, Shivakumar K et al (2020) CT-ORG, a new dataset for multiple organ segmentation in computed tomography. Scientific Data 7:381. https://doi.org/10.1038/s41597-020-00715-8
He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. IEEE. https://doi.org/10.1109/CVPR.2016.90
Huang G, Liu Z, Laurens V et al (2016) Densely connected convolutional networks. IEEE Computer Society. https://doi.org/10.1109/CVPR.2017.243
Du T, Wang H, Torresani L, et al (2018) 'A closer look at spatiotemporal convolutions for action recognition' IEEE/CVF conference on computer vision and pattern recognition
Gedas Bertasius HW, Lorenzo Torresani (2021) Is space-time attention all you need for video understanding? (Paper presented at the proceedings of the international conference on machine learning (ICML)). https://doi.org/10.48550/arXiv.2102.05095
Fenstermaker M, Tomlins SA, Singh K et al (2020) Development and validation of a deep-learning model to assist with renal cell carcinoma histopathologic Interpretation. Urology 144:152–157. https://doi.org/10.1016/j.urology.2020.05.094
Suarez-Ibarrola R, Hein S, Reis G et al (2020) Current and future applications of machine and deep learning in urology: a review of the literature on urolithiasis, renal cell carcinoma, and bladder and prostate cancer. World J Urol 38:2329–2347. https://doi.org/10.1007/s00345-019-03000-5
Sunoqrot MRS, Selnæs KM, Sandsmark E, et al (2021) The reproducibility of deep learning-based segmentation of the prostate gland and zones on T2-weighted MR images. Diagnostics 11:1690. https://www.mdpi.com/2075-4418/11/9/1690
Herrmann P, Busana M, Cressoni M et al (2021) Using artificial intelligence for automatic segmentation of CT lung images in acute respiratory distress syndrome (Methods). Front Physiol. https://doi.org/10.3389/fphys.2021.676118
Jiang Y, Yao H, Tao S, et al (2021) Gated skip-connection network with adaptive upsampling for retinal vessel segmentation. Sensors 21:6177. https://www.mdpi.com/1424-8220/21/18/6177
Chen Y, Ruan D, Xiao J et al (2020) Fully automated multiorgan segmentation in abdominal magnetic resonance imaging with deep neural networks. Med Phys 47:4971–4982. https://doi.org/10.1002/mp.14429
De Coninck V, Keller EX, Somani B et al (2020) Complications of ureteroscopy: a complete overview. World J Urol 38:2147–2166. https://doi.org/10.1007/s00345-019-03012-1
Dong H, Peng Y, Li L et al (2018) Prevention strategies for ureteral stricture following ureteroscopic lithotripsy. Asian J Urol 5:94–100. https://doi.org/10.1016/j.ajur.2017.09.002
Acknowledgements
We gratefully acknowledge Jun Junior Wang from Computer School, Beijing Information Science and Technology University for technical support.
Funding
This work was financially supported by grants from the Science and Technology Commission of Songjiang District (Grant No.18sjkjgg13), Shanghai Pujiang Program (Grant No. 2020PJD046), Scientific and Technological Innovative Action Plan from Science and Technology Commission of Shanghai Municipality (20Y11904600).
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection, and analysis were performed by Jun Wang, Dawei Wang, Yong Wang, and Shoutong Wang. The first draft of the manuscript was written by Jun Wang and Yi Shao and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Conflict of interest
The authors declared that they have no conflict of interest.
Ethical approval
Ethics approval was obtained from the Institutional Research Ethics Board of Shanghai General Hospital. All procedures performed in studies were in accordance with the institutional ethical standards and with the 1964 Helsinki Declaration.
Informed consent
Informed consent was waived.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
The original online version of this article was revised: Author Jun Wang was incorrectly denoted as the corresponding author.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Wang, J., Wang, D., Wang, Y. et al. Predicting narrow ureters before ureteroscopic lithotripsy with a neural network: a retrospective bicenter study. Urolithiasis 50, 599–610 (2022). https://doi.org/10.1007/s00240-022-01341-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00240-022-01341-2