1
|
Jang DH, Lee J, Jeon YJ, Yoon YE, Ahn H, Kang BK, Choi WS, Oh J, Lee DK. Kidney, ureter, and urinary bladder segmentation based on non-contrast enhanced computed tomography images using modified U-Net. Sci Rep 2024; 14:15325. [PMID: 38961140 PMCID: PMC11222420 DOI: 10.1038/s41598-024-66045-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2023] [Accepted: 06/26/2024] [Indexed: 07/05/2024] Open
Abstract
This study was performed to segment the urinary system as the basis for diagnosing urinary system diseases on non-contrast computed tomography (CT). This study was conducted with images obtained between January 2016 and December 2020. During the study period, non-contrast abdominopelvic CT scans of patients and diagnosed and treated with urinary stones at the emergency departments of two institutions were collected. Region of interest extraction was first performed, and urinary system segmentation was performed using a modified U-Net. Thereafter, fivefold cross-validation was performed to evaluate the robustness of the model performance. In fivefold cross-validation results of the segmentation of the urinary system, the average dice coefficient was 0.8673, and the dice coefficients for each class (kidney, ureter, and urinary bladder) were 0.9651, 0.7172, and 0.9196, respectively. In the test dataset, the average dice coefficient of best performing model in fivefold cross validation for whole urinary system was 0.8623, and the dice coefficients for each class (kidney, ureter, and urinary bladder) were 0.9613, 0.7225, and 0.9032, respectively. The segmentation of the urinary system using the modified U-Net proposed in this study could be the basis for the detection of kidney, ureter, and urinary bladder lesions, such as stones and tumours, through machine learning.
Collapse
Affiliation(s)
- Dong-Hyun Jang
- Department of Public Healthcare Service, Seoul National University Bundang Hospital, Seongnam, Republic of Korea
| | - Juncheol Lee
- Department of Emergency Medicine, College of Medicine, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763, Republic of Korea
| | | | - Young Eun Yoon
- Department of Urology, College of Medicine, Hanyang University, Seoul, Republic of Korea
| | - Hyungwoo Ahn
- Department of Radiology, Seoul National University Bundang Hospital, Seongnam, Republic of Korea
| | - Bo-Kyeong Kang
- Department of Radiology, College of Medicine, Hanyang University, Seoul, Republic of Korea
| | - Won Seok Choi
- Department of Radiology, Seoul National University Bundang Hospital, Seongnam, Republic of Korea
| | - Jaehoon Oh
- Department of Emergency Medicine, College of Medicine, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763, Republic of Korea.
| | - Dong Keon Lee
- Department of Emergency Medicine, Seoul National University Bundang Hospital, 13620, 82, Gumi-ro 173 Beon-gil, Bundang-gu, Seongnam-si, Gyeonggi-do, Republic of Korea.
- Department of Emergency Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea.
| |
Collapse
|
2
|
Hayashi K, Shigemura K, Tanimoto H, Kumagai K, Gonzales RR, Yang YM, Maeda K, Matsuyama H, Fujisawa M. Establishment of an artificial urine model in vitro and rat or pig model in vivo to evaluate urinary crystal adherence. Sci Rep 2024; 14:12001. [PMID: 38796538 PMCID: PMC11127959 DOI: 10.1038/s41598-024-62766-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/26/2023] [Accepted: 05/21/2024] [Indexed: 05/28/2024] Open
Abstract
The current study aimed to establish an experimental model in vitro and in vivo of urinary crystal deposition on the surface of ureteral stents, to evaluate the ability to prevent crystal adhesion. Non-treated ureteral stents were placed in artificial urine under various conditions in vitro. In vivo, ethylene glycol and hydroxyproline were administered orally to rats and pigs, and urinary crystals and urinary Ca were investigated by Inductively Coupled Plasma-Optical Emission Spectrometer. in vitro, during the 3- and 4-week immersion periods, more crystals adhered to the ureteral stent in artificial urine model 1 than the other artificial urine models (p < 0.01). Comparing the presence or absence of urea in the composition of the artificial urine, the artificial urine without urea showed less variability in pH change and more crystal adhesion (p < 0.05). Starting the experiment at pH 6.3 resulted in the highest amount of crystal adhesion to the ureteral stent (p < 0.05). In vivo, urinary crystals and urinary Ca increased in rat and pig experimental models. This experimental model in vitro and in vivo can be used to evaluate the ability to prevent crystal adhesion and deposition in the development of new ureteral stents to reduce ureteral stent-related side effects in patients.
Collapse
Affiliation(s)
- Kana Hayashi
- Division of Infectious Diseases, Department of Public Health, Kobe University Graduate School of Health Sciences, 7-10-2 Tomogaoka Suma-Ku, Kobe, 654-0142, Japan
| | - Katsumi Shigemura
- Department of Urology, Teikyo University Graduate School of Medicine, 2-11-1 Kaga, Itabashi-Ku, Tokyo, 173-8605, Japan.
| | - Hiroshi Tanimoto
- Division of Infectious Diseases, Department of Public Health, Kobe University Graduate School of Health Sciences, 7-10-2 Tomogaoka Suma-Ku, Kobe, 654-0142, Japan
| | - Kazuo Kumagai
- Research Center for Membrane and Film Technology, Kobe University, 1-1 Rokkodaicho, Nada-Ku, Kobe, 657-8501, Japan
- Department of Chemical Science and Engineering, Kobe University, 1-1 Rokkodaicho, Nada-Ku, Kobe, 657-8501, Japan
| | - Ralph Rolly Gonzales
- Research Center for Membrane and Film Technology, Kobe University, 1-1 Rokkodaicho, Nada-Ku, Kobe, 657-8501, Japan
| | - Young-Min Yang
- Division of Urology, Kobe University Graduate School of Medicine, 7-5-1 Kusunoki-Cho, Chuo-Ku, Kobe, 650-0017, Japan
| | - Koki Maeda
- Division of Urology, Kobe University Graduate School of Medicine, 7-5-1 Kusunoki-Cho, Chuo-Ku, Kobe, 650-0017, Japan
| | - Hideto Matsuyama
- Research Center for Membrane and Film Technology, Kobe University, 1-1 Rokkodaicho, Nada-Ku, Kobe, 657-8501, Japan
- Department of Chemical Science and Engineering, Kobe University, 1-1 Rokkodaicho, Nada-Ku, Kobe, 657-8501, Japan
| | - Masato Fujisawa
- Division of Urology, Kobe University Graduate School of Medicine, 7-5-1 Kusunoki-Cho, Chuo-Ku, Kobe, 650-0017, Japan
| |
Collapse
|
3
|
Liu Z, Yan M, Naji Y, Qiu J, Wang H, Lin Y, Dai Y. Can Double J stent encrustation be predicted by risk analysis and nomogram?: A retrospective case-control study. Medicine (Baltimore) 2024; 103:e35303. [PMID: 38215087 PMCID: PMC10783324 DOI: 10.1097/md.0000000000035303] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/16/2023] [Accepted: 08/30/2023] [Indexed: 01/14/2024] Open
Abstract
To explore the risk factors and develop a nomogram to predict Double J stent encrustation incidence. The general demographic characteristics and underlying risk factors of 248 patients with upper urinary tract calculus who underwent endoscopic lithotripsy and Double J stenting at the Fifth Affiliated Hospital of Sun Yat-Sen University between January 1st, 2018 and January 1st, 2023 were retrospectively analyzed. Among them,173 patients were randomly selected to form the development cohort. A multivariate logistic regression model was employed to identify the independent risk factors associated with Double J stent encrustation, and a nomogram was developed for predicting its occurrence. Additionally, 75 patients were randomly selected to form the validation cohort to validate the nomogram. Multivariate logistic regression analysis revealed that several factors were significantly associated with Double J stent encrustation: indwelling time (odds ratio [OR]1.051; 95% confidence interval [CI] 1.030-1.073, P < .001), urine PH (OR 2.198; 95% CI 1.061-4.539, P = .033), fasting blood glucose (OR 1.590; 95% CI 1.300-1.943, P < .001), and total cholesterol (OR 2.676; 95% CI 1.551-4618, P < .001).Based on these findings, A nomogram was developed to predict the occurrence of Double J stent encrustation. The nomogram demonstrated good performance with an area under the curve of 0.870 and 0.862 in the development and validation cohorts, respectively. Furthermore, the calibration curve indicated a well-fitted model. We constructed and validated an accessible nomogram to assist urologists in evaluating the risk factors associated with Double J stent encrustation and predicting its likelihood.
Collapse
Affiliation(s)
- Zicheng Liu
- Department of Urology, The Fifth Affiliated Hospital of Sun Yat-Sen University, Zhuhai, China
| | - Minbo Yan
- Department of Urology, The Fifth Affiliated Hospital of Sun Yat-Sen University, Zhuhai, China
| | - Yaser Naji
- Department of Urology, The Fifth Affiliated Hospital of Sun Yat-Sen University, Zhuhai, China
| | - Junliang Qiu
- Department of Urology, The Fifth Affiliated Hospital of Sun Yat-Sen University, Zhuhai, China
| | - Haojie Wang
- Department of Urology, The Fifth Affiliated Hospital of Sun Yat-Sen University, Zhuhai, China
| | - Yuteng Lin
- Department of Urology, The Fifth Affiliated Hospital of Sun Yat-Sen University, Zhuhai, China
| | - Yingbo Dai
- Department of Urology, The Fifth Affiliated Hospital of Sun Yat-Sen University, Zhuhai, China
| |
Collapse
|
4
|
Qiu J, Yan M, Wang H, Liu Z, Wang G, Wu X, Gao Q, Hu H, Chen J, Dai Y. Identifying ureteral stent encrustation using machine learning based on CT radiomics features: a bicentric study. Front Med (Lausanne) 2023; 10:1202486. [PMID: 37601775 PMCID: PMC10433756 DOI: 10.3389/fmed.2023.1202486] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2023] [Accepted: 07/12/2023] [Indexed: 08/22/2023] Open
Abstract
Obstructive To develop and validate radiomics and machine learning models for identifying encrusted stents and compare their recognition performance with multiple metrics. Methods A total of 354 patients with ureteral stent placement were enrolled from two medical institutions and divided into the training cohort (n = 189), internal validation cohort (n = 81) and external validation cohort (n = 84). Based on features selected by Wilcoxon test, Spearman Correlation Analysis and least absolute shrinkage and selection operator (LASSO) regression algorithm, six machine learning models based on radiomics features were established with six classifiers (LR, DT, SVM, RF, XGBoost, KNN). After comparison with those models, the most robust model was selected. Considering its feature importance as radscore, the combined model and a nomogram were constructed by incorporating indwelling time. Accuracy, sensitivity, specificity, area under the curve (AUC), decision curve analysis (DCA) and calibration curve were used to evaluate the recognition performance of models. Results 1,409 radiomics features were extracted from 641 volumes of interest (VOIs) and 20 significant radiomics features were selected. Considering the superior performance (AUC 0.810, 95%CI, 0.722-0.888) in the external validation cohort, feature importance of XGBoost was used as a radscore, constructing a combined model and a nomogram with indwelling time. The accuracy, sensitivity, specificity and AUC of the combined model were 98, 100, 97.3% and 0.999 for the training cohort, 83.3, 80, 84.5% and 0.867 for the internal cohort and 78.2, 76.3, 78.8% and 0.820 for the external cohort, respectively. DCA indicates the favorable clinical utility of models. Conclusion Machine learning model based on radiomics features enables to identify ureteral stent encrustation with high accuracy.
Collapse
Affiliation(s)
- Junliang Qiu
- Department of Urology, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China
| | - Minbo Yan
- Department of Urology, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China
| | - Haojie Wang
- Department of Urology, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China
| | - Zicheng Liu
- Department of Urology, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China
| | - Guojie Wang
- Department of Radiology, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China
| | - Xianbo Wu
- Department of Urology, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China
| | - Qindong Gao
- Department of Urology, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China
| | - Hongji Hu
- Department of Urology, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China
| | - Junyong Chen
- Department of Urology, Zhuhai People’s Hospital (Zhuhai Hospital Affiliated with Jinan University), Zhuhai, Guangdong, China
| | - Yingbo Dai
- Department of Urology, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China
| |
Collapse
|
5
|
Zheng S, Amado P, Obrist D, Burkhard F, Clavica F. An in vitro bladder model with physiological dynamics: Vesicoureteral reflux alters stent encrustation pattern. Front Bioeng Biotechnol 2022; 10:1028325. [PMID: 36304894 PMCID: PMC9592728 DOI: 10.3389/fbioe.2022.1028325] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2022] [Accepted: 09/22/2022] [Indexed: 11/22/2022] Open
Abstract
In vitro models are indispensable to study the physio-mechanical characteristics of the urinary tract and to evaluate ureteral stent performances. Yet previous models mimicking the urinary bladder have been limited to static or complicated systems. In this study, we designed a simple in vitro bladder model to simulate the dynamics of filling and voiding. The physio-mechanical condition of the model was verified using a pressure-flow test with different bladder outlet obstruction levels, and a reflux test was performed to qualitatively demonstrate the stent associated vesicoureteral reflux (VUR). Finally, the setup was applied with and without the bladder model to perform encrustation tests with artificial urine on commercially available double-J stents, and the volumes of luminal encrustations were quantified using micro-Computed Tomography and image segmentation. Our results suggest that, VUR is an important factor contributing to the dynamics in the upper urinary tract with indwelling stents, especially in patients with higher bladder outlet obstruction levels. The influence of VUR should be properly addressed in future in vitro studies and clinical analyses.
Collapse
Affiliation(s)
- Shaokai Zheng
- ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland
- *Correspondence: Shaokai Zheng,
| | - Pedro Amado
- ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland
| | - Dominik Obrist
- ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland
| | - Fiona Burkhard
- Department of Urology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Francesco Clavica
- ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland
- Department of Urology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| |
Collapse
|
6
|
Abstract
PURPOSE OF REVIEW Ureteral stents are an invaluable tool for urologists but suffer from several drawbacks, including: limited durability due to stent encrustation, significant morbidity from bothersome urinary symptoms, pain and infection, risk of the forgotten stent and costly removal. This review highlights key advances in ureteral stent technology that seek to address these issues. RECENT FINDINGS Over the past 2 years clinical trials have brought ureteral stent technology aimed to reduce stent-associated morbidity closer to clinical application. Stent material and changes to stent design show promise in improving patient tolerability without increasing complications. Low-tech innovations such as magnetic and catheter snare removal may quickly reduce costs. Radical advances such as biodegradable stent materials remain in preclinical models but show promise for eliminating the need for stent removal. SUMMARY The ideal ureteral stent does not currently exist in clinical practice. This review highlights key studies that have advanced ureteral stent technology in the past 2 years.
Collapse
|
7
|
Silicone vs. Polyurethane Stent: The Final Countdown. J Clin Med 2022; 11:jcm11102746. [PMID: 35628873 PMCID: PMC9142971 DOI: 10.3390/jcm11102746] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2022] [Revised: 05/02/2022] [Accepted: 05/06/2022] [Indexed: 12/04/2022] Open
Abstract
Ureteric stents are conventionally used in daily urological practice. There is ongoing debate on the superiority of different stent materials, particularly in terms of patient tolerance. We conducted a literature review to compare silicone stents and stents made of other materials from a patient tolerability perspective. We conclude that silicone stents are better tolerated but further research is required.
Collapse
|
8
|
Amitay-Rosen T, Dror I, Shilo Y, Berkowitz B. Imaging and Chemical Analysis of External and Internal Ureteral Stent Encrustation. Res Rep Urol 2022; 14:159-166. [PMID: 35493770 PMCID: PMC9045707 DOI: 10.2147/rru.s364336] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2022] [Accepted: 04/03/2022] [Indexed: 11/23/2022] Open
Abstract
Introduction Ureteral stents are effective in alleviating flow disruptions in the urinary tract, whether due to ureteral stones, strictures or extrinsic ureteral obstruction. However, significant stent encrustation on the external and/or internal stent lumen walls can occur, which may interfere with stent functioning and/or removal. Currently, there is only limited, generally qualitative, information on the distribution, mineral structure, and chemical content of these deposits, particularly in terms of stent lumen encrustation. Objective To quantify, in an initial investigation, external and internal encrustation in representative, intact ureteral stents. The study investigates possible correlations between patterns of external and internal encrustation, determines mineral structure and chemical composition, and examines the potential for stent lumen obstruction even in the absence of external stent wall encrustation. Study Design High-resolution, laboratory micro-computed tomography (micro-CT) was used to non-destructively image external and internal stent encrustation in four representative stents. X-ray diffractometry (XRD) and scanning electron microscopy–energy dispersive x-ray spectroscopy (SEM-EDS) enabled parallel analysis of mineral structure and chemical content of samples collected from external and internal encrusted material along the distal, proximal and mid-ureteral stent regions. Results Extensive stent lumen encrustation can occur within any region of a stent, with only incidental or minor external encrustation, along the entire length of the stent. External and internal encrusted materials in a given stent are generally similar, consisting of a combination of amorphous (mostly organic) and crystalline mineral deposits. Conclusion Micro-CT demonstrates that significant stent lumen encrustation can occur, which can lead to partial or full stent lumen occlusion, even when the exterior stent wall is essentially free of encrusted material.
Collapse
Affiliation(s)
- Tal Amitay-Rosen
- Department of Physical Chemistry, Institute for Biological Research, Ness-Ziona, 7410001, Israel
| | - Ishai Dror
- Department of Earth and Planetary Sciences, Weizmann Institute of Science, Rehovot, 7610001, Israel
| | - Yaniv Shilo
- Department of Urology, Kaplan Medical Center, Affiliated with the Hebrew University of Jerusalem, Rehovot, 7661041, Israel
| | - Brian Berkowitz
- Department of Earth and Planetary Sciences, Weizmann Institute of Science, Rehovot, 7610001, Israel
- Correspondence: Brian Berkowitz, Department of Earth and Planetary Sciences, Weizmann Institute of Science, Rehovot, 7610001, Israel, Tel +972-8-9342098, Fax +972-8-9344124, Email
| |
Collapse
|