Six of one, half a dozen of the other: A measure of multidisciplinary inter/intra-rater reliability of the society for fetal urology and urinary tract dilation grading systems for hydronephrosis

Risk Factors for Failure of Endoscopic Balloon Dilatation of Primary Obstructive Megaureter: Single-Center 12-Year Experience with 123 Cases

Purpose: To review our experience with >100 patients with primary obstructive megaureter (POM) undergoing endoscopic balloon dilatation (EBD) and a follow-up of up to 12 years and determine potential risk factors for failure. Our hypothesis is that EBD allows for long-term treatment in >80% of patients, and its effectiveness decreases in more severe cases. Methods: This is a retrospective study of 123 consecutive patients (131 ureters) undergoing EBD from 2009 to 2021. Indications for EBD included symptoms, worsening dilatation, and/or renal function impairment. Clinical characteristics, complications, and outcomes, including those in the patients with >5-year follow-up, were described. Preoperative and intraoperative markers of severity chosen a priori were tested as risk factors for failure. Failure was defined as the need for ureteral reimplantation after EBD. Results: EBD was feasible in 121 of 123 (98%) patients, regardless of age. After a median follow-up of 38 (9-143) months, EBD was effective in 84.5% of cases. Failures generally occurred in the 1st year after EBD and were seldom associated with permanent loss of renal function. Of the 66 patients with follow-up >5 years, EBD was effective in 56 patients. No preoperative characteristic proved to be a risk factor for failure. The intraoperative absence of a ring was the only significant risk factor for failure, odd ratio 117.86 (95% confidence interval 6.27-2215.84). Conclusions: EBD was feasible and definitive treatment in 85% of our cases, regardless of age. Since this study did not identify preoperative factors to help the clinicians in patient selection, we consider EBD a viable initial procedure in all patients with POM who require surgical intervention, especially in infants.

Fetal urinary tract dilation: What to tell the parents

Urinary tract dilation (UTD), which refers to the abnormal dilation of the urinary collection system, is the most common finding on prenatal ultrasound and presents with varying severity, presentation, etiology, and prognosis. Prenatal classification and risk stratification aim to prevent postnatal complications, such as urinary tract infections and further kidney dysfunction. Parents expecting a child with UTD should be counseled by a multidisciplinary team consisting of maternal-fetal medicine specialists, and pediatric urology and nephrology providers. This review summarizes the key points in the diagnostic evaluation and management during the prenatal and initial postnatal period, focusing on the information that should be provided to future parents. We address frequently asked parental questions and concerns that our multidisciplinary clinical practice faces.

Automated Society of Fetal Urology (SFU) grading of hydronephrosis on ultrasound imaging using a convolutional neural network

INTRODUCTION

Grading of hydronephrosis severity on postnatal renal ultrasound guides management decisions in antenatal hydronephrosis (ANH). Multiple systems exist to help standardize hydronephrosis grading, yet poor inter-observer reliability persists. Machine learning methods may provide tools to improve the efficiency and accuracy of hydronephrosis grading.

OBJECTIVE

To develop an automated convolutional neural network (CNN) model to classify hydronephrosis on renal ultrasound imaging according to the Society of Fetal Urology (SFU) system as potential clinical adjunct.

STUDY DESIGN

A cross-sectional, single-institution cohort of postnatal renal ultrasounds with radiologist SFU grading from pediatric patients with and without hydronephrosis of stable severity was obtained. Imaging labels were used to automatedly select sagittal and transverse grey-scale renal images from all available studies from each patient. A VGG16 pre-trained ImageNet CNN model analyzed these preprocessed images. Three-fold stratified cross-validation was used to build and evaluate the model that was used to classify renal ultrasounds on a per patient basis into five classes based on the SFU system (normal, SFU I, SFU II, SFU III, or SFU IV). These predictions were compared to radiologist grading. Confusion matrices evaluated model performance. Gradient class activation mapping demonstrated imaging features driving model predictions.

RESULTS

We identified 710 patients with 4659 postnatal renal ultrasound series. Per radiologist grading, 183 were normal, 157 were SFU I, 132 were SFU II, 100 were SFU III, and 138 were SFU IV. The machine learning model predicted hydronephrosis grade with 82.0% (95% CI: 75-83%) overall accuracy and classified 97.6% (95% CI: 95-98%) of the patients correctly or within one grade of the radiologist grade. The model classified 92.3% (95% CI: 86-95%) normal, 73.2% (95% CI: 69-76%) SFU I, 73.5% (95% CI: 67-75%) SFU II, 79.0% (95% CI: 73-82%) SFU III, and 88.4% (95% CI: 85-92%) SFU IV patients accurately. Gradient class activation mapping demonstrated that the ultrasound appearance of the renal collecting system drove the model's predictions.

DISCUSSION

The CNN-based model classified hydronephrosis on renal ultrasounds automatically and accurately based on the expected imaging features in the SFU system. Compared to prior studies, the model functioned more automatically with greater accuracy. Limitations include the retrospective, relatively small cohort, and averaging across multiple imaging studies per patient.

CONCLUSIONS

An automated CNN-based system classified hydronephrosis on renal ultrasounds according to the SFU system with promising accuracy based on appropriate imaging features. These findings suggest a possible adjunctive role for machine learning systems in the grading of ANH.

2021 update on the urinary tract dilation (UTD) classification system: clarifications, review of the literature, and practical suggestions

In 2014, a multidisciplinary consensus on the classification of pre- and postnatal urinary tract dilation (UTD classification) was developed. Its goal was to provide a standardized system for evaluating and reporting urinary tract dilation both in the prenatal and postnatal periods. In this review, we summarize insights learned from the implementation of the UTD classification system since its inception, providing clarifications on common points of confusion. In addition, we review current literature in the clinical validation of the UTD classification system to provide credence for its use in managing fetuses and children with urinary tract dilation.

Postnatal urinary tract dilatation classification: improvement of the accuracy in predicting kidney injury

BACKGROUND

The grading of urinary tract dilatation (UTD) on postnatal sonography is a fundamental step to establish rational management for infants with antenatal hydronephrosis (ANH). The aim of this study was to compare the prediction accuracy of UTD grading systems for relevant clinical outcomes. In addition, we propose a refinement of the UTD classification by adding quantitative measurements and evaluate its impact on accuracy.

METHODS

Between 1989 and 2019, 447 infants diagnosed with isolated AHN were prospectively followed. The events of interest were surgical interventions and kidney injury. Comparison of performance of the grading systems and the impact on the accuracy of a modified UTD classification (including the size of the kidney parenchyma) was assessed by the area under the receiver-operating characteristic curve (AUC).

RESULTS

Of 447 infants, 131 (29%) underwent surgical intervention and 26 (5.8%) had developed kidney injury. The median follow-up time was 9 years (IQ range, 7-12 years). The performance for detecting the need for surgical intervention was excellent for all grading systems (AUC > 0.90). However, for predicting kidney injury, the modified UTD classification exhibited significant improvement in accuracy (AUC = 0.913, 95%CI, 0.883-0.937) as compared with UTD classification (AUC = 0.887, 95%CI, 0.854-0.915) (P = 0.027).

CONCLUSIONS

Our study confirms that the hydronephrosis grading systems provide excellent accuracy in discriminating patients who need surgical intervention among infants with AHN. Our findings suggest that the inclusion of kidney parenchymal thickness to UTD classification might increase the accuracy for predicting infants who may develop kidney injury. A higher resolution version of the Graphical abstract is available as Supplementary information.

Urinary Tract Dilation in the Fetus and Neonate

Urinary tract dilation (UTD), previously known as hydronephrosis, is the most common congenital condition identified on prenatal ultrasonography. UTD can be physiologic and resolve spontaneously or can be caused by various congenital anomalies of the urinary tract, which can lead to renal failure if not treated properly. In 2014, a multidisciplinary consensus group established UTD definitions, a classification system, and a standardized scheme for perinatal evaluation. Various imaging modalities are available to help diagnose the cause of UTD in fetuses and neonates and to help identify those patients who may benefit from fetal or early postnatal intervention. In this article, we will review the diagnosis and quantification of antenatal and postnatal UTD based on the UTD classification system, outline the imaging studies available to both evaluateUTD and determine its cause, briefly review the most common causes of UTD in the fetus and neonate, outline management strategies for UTD including the role for fetal intervention and prophylactic antibiotics, and report on the outcome and prognosis in patients with UTD.

Prenatal Hydronephrosis: Bridging Pre- and Postnatal Management

Urinary tract dilation (UTD), including hydronephrosis (HN) is the most common prenatally detected anomaly and affects up to 1-2% of pregnancies. Postnatally, it resolves without surgical intervention in approximately 75-80% of children, however this may take several years to occur, necessitating repeated clinic visits and additional invasive testing for many. For the remainder, a surgical intervention will be offered to relieve obstruction or to correct vesicoureteral reflux. During the monitoring period, many of these infants will be offered continuous antibiotic prophylaxis for the prevention of urinary tract infections, however this remains a controversial topic among pediatric urologists and nephrologists. Herein, we present an up-to-date review of the early management of prenatally detected UTD including timing of postnatal imaging, the use of antibiotics, when circumcision may be beneficial and long term outcomes of the most common HN etiologies. We also propose a decision making tool to help guide the care of infants with UTD. This article is protected by copyright. All rights reserved.

Postnatal management of children with antenatal hydronephrosis

Background

Postnatal management of infants with antenatal hydronephrosis (ANH) is still one of the most controversial issues. The majority of infants with ANH are asymptomatic with only few children who develop renal insufficiency. Thus, the biggest challenge for pediatric urologists is to distinguish children who will require further investigations and possible intervention prior to the development of symptoms, complications or renal damage in a cost effective manner without exposing them to the hazards of unnecessary investigations.

Main body

In this review article, literature on ANH were reviewed to present the current suggestions, recommendations, guidelines and their rational for postnatal management of ANH. It is agreed that a large portion of infants with ANH will improve; thus, the protocol of management is based mainly on observation and follow-up by ultrasound to detect either resolution, stabilization or worsening of hydronephrosis. The first 2 years of life are critical for this follow-up as the final picture is mostly reached during that period. Advanced imaging using voiding cystourethrography or renal scintigraphy are required for children at risk. Then, surgical intervention is selected only for a subgroup of these infants who showed worsening of hydronephrosis or renal function.

Conclusions

The protocol of management is based mainly on observation and follow-up by US to detect either resolution, stabilization or worsening of hydronephrosis. Postnatal evaluation should be performed for any neonate with a history ANH at any stage during pregnancy even if it was resolved during third trimester. Exclusion of UTI should be performed by urinalysis for all cases followed by urine culture if indicated. Serum creatinine should be performed especially in patients with bilateral ANH. US is the initial standard diagnostic imaging technique. Other imaging modalities like VCUG and nuclear renal scans may be required according to the results of the US evaluation. The most important items in decision making are the presence of bilateral or unilateral hydronephrosis, presence or absence of hydroureter, presence of lower urinary tract obstruction and degree of hydronephrosis on the initial postnatal US. Then an intervention is selected only for a subgroup of these patients who showed deterioration in renal function or degree of hydronephrosis or were complicated by UTIs. All these recommendations are based on the available literature. However, management of ANH is still a controversial issue due to lack of high evidence-based recommendations. Randomised controlled studies are still needed to provide a high level evidence for different aspects of management.

Appropriate timing of performing abdominal ultrasonography and termination of follow-up observation for antenatal grade 1 or 2 hydronephrosis

Background

Most cases of antenatal the Society of Fetal Urology (SFU) grade 1or 2 hydronephrosis (HN) improve or resolve spontaneously with conservative treatment. However, there is no consensus on the duration of follow-up for cases of grade 1or 2 HN. The aim of this study was to determine the need for continuous follow-up period and new management of children with antenatal grade 1or 2 HN.

Methods

Subjects underwent ultrasonographic assessment for HN according to the SFU classification. We retrospectively evaluated 112 patients with postnatal grade 1 HN and 69 with grade 2 HN using abdominal ultrasonography between January 2010 and December 2017. We examined the change in HN grade on repeat ultrasonography. Kaplan–Meier method was used to show the effect of HN grade on the rate of HN changes.

Results

The mean follow-up duration was 44.9 ± 36.4 months (range 12–274). Initial SFU grade 1 HN disappeared in 47.0% of cases at 12 months, 66.4% at 24 months and 73.2% at 48 months. Initial SFU grade 2 HN showed improvement in grade in 74.7% of cases at 12 months, 88.3% at 24 months and 89.5% at 48 months. However, 14.6% of SFU grade 1 and 2.8% of SFU grade 2 cases increased in grade and of the 17 cases, 16 cases worsened within the first 6 months. No cases with increased grade required pyeloplasty. Initial disappearance and later reappearance of HN occurred in 40.5% of SFU grade 1 and 2 cases. The mean duration of later reappearance of HN was 39.1 ± 36.2 months (range 12–137). No cases showed reappearance of HN after more than 1 year.

Conclusions

Ultrasonography within the first 6 months was necessary for management of children with antenatal grade 1or 2 HN, because some patients showed worsening. After that, it is considered safe to spread the follow-up interval for stable cases. Most cases of grade 1or 2 HN resolved spontaneously, however a few cases reappeared within 1 year. Therefore, ultrasonography after 1 year was necessary in children with HN that spontaneously disappeared. The appropriate time to end the follow-up was considered to have been after 1 year or more has passed since the disappearance was confirmed.

Do current scientific reports of hydronephrosis make the grade?

BACKGROUND

In December 2014, Nguyen et al. introduced the Upper Tract Dilation (UTD) classification scheme, hoping to unify multiple disciplines when describing ultrasound imaging of congenital hydronephrosis. We hypothesized that the academic community has been slow to adopt its use in publications.

PRIMARY AIM

To evaluate which hydronephrosis grading systems were currently preferred in publications.

STUDY DESIGN

A PubMed® search for hydronephrosis was performed, and abstracts between May 2017 and May 2019 were reviewed. The following data points were collected from the 197 manuscripts meeting inclusion criteria: journal, first and senior author specialty, country, type of article, primary pathology, and classification of hydronephrosis when present. Differences between use of classification system, and author specialty, manuscript type, and pathology were evaluated.

RESULTS

First and/or senior author specialties were most commonly pediatric urology, urology, pediatric surgery, and pediatric nephrology. The manuscripts were comprised of retrospective studies (48.2%), prospective studies (25.4%), case reports (15.7%), review articles (9.1%), and systematic reviews (1.5%). The most common pathologies were hydronephrosis (36.5%) and ureteropelvic junction obstruction (21.3%). Over 20% of manuscripts did not categorize hydronephrosis at all. The UTD classification was used by 5.6%, while Society for Fetal Urology (SFU) grading was used by 37.1% and Anterior-Posterior Diameter (APD) measurements by 32.5%. The Summary Table presents grading system by manuscript type, specialty, and pathology.

DISCUSSION

There is great variability in hydronephrosis grading. One potential weakness of our study is that sufficient time may not have passed for the UTD system to be adopted. Researchers may need more time to complete and publish their studies, or could be awaiting further validation of UTD utility. They could also be hesitant to change systems when it is unknown if one classification schema is superior to another, either in general or for specific diagnoses. Another weakness is that this study does not quantify what, if any, systems are used clinically. Some attempt to provide objective classification would help clarify the implications of the manuscript for research or clinical applications. Reviewers should ensure that where possible, adequate descriptions of hydronephrosis are included. Education outreach to other specialties may help increase objective grading in research.

CONCLUSIONS

The UTD system is not commonly utilized in the literature. SFU grading is applied most commonly, followed by APD measurements. Over one third of manuscripts used no classification system or descriptive terminology.

The different elements of the Urinary Tract Dilation (UTD) Classification System and their capacity to predict findings on mercaptoacetyltriglycine (MAG3) diuretic renography

INTRODUCTION

The UTD Classification System risk stratifies postnatal UTD into three groups: low risk (UTD P1), intermediate risk (UTD P2), and high risk (UTD P3). In the original consensus document, a functional scan is not recommended for UTD P1 and is left to the discretion of the clinician for UTD P2 and P3.

OBJECTIVE

This study aims to understand which patients with postnatal urinary tract dilation would benefit from a functional study. We investigated how different elements of the UTD classification system predict differential renal function (DRF) and diuretic half-life (T½) on MAG3 scan in infants undergoing evaluation for prenatally detected UTD.

STUDY DESIGN

This is a multicenter retrospective chart review of infants 6 months of age or younger evaluated for prenatal UTD, correlating their first MAG3 scan and first postnatal renal ultrasound (RUS). Multivariable logistic regression was used to find UTD elements predictive of DRF < 40% and/or T½ > 20 min.

RESULTS

A total of 517 patients met study criteria. Median age at time of RUS and MAG3 renal scan was 48 days (IGR 31-81) and 63 days (IQR 45-98), respectively. DRF < 40% was found in 6% of kidneys with UTD P2 and 35% of kidneys with UTD P3. T½ > 20 min was found in 31% of kidneys with UTD P2 and 79% of kidneys with UTD P3. An abnormal ureter (OR 2.7, 95% CI 1.2-6.0) and parenchymal thinning (OR 16, 95% CI 5.8-41.4) were significant at predicting DRF < 40%. Parenchymal thinning (OR 3.0, 95% CI 1.5-6.1) also predicted T½ > 20 min, as did each cm increase in the anterior-posterior renal pelvic diameter (APRPD) (OR 4.8, 95% CI 3.0-7.7).

DISCUSSION

The UTD system discriminates well and correlates with the likelihood of finding adverse features on diuretic renography. Patients in the UTD P3 high-risk category had a significantly higher incidence of decreased differential renal function and delayed drainage than those in UTD P1 and P2. Of the individual components of the UTD Classification system, the presence of parenchymal thinning was the most important factor in predicting both decreased differential renal function and delayed drainage.

CONCLUSION

Given the high incidence of poor function and delayed drainage seen in the UTD P3 group, we believe a functional study should be recommended in the evaluation of these patients. Our findings support leaving the performance of a functional study at the discretion of the physician for UTD P2.

Assessment of urinary tract dilation grading amongst pediatric urologists

INTRODUCTION

The Urinary Tract Dilation (UTD) system was created to address variability in hydronephrosis grading. It is unknown if or how pediatric urologists are integrating this newer system into practice.

OBJECTIVE

We sought to evaluate the current use of hydronephrosis grading systems, inter-rater reliability (IRR) for individual systems, and management preferences based on degree of hydronephrosis.

STUDY DESIGN

A survey was emailed to the Societies for Pediatric Urology listserv. Questions addressed familiarity/preference for various grading systems and respondent confidence in interpretation of hydronephrosis. Three clinical vignettes asked respondents to grade hydronephrosis using their system of choice and report further imaging they would obtain. Descriptive statistics were calculated, and IRR was calculated using a linear-weighted modified Fleiss' kappa test.

RESULTS

Response rate was 43% (n = 138). The majority of respondents used Society for Fetal Urology (SFU) (70%) or UTD (19%) systems. Most favored SFU (58%) or UTD (34%) systems for a unified system. Confidence in own interpretation was higher than confidence in radiologists' reads (median 4.4 vs 3.6, p < 0.001). IRR was substantial for UTD (κ0.68 [0.64-0.71]) and moderate for SFU (κ0.60 [0.52-0.76]). There was notable heterogeneity regarding follow-up imaging for cases. There was no difference in requested follow-up studies between SFU and UTD systems, except for fewer voiding cystourethrogram (VCUG) requests for Case 3 with UTD (28% vs 4%, p = 0.02).

CONCLUSION

Most pediatric urologists still use SFU rather than the UTD system. There was slightly higher IRR with the UTD system. There was substantial variability in follow-up imaging not related to grading system, except with low grade hydronephrosis.

Interobserver Reliability of the Antenatal Consensus Classification System for Urinary Tract Dilatation

OBJECTIVES

The consensus classification system for urinary tract dilatation (UTD) was designed to be more objective and reproducible than previously used systems. We sought to evaluate interobserver reliability of UTD components and overall scores in a prenatal population undergoing third-trimester ultrasound examinations.

METHODS

We retrospectively identified patients who underwent antenatal ultrasound examinations for UTD between 28 and 40 weeks' gestation. All images from individual studies of 300 fetuses were reviewed independently by 5 experienced sonologists (1 maternal-fetal medicine specialist and 4 radiologists). Urinary tract dilatation scores (normal, A1, or A2/3) and Society for Fetal Urology (SFU) scores were assigned. Interobserver agreement between raters was evaluated with the Fleiss κ statistic.

RESULTS

Overall interobserver agreement for the antenatal UTD risk score showed substantial agreement among all 5 readers (κ = 0.657 [95% confidence interval, 0.632, 0.683]; P < .001). All 5 readers applied the same UTD risk score in 53.7% of cases. Some variability in the antenatal UTD score and individual elements was observed. At least 2 UTD risk scores were assigned to a specific individual patient in 46.3% of cases (139 of 300), and all 3 UTD risk scores were assigned to a specific individual patient in 1.7% of cases (5 of 300). In 18.0% of cases (54 of 300), at least 2 readers assigned a UTD score different from that assigned by the other readers. Agreement was lowest for parenchymal appearance (κ = 0.225). Agreement for the SFU system was fair (κ = 0.368; P < .001).

CONCLUSIONS

Interobserver agreement for the antenatal UTD grading system was substantial. Compared to the SFU system, the antenatal UTD system showed better agreement among readers.

Supine versus prone positioning for ultrasound evaluation of postnatal urinary tract dilation in children

BACKGROUND

Ultrasound (US) is used in the initial evaluation and surveillance of urinary tract dilation in children. Urinary tract dilation is diagnosed in 1-2% of all pregnancies during routine prenatal sonography with technological advances in US imaging. Urinary tract dilation classification systems, including the 2014 multidisciplinary consensus, assess anterior-posterior renal pelvic diameter and calyceal dilation. There is no consensus regarding optimal patient positioning - supine versus prone - during US assessment of urinary tract dilation.

OBJECTIVE

We performed this study to determine whether there is a significant difference in the measurement of the anterior-posterior renal pelvic diameter, presence of calyceal dilation, or resulting urinary tract dilation consensus score obtained between supine and prone positions.

MATERIALS AND METHODS

Two raters retrospectively reviewed renal bladder US exams of children with urinary tract dilation of one or both kidneys. We included technically adequate US examinations of orthotopic kidneys that were imaged in both supine and prone positions; we excluded children with renal anomalies or prior surgery. Anterior-posterior renal pelvic diameter measurements as well as central and peripheral calyceal dilation were documented in both supine and prone positions. A postnatal urinary tract dilation consensus score was assigned to each kidney based only on these features.

RESULTS

Urinary tract dilation in either the supine or prone position was performed in 146 kidneys (69 right, 77 left) in 89 children. Median age was 0.26 years (interquartile ratio [IQR] 0.08-0.61 years). Female-to-male ratio was 1:3 (21/89). The interclass correlations of the anterior-posterior renal pelvic diameter were 0.88 and 0.87 in the supine and prone positions, respectively, without significant differences (P=0.1). When comparing all kidneys together, the mean anterior-posterior renal pelvic diameter was 7.1 mm (95% confidence interval [CI] 6.4-7.8) in supine and 7.9 (95% CI 7.1-8.7) in prone, with a mean difference between the measurements of 0.83 mm (95% CI 0.3-1.4; P=0.16). Central calyceal and peripheral calyceal dilation were more commonly found in the prone position versus the supine position in both kidneys. Central calyceal dilation was observed in 15 cases in the prone but not in the supine position. In one kidney, it was seen only in the supine but not in the prone position. Overall the urinary tract dilation score differed between positions in 10.3% (15/146) of cases, most of them (14/15) with a higher score in prone compared to the supine position.

CONCLUSION

Scanning in prone position tends to more frequently show calyceal dilation and a greater size of the anterior-posterior renal pelvic diameter, resulting in higher urinary tract dilation classification scores, with almost perfect interobserver agreement.

Using Deep Learning Algorithms to Grade Hydronephrosis Severity: Toward a Clinical Adjunct

Grading hydronephrosis severity relies on subjective interpretation of renal ultrasound images. Deep learning is a data-driven algorithmic approach to classifying data, including images, presenting a promising option for grading hydronephrosis. The current study explored the potential of deep convolutional neural networks (CNN), a type of deep learning algorithm, to grade hydronephrosis ultrasound images according to the 5-point Society for Fetal Urology (SFU) classification system, and discusses its potential applications in developing decision and teaching aids for clinical practice. We developed a five-layer CNN to grade 2,420 sagittal hydronephrosis ultrasound images [191 SFU 0 (8%), 407 SFU I (17%), 666 SFU II (28%), 833 SFU III (34%), and 323 SFU IV (13%)], from 673 patients ranging from 0 to 116.29 months old (M age = 16.53, SD = 17.80). Five-way (all grades) and two-way classification problems [i.e., II vs. III, and low (0-II) vs. high (III-IV)] were explored. The CNN classified 94% (95% CI, 93-95%) of the images correctly or within one grade of the provided label in the five-way classification problem. Fifty-one percent of these images (95% CI, 49-53%) were correctly predicted, with an average weighted F1 score of 0.49 (95% CI, 0.47-0.51). The CNN achieved an average accuracy of 78% (95% CI, 75-82%) with an average weighted F1 of 0.78 (95% CI, 0.74-0.82) when classifying low vs. high grades, and an average accuracy of 71% (95% CI, 68-74%) with an average weighted F1 score of 0.71 (95% CI, 0.68-0.75) when discriminating between grades II vs. III. Our model performs well above chance level, and classifies almost all images either correctly or within one grade of the provided label. We have demonstrated the applicability of a CNN approach to hydronephrosis ultrasound image classification. Further investigation into a deep learning-based clinical adjunct for hydronephrosis is warranted.

Grading of Hydronephrosis: An Ongoing Challenge

The crucial point for prompt diagnostics, ideal therapeutic approach, and follow-up of hydronephrosis associated with UPJ anomalies in children is the severity of hydronephrosis. Such many hydronephrosis grading systems as AP diameter, SFU, radiology, UTD, and Onen have been developed to evaluate hydronephrosis severity in infants. Unfortunately, it is still an ongoing challenge and there is no consensus between different disciplines. AP diameter is a very dynamic parameter and is affected by many factors (hydration, bladder filling, position, respiration). More importantly, its measurement is very variable and misleading due to different renal pelvic configurations. The radiology grading system has the same grades 1, 2, and 3 as the SFU grading system with addition of the AP diameter for the first 3 grades. This grading system divides parenchymal loss into two different grades. Grade 4 represents mild parenchymal loss while grade 5 suggests severe parenchymal loss. However, it is operator dependent, is not decisive, and does not differentiate grades 4 and 5 clearly. All grades of SFU are very variable between operators and clinicians. UTD classification aims to put all significant abnormal urinary findings together including the kidney, ureter, and bladder and thus determines the risk level for infants with any urinary disease. Different renal deterioration risks occur depending on the mechanism of hydronephrosis. Therefore, SFU and UTD classification may result in significant confusion and misleading in determining the severity of hydronephrosis. SFU-4 and UTD-P3 represent a considerable range of severity of hydronephrosis. Both represent minimal thinning of the medullary parenchyma and severe thinning of the cortical parenchyma (cyst-like hydronephrotic kidneys) at the same grade. The wide definition of SFU-4 and UTD-P3 fails to indicate accurately the severity of hydronephrosis and thus significantly misleads from a prompt treatment. They do not suggest who need surgical treatment and who can safely be followed non-operatively. The anatomy and physiology of the 4 suborgans of the kidney (renal pelvis, calices, medulla, and cortex) are completely different from each other. Therefore, each part of the kidney affect and behave differently as a response to UPJ-type hydronephrosis (UPJHN) depending on the severity of hydronephrosis. The upgraded Onen hydronephrosis grading system has been developed based on this basic evidence both for prenatal and post-natal periods. The Onen grading system determines specific detailed findings of significant renal damage, which clearly show and suggest who can safely be followed conservatively from who will need surgical intervention for UPJHN. Neither AP diameter nor radiology, SFU, or UTD classification is the gold standard in determining the severity of hydronephrosis. All these grading systems are based on subjective parameters and are affected by many factors. They do not determine the exact severity of UPJHN and thus cause permanent renal damage due to a delay in surgical decision in some infants while they may cause an unnecessary surgery in others. The Onen grading system has resolved all disadvantages of other grading systems and promises a safer follow-up and a prompt treatment for UPJHN. It is an accurate and easily reproducible grading that has high sensitivity and specificity.

Prognostic significance of maternal urinary carbohydrate antigen 19-9 for antenatal diagnosis of posterior urethral valve associated with fetal hydronephrosis

PURPOSE

To evaluate the predictive role of maternal urinary CA 19-9 as a non-invasive marker for diagnosing antenatal posterior urethral valve (PUV).

METHODS

A total of 40 women in the third pregnancy trimester were enrolled. Case group (group A) consisted of 20 women with a diagnosis of antenatal PUV. Twenty women with similar gestational age, fetal sex, normal US, and no history of congenital anomalies were chosen as a control group (group B). Maternal urine samples were collected and urinary CA 19-9 was measured in both groups. The correlations between maternal urinary CA 19-9 and APD (measured during pregnancy and the initial evaluation of the newborn) were assessed. CA 19-9 level in first urine of neonates was also evaluated.

RESULTS

The mean ± SD of maternal urine CA 19-9 was higher in PUV group compared to the control group (131.6 ± 23.8 vs. 13 ± 2.7 U/mL). In addition, there was a significant correlation between maternal urinary CA 19-9 and the APD measured at the third trimester (p < 0.001) and the initial evaluation of fetus after birth according to SFU grading system (p < 0.001). However, no significant difference was found between gestational age and urinary CA 19-9 level (p = 0.34). There was also a significant correlation between the CA 19-9 level in first urine of neonates and CA 19-9 level of maternal urine (p < 0.001).

CONCLUSIONS

This is the first time that maternal urinary CA 19-9 has been applied as a noninvasive and practical diagnostic marker in antenatal PUV.

Rater reliability of postnatal urinary tract dilation consensus classification

BACKGROUND

A multidisciplinary urinary tract dilation (UTD) classification system was published in 2014 to standardize definitions and renal/bladder ultrasound image interpretation.

OBJECTIVE

To evaluate intra- and inter-rater reliability of this system on postnatal RBUS.

MATERIALS AND METHODS

Renal/bladder US of 60 infants (<12 months) with urinary tract dilation were anonymized, retrospectively reviewed and scored twice using the UTD classification system by a pediatric urologist and four pediatric radiologists. Exams included supine and prone images of each kidney. Raters recorded the anterior posterior renal pelvis diameter in each position; and when present calyceal dilation (central and peripheral), ureteral dilation, parenchymal and bladder abnormalities. A UTD score was given to each kidney based on these components.

RESULTS

Intraclass correlation (ICC) of anterior posterior renal pelvis diameter measures was 0.99 (P<0.001). Intra-rater reliability for the anterior posterior renal pelvis diameter of each kidney was high, with ICC >0.95 (P<0.001). Inter-rater kappa values for UTD scores of both kidneys ranged from 0.60 to 0.77 (P <0.001). Intra-rater kappa values for UTD scores of both kidneys ranged from 0.74 to 0.92 (P <0.001). Of the six categories comprising the UTD score, discrepancy between raters was highest for interpretation of central and peripheral calyceal dilation.

CONCLUSION

Present inter- and intra-rater reliability findings were similar to those previously reported for grading systems for urinary tract dilation. Across these studies, kappa values are generally lower than the 0.8 cut-off advocated for medical measures. Here, calyceal dilation commonly determined the kidney UTD score and was also the source of greatest discrepancy between raters. Improving consistency of calyceal dilation interpretation may improve UTD consensus score reliability.

Hydronephrosis After Pyeloplasty: "Will It Go Away?"

OBJECTIVE

To identify attributes of pediatric patients with hydronephrosis due to ureteropelvic junction obstruction and of their surgical encounters which are predictive of resolution of dilatation in order to provide more effective counseling about expected outcomes. This study was inspired by the suggestion in recent literature that greater than 20% improvement in anteroposterior diameter (APD) of the renal pelvis after pyeloplasty is indicative of resolution of obstruction. The remaining dilatation, however, is often distressing to caregivers, and there are no data to guide clinicians in counseling about its likelihood to resolve.

METHODS

We retrospectively reviewed children who underwent surgery at our institution for ureteropelvic junction obstruction between 1/01/2010 and 6/30/2017. APD of the pre- (preAPD) and postoperative (postAPD) renal pelves were documented. In children with more than 1 postoperative ultrasound, lastAPD was the measurement on their most recent study. Appropriate statistical tests examined the effects of clinical and surgical variables on hydronephrosis resolution.

RESULTS

PostAPD and lastAPD were obtained at medians of 3 months and 1.9 years after surgery, and were 0 cm in 12 of 105 (11.5%) and 9 of 65 (13.8%) patients, respectively. None of the variables analyzed significantly impacted complete resolution at either time point. Of those that did not resolve, 80.6% (75/93) showed greater than 20% improvement in APD; however, 3 of these children required reoperation due to secondary obstruction. In our study, no one with APD reduction greater than 43% required reintervention.

CONCLUSION

Complete resolution of hydronephrosis is uncommon and unpredictable. All caregivers should be counseled to expect dilatation to persist after obstruction is corrected.

Society for Fetal Urology Classification vs Urinary Tract Dilation Grading System for Prognostication in Prenatal Hydronephrosis: A Time to Resolution Analysis

PURPOSE

The Urinary Tract Dilation grading system for prenatal hydronephrosis was introduced to address potential shortcomings of the Society for Fetal Urology classification. Hydronephrosis resolution is an important patient outcome and is frequently discussed during family counseling. We compared these 2 grading systems and their ability to predict time to hydronephrosis resolution.

MATERIALS AND METHODS

We prospectively screened 855 patients with prenatal hydronephrosis due to ureteropelvic junction obstruction-like hydronephrosis, nonrefluxing primary megaureter or vesicoureteral reflux between 2009 and 2015. Of the patients 454 were excluded due to surgery, late referral, absence of postnatal dilatation or presence of other anomalies, resulting in 401 eligible patients (of whom 81% were male) to be included for analyses. Hydronephrosis grades collected at baseline and last followup were compared to identify resolution trends through time. Hydronephrosis resolution was defined as renal pelvis anteroposterior diameter 10 mm or less at last followup. Time to resolution was analyzed using Cox proportion regression.

RESULTS

Of 401 patients 328 (82%) had resolution during a mean ± SD followup of 24 ± 18 months (maximum 107). Cumulative resolution rate at 3 years was 98% for Society for Fetal Urology grade I hydronephrosis, 87% for grade II, 76% for grade III and 57% for grade IV. The 3-year hydronephrosis resolution rate was 90% for Urinary Tract Dilation postnatal grade 1 (low risk), 81% for grade 2 (intermediate risk) and 71% for grade 3 (high risk).

CONCLUSIONS

Patients with distinctive baseline hydronephrosis grades (classified by Society for Fetal Urology or Urinary Tract Dilation system) had significantly different resolution times for hydronephrosis (p <0.001). Counseling families regarding time to resolution of prenatal hydronephrosis should remain the same whether using Society for Fetal Urology or Urinary Tract Dilation grading system.

Advances in paediatric urology

Paediatric urological surgery is often required for managing congenital and acquired disorders of the genitourinary system. In this Series paper, we highlight advances in the surgical management of six paediatric urological disorders. The management of vesicoureteral reflux is evolving, with advocacy ranging from a less interventional assessment and antimicrobial prophylaxis to surgery including endoscopic injection of a bulking agent and minimally invasive ureteric reimplantation. Evidence supports early orchidopexy to improve fertility and reduce malignancy in boys with undescended testes. A variety of surgical techniques have been developed for hypospadias, with excellent outcomes for distal but not proximal hypospadias. Pelvi-ureteric junction obstruction is mostly detected prenatally; indications for surgery have been refined with evidence, and minimally invasive pyeloplasty is now standard. The outlook for patients with neurogenic bladder has been transformed by a combination of clean intermittent catheterisation, algorithms of diagnostic investigations, and innovative medical and surgical therapies. Posterior urethral valves are associated with considerable mortality; fetal diagnosis allows stratification of candidates for intervention, but ongoing bladder dysfunction in patients after valve ablation remains a cause of long-term morbidity.

Associations of Initial Society for Fetal Urology Grades and Urinary Tract Dilatation Risk Groups with Clinical Outcomes in Patients with Isolated Prenatal Hydronephrosis

PURPOSE

There are limited comparative data on the predictive value of the 2 most commonly used classification systems, that is SFU (Society for Fetal Urology) hydronephrosis grades and urinary tract dilatation risk groups, in regard to the future risk of surgical intervention and the development of febrile urinary tract infection. We explored this topic in infants with isolated hydronephrosis.

MATERIALS AND METHODS

After screening 938 patients with prenatal hydronephrosis from 2009 to 2016 we selected 322 patients with ureteropelvic junction obstruction-like hydronephrosis for study. Hydronephrosis grades were prospectively collected at baseline, surgery and last followup. Gender, circumcision status, antibiotic prophylaxis and renal pelvis anteroposterior diameter were captured. The primary outcome was pyeloplasty and the development of febrile urinary tract infection. Comparative analyses between SFU grades/urinary tract dilatation groups and the primary outcome were performed with the Fisher exact and log rank tests.

RESULTS

Mean ± SD age at presentation was 3.3 ± 2.6 months and mean followup was 22 ± 19 months. Pyeloplasty was performed in 32% of patients with SFU III/IV vs 31% with urinary tract dilatation 2/3. The rate of febrile urinary tract infection in patients with SFU III/IV was similar to that in those with urinary tract dilatation group 2/3 (8% vs 10%). Children with SFU III/IV showed a significantly higher rate of surgery than those with SFU I/II (32% vs 2%, p <0.01). Similar findings were seen when using urinary tract dilatation groups to compare patients at low risk (1) vs moderate/high risk (2/3).

CONCLUSIONS

Both grading systems equally allowed for proper risk stratification and prediction of clinical outcomes based on baseline ultrasound. They correctly separated most infants who underwent surgery or in whom febrile urinary tract infection developed from those who could be treated nonsurgically. Use of the new urinary tract dilatation classification should not affect how families of children with isolated hydronephrosis are counseled regarding surgical intervention and the risk of febrile urinary tract infection.