Incidence and resolution of de novo hydronephrosis after pediatric robot-assisted laparoscopic extravesical ureteral reimplantation for primary vesicoureteral reflux.

2022

517.e1-517.e5

08/2022

1873-4898

INTRODUCTION: With the advent of robot-assisted laparoscopic ureteral reimplantation (RALUR) for primary vesicoureteral reflux (VUR), understanding and minimizing its complications continues to be critical. Incidence of de novo hydronephrosis after RALUR could be indicative of an outcome that needs further study or could be a benign transient finding.

OBJECTIVE: In the present study, we hypothesized that the incidence of de novo hydronephrosis after RALUR is low and resolves spontaneously.

METHODS: An IRB-approved prospective single-institutional registry was utilized to identify all patients undergoing RALUR via an extravesical approach from 2012 to 2020. Patients with primary VUR and minimal (Grade I SFU) or no hydronephrosis prior to surgery were included. Patients who had other associated pathology or underwent concomitant procedures were excluded. Preoperative characteristics including VUR and hydronephrosis grades as well as post-operative clinical details and hydronephrosis grades were aggregated and analyzed.

RESULTS: 86/172 (50%) patients (133 ureters), with median reflux grade of 3 (IQR: G2, G3) met the inclusion criteria. Patients underwent RALUR at a median age of 5.7 years (IQR: 3.4, 8.7) with median 36.2 months (IQR: 19.6, 63.6) follow-up. Renal ultrasound at 4-6 weeks post-op showed de novo hydronephrosis in 18 (13.5%) ureters; the complete resolution was seen in 13 ureters (72%) at a median of 4.5 months from surgery. Among the 5 with non-resolved hydronephrosis (SFU G2:4, G3:1), 2 patients (3 ureters) underwent subsequent interventions.

DISCUSSION: The present study evaluating the natural history of de novo hydronephrosis after RALUR-EV performed for primary VUR, is to our knowledge the largest cohort of patients undergoing RALUR that this has been studied in. In our cohort, the incidence of de novo hydronephrosis after RALUR was 13.5%, similar to rates reported in two OUR cohorts, and significantly lower than reported incidence rates of 22-26% in several OUR cohorts, and 30% in a RALUR cohort. In the present cohort, hydronephrosis resolved spontaneously in more than 72% of cases. The median time from surgery until resolution of hydronephrosis was 4.5 (1.6, 10.5) months, which is shorter in comparison to the average time to resolution of 7.6 months, reported by Kim et al. in an earlier study.

CONCLUSIONS: De novo hydronephrosis after RALUR can be followed with serial renal ultrasounds. The majority of de novo hydronephrosis post-RALUR is transient and resolves spontaneously within a year of surgery with a very low re-intervention rate.

10.1016/j.jpurol.2022.04.005

J Pediatr Urol

35654725

Multi-institutional Validation of Improved Vesicoureteral Reflux Assessment With Simple and Machine Learning Approaches.

2022

101097JU0000000000002987

10/2022

1527-3792

PURPOSE: Vesicoureteral reflux grading from voiding cystourethrograms is highly subjective with low reliability. We aimed to demonstrate improved reliability for vesicoureteral reflux grading with simple and machine learning approaches using ureteral tortuosity and dilatation on voiding cystourethrograms.

MATERIALS AND METHODS: Voiding cystourethrograms were collected from our institution for training and 5 external data sets for validation. Each voiding cystourethrogram was graded by 5-7 raters to determine a consensus vesicoureteral reflux grade label and inter- and intra-rater reliability was assessed. Each voiding cystourethrogram was assessed for 4 features: ureteral tortuosity, proximal, distal, and maximum ureteral dilatation. The labels were then assigned to the combination of the 4 features. A machine learning-based model, qVUR, was trained to predict vesicoureteral reflux grade from these features and model performance was assessed by AUROC (area under the receiver-operator-characteristic).

RESULTS: A total of 1,492 kidneys and ureters were collected from voiding cystourethrograms resulting in a total of 8,230 independent gradings. The internal inter-rater reliability for vesicoureteral reflux grading was 0.44 with a median percent agreement of 0.71 and low intra-rater reliability. Higher values for each feature were associated with higher vesicoureteral reflux grade. qVUR performed with an accuracy of 0.62 (AUROC=0.84) with stable performance across all external data sets. The model improved vesicoureteral reflux grade reliability by 3.6-fold compared to traditional grading (001).

CONCLUSIONS: In a large pediatric population from multiple institutions, we show that machine learning-based assessment for vesicoureteral reflux improves reliability compared to current grading methods. qVUR is generalizable and robust with similar accuracy to clinicians but the added prognostic value of quantitative measures warrants further study.

10.1097/JU.0000000000002987

J Urol

36215077

Deep learning imaging features derived from kidney ultrasounds predict chronic kidney disease progression in children with posterior urethral valves.

2022

07/2022

1432-198X

BACKGROUND: We sought to use deep learning to extract anatomic features from postnatal kidney ultrasounds and evaluate their performance in predicting the risk and timing of chronic kidney disease (CKD) progression for boys with posterior urethral valves (PUV). We hypothesized that these features would predict CKD progression better than clinical characteristics such as nadir creatinine alone.

METHODS: We performed a retrospective cohort study of boys with PUV treated at two pediatric health systems from 1990 to 2021. Features of kidneys were extracted from initial postnatal kidney ultrasound images using a deep learning model. Three time-to-event prediction models were built using random survival forests. The Imaging Model included deep learning imaging features, the Clinical Model included clinical data, and the Ensemble Model combined imaging features and clinical data. Separate models were built to include time-dependent clinical data that were available at 6 months, 1 year, 3 years, and 5 years.

RESULTS: Two-hundred and twenty-five patients were included in the analysis. All models performed well with C-indices of 0.7 or greater. The Clinical Model outperformed the Imaging Model at all time points with nadir creatinine driving the performance of the Clinical Model. Combining the 6-month Imaging Model (C-index 0.7; 95% confidence interval [CI] 0.6, 0.79) with the 6-month Clinical Model (C-index 0.79; 95% CI 0.71, 0.86) resulted in a 6-month Ensemble Model that performed better (C-index 0.82; 95% CI 0.77, 0.88) than either model alone.

CONCLUSIONS: Deep learning imaging features extracted from initial postnatal kidney ultrasounds may improve early prediction of CKD progression among children with PUV. A higher resolution version of the Graphical abstract is available as Supplementary information.

10.1007/s00467-022-05677-0

Pediatr Nephrol

35867160

Computer-Aided Diagnosis of Congenital Abnormalities of the Kidney and Urinary Tract in Children Using a Multi-Instance Deep Learning Method Based on Ultrasound Imaging Data.

2020

1347-1350

2020 Apr

1945-7928

<p>Ultrasound images are widely used for diagnosis of congenital abnormalities of the kidney and urinary tract (CAKUT). Since a typical clinical ultrasound image captures 2D information of a specific view plan of the kidney and images of the same kidney on different planes have varied appearances, it is challenging to develop a computer aided diagnosis tool robust to ultrasound images in different views. To overcome this problem, we develop a multi-instance deep learning method for distinguishing children with CAKUT from controls based on their clinical ultrasound images, aiming to automatic diagnose the CAKUT in children based on ultrasound imaging data. Particularly, a multi-instance deep learning method was developed to build a robust pattern classifier to distinguish children with CAKUT from controls based on their ultrasound images in sagittal and transverse views obtained during routine clinical care. The classifier was built on imaging features derived using transfer learning from a pre-trained deep learning model with a mean pooling operator for fusing instance-level classification results. Experimental results have demonstrated that the multi-instance deep learning classifier performed better than classifiers built on either individual sagittal slices or individual transverse slices.</p>

10.1109/isbi45749.2020.9098506

Proc IEEE Int Symp Biomed Imaging

33850604

Multi-instance deep learning of ultrasound imaging data for pattern classification of congenital abnormalities of the kidney and urinary tract in children.

2020

2020 May 20

1527-9995

<p><strong>OBJECTIVE: </strong>To reliably and quickly diagnose children with posterior urethral valves (PUV), we developed a multi-instance deep learning method to automate image analysis.</p>

<p><strong>METHODS: </strong>We built a robust pattern classifier to distinguish 86 children with PUV from 71 children with mild unilateral hydronephrosis based on ultrasound images (3504 in sagittal view and 2558 in transverse view) obtained during routine clinical care.</p>

<p><strong>RESULTS: </strong>The multi-instance deep learning classifier performed better than classifiers built on either single sagittal images or single transverse images. Particularly, the deep learning classifiers built on single images in the sagittal view and single images in the transverse view obtained area under the receiver operating characteristic curve (AUC) values of 0.796±0.064 and 0.815±0.071, respectively. AUC values of the multi-instance deep learning classifiers built on images in the sagittal and transverse views with mean pooling operation were 0.949±0.035 and 0.954±0.033, respectively. The multi-instance deep learning classifiers built on images in both the sagittal and transverse views with a mean pooling operation obtained an AUC of 0.961±0.026 with a classification rate of 0.925±0.060, specificity of 0.986±0.032, and sensitivity of 0.873±0.120, respectively. Discriminative regions of the kidney located using classification activation map demonstrated that the deep learning techniques could identify meaningful anatomical features from ultrasound images.</p>

<p><strong>CONCLUSION: </strong>The multi-instance deep learning method provides an automatic and accurate means to extract informative features from ultrasound images and discriminate infants with PUV from male children with unilateral hydronephrosis.</p>

10.1016/j.urology.2020.05.019

Urology

32445770

Multi-instance Deep Learning with Graph Convolutional Neural Networks for Diagnosis of Kidney Diseases Using Ultrasound Imaging.

2019

146-154

2019 Oct

<p>Ultrasound imaging (US) is commonly used in nephrology for diagnostic studies of the kidneys and lower urinary tract. However, it remains challenging to automate the disease diagnosis based on clinical 2D US images since they provide partial anatomic information of the kidney and the 2D images of the same kidney may have heterogeneous appearance. To overcome this challenge, we develop a novel multi-instance deep learning method to build a robust classifier by treating multiple 2D US images of each individual subject as multiple instances of one bag. Particularly, we adopt convolutional neural networks (CNNs) to learn instance-level features from 2D US kidney images and graph convolutional networks (GCNs) to further optimize the instance-level features by exploring potential correlation among instances of the same bag. We also adopt a gated attention-based MIL pooling to learn bag-level features using full-connected neural networks (FCNs). Finally, we integrate both instance-level and bag-level supervision to further improve the bag-level classification accuracy. Ablation studies and comparison results have demonstrated that our method could accurately diagnose kidney diseases using ultrasound imaging, with better performance than alternative state-of-the-art multi-instance deep learning methods.</p>

10.1007/978-3-030-32689-0_15

Uncertain Safe Util Machine Learn Med Imaging Clin Image Based Proced (2019)

31893285

Automatic kidney segmentation in ultrasound images using subsequent boundary distance regression and pixelwise classification networks.

2019

101602

2019 Nov 08

1361-8423

<p>It remains challenging to automatically segment kidneys in clinical ultrasound (US) images due to the kidneys' varied shapes and image intensity distributions, although semi-automatic methods have achieved promising performance. In this study, we propose subsequent boundary distance regression and pixel classification networks to segment the kidneys automatically. Particularly, we first use deep neural networks pre-trained for classification of natural images to extract high-level image features from US images. These features are used as input to learn kidney boundary distance maps using a boundary distance regression network and the predicted boundary distance maps are classified as kidney pixels or non-kidney pixels using a pixelwise classification network in an end-to-end learning fashion. We also adopted a data-augmentation method based on kidney shape registration to generate enriched training data from a small number of US images with manually segmented kidney labels. Experimental results have demonstrated that our method could automatically segment the kidney with promising performance, significantly better than deep learning-based pixel classification networks.</p>

10.1016/j.media.2019.101602

Med Image Anal

31760193

Renal Parenchymal Area Growth Curves for Children 0 to 10 Months Old.

2016

1203-8

2016 Apr

1527-3792

<p><strong>PURPOSE: </strong>Low renal parenchymal area, which is the gross area of the kidney in maximal longitudinal length minus the area of the collecting system, has been associated with increased risk of end stage renal disease during childhood in boys with posterior urethral valves. To our knowledge normal values do not exist. We aimed to increase the clinical usefulness of this measure by defining normal renal parenchymal area during infancy.</p>

<p><strong>MATERIALS AND METHODS: </strong>In a cross-sectional study of children with prenatally detected mild unilateral hydronephrosis who were evaluated between 2000 and 2012 we measured the renal parenchymal area of normal kidney(s) opposite the kidney with mild hydronephrosis. Measurement was done with ultrasound from birth to post-gestational age 10 months. We used the LMS method to construct unilateral, bilateral, side and gender stratified normalized centile curves. We&nbsp;determined the z-score and the centile of a total renal parenchymal area of 12.4 cm(2) at post-gestational age 1 to 2 weeks, which has been associated with an&nbsp;increased risk of kidney failure before age 18 years in boys with posterior urethral valves.</p>

<p><strong>RESULTS: </strong>A total of 975 normal kidneys of children 0 to 10 months old were used to create renal parenchymal area centile curves. At the 97th centile for unilateral and single stratified curves the estimated margin of error was 4.4% to 8.8%. For&nbsp;bilateral and double stratified curves the estimated margin of error at the 97th centile was 6.6% to 13.2%. Total renal parenchymal area less than 12.4 cm(2) at post-gestational age 1 to 2 weeks had a z-score of -1.96 and fell at the 3rd percentile.</p>

<p><strong>CONCLUSIONS: </strong>These normal renal parenchymal area curves may be used to track kidney growth in infants and identify those at risk for chronic kidney disease progression.</p>

10.1016/j.juro.2015.08.097

J. Urol.

26926532