Gravity-assisted drainage imaging in the assessment of pediatric hydronephrosis

Deep learning of renal scans in children with antenatal hydronephrosis

INTRODUCTION

Antenatal hydronephrosis (ANH) is one of the most common anomalies identified on prenatal ultrasound, found in up to 4.5% of all pregnancies. Children with ANH are surveilled with repeated renal ultrasound and when there is high suspicion for a ureteropelvic junction obstruction on renal ultrasound, a mercaptuacetyltriglycerine (MAG3) Lasix renal scan is performed to evaluate for obstruction. However, the challenging interpretation of MAG3 renal scans places patients at risk of misdiagnosis.

OBJECTIVE

Our objective was to analyze MAG3 renal scans using machine learning to predict renal complications. We hypothesized that our deep learning model would extract features from MAG3 renal scans that can predict renal complications in children with ANH.

STUDY DESIGN

We performed a case-control study of MAG3 studies drawn from a population of children with ANH concerning for ureteropelvic junction obstruction evaluated at our institution from January 2009 until June of 2021. The outcome was renal complications that occur ≥6 months after an equivocal MAG-3 renal scan. We created two machine learning models: a deep learning model using the radiotracer concentration versus time data from the kidney of interest and a random forest model created using clinical data. The performance of the models was assessed using measures of diagnostic accuracy.

RESULTS

We identified 152 eligible patients with available images of which 62 were cases and 90 were controls. The deep learning model predicted future renal complications with an overall accuracy of 73% (95% confidence inteveral [CI] 68-76%) and an AUC of 0.78 (95% CI 0.7, 0.84). The random forest model had an accuracy of 62% (95% CI 60-66%) and an AUC of 0.67 (95% CI. 0 64, 0.72) DISCUSSION: Our deep learning model predicted patients at high risk of developing renal complications following an equivocal renal scan and discriminate those at low risk with moderately high accuracy (73%). The deep learning model outperformed the clinical model built from clinical features classically used by urologists for surgical decision making.

CONCLUSION

Our models have the potential to influence clinical decision making by providing supplemental analytical data from MAG3 scans that would not otherwise be available to urologists. Future multi-institutional retrospective and prospective trials are needed to validate our model.

Comparison of two drainage parameters on diuretic renogram in predicting the fate of prenatally detected pelvi-ureteric junction-like obstruction

INTRODUCTION

In infants with suspected pelviureteric junction (PUJ) like obstruction, we compared the drainage patterns suggested by t 1/2 and normalized residual activity (NORA) to determine which parameter can differentiate obstructive from nonobstructive dilatation and thus predict the need for surgery.

MATERIALS AND METHODS

Infants presenting with prenatally detected PUJ-like obstruction from January 2014 to March 2020 were evaluated with ultrasonography. Diuretic renogram was performed using Tc99m ethylene dicysteine using the F0 protocol. Subjects with a differential renal function >40% were included in the study. The t ½ values were noted. NORA was calculated by dividing the tracer values at 60 min with the values at 2 min. The infants were followed using ultrasonography. Renogram was repeated if there was increase in hydronephrosis or after 6 months if hydronephrosis did not regress. The follow-up was continued till a decision for pyeloplasty was made or the hydronephrosis regressed. Pyeloplasty was advised if differential function dropped to below 40%.

RESULTS

34 patients met the inclusion criteria. NORA and t ½ had very poor concordance in defining the drainage pattern. t ½ values did not correlate with the need for surgery or conservative management (P ≥ 0.05). Good drainage pattern by NORA was associated with regression of hydronephrosis (P ≤ 0.001). NORA predicted obstruction more accurately.

CONCLUSION

NORA can define good drainage in a much larger subset of patients with PUJ-like obstruction who eventually do not need surgery. However, further multicenter studies are needed to confirm this.

Diuresis renography in the evaluation and management of pediatric hydronephrosis: What have we learned?

Diuresis renography (DR) is widely used in the evaluation of hydronephrosis and hydroureter in infants and children. The goal of this provocative nuclear imaging examination should be to detect the hydronephrotic kidneys at risk for loss of function and development of pain, hematuria, and urinary tract infection. The reliability of DR is dependent on the acquisition and processing of the data as well as interpretation and utilization of the results. In this review, the key concepts of standardized DR and pitfalls to avoid are highlighted.