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.

Potential benefits of functional magnetic resonance urography (fMRU) over MAG3 renal scan in children with obstructive uropathy.

INTRODUCTION: Functional renal imaging, most commonly with MAG3 nuclear medicine renal scan, is recommended in the evaluation of children with urinary tract dilation (UTD) suspected of obstructive uropathy. Alternatively, renal function can be evaluated with functional Magnetic Resonance Urography (fMRU), which has superior anatomic detail. However, there are not enough data comparing both methods' equivalency. In this study, we compare the functional and obstruction parameters of fMRU and MAG3 in a pediatric cohort presenting with obstructive uropathy. STUDY DESIGN: This is an IRB-approved retrospective review of all children undergoing fMRU at a single, free-standing children's hospital between May 2008 and September 2017. Patients who also underwent a MAG3 renal scan within 6 months and who had no interval surgical intervention were included in the study. Bladder catheterization was performed prior to both imaging studies. RESULTS: 735 children had 988 fMRU studies performed during the study period. 37 unique patients (13 girls and 24 boys) with median age of 6 months (range: 2 mo-19 y) were included in the final sample. Median time interval between studies was 70 days (range 6-179 days). The majority of participants (26/37, 70.3%) presented with UTD P3 and had diagnosis of uretero-pelvic junction obstruction (UPJO) in 21/37. Differential renal function (DRF) was used to group 10 fMRU and 9 MAG3 patients as normal; 9 fMRU and 11 MAG3 as mild; 11 fMRU and 6 MAG3 as moderate; and 7 fMRU and 6 MAG3 as severe; Wilcoxon signed-rank test (p = 0.5106). Results were similar for DRF among patients with and without duplex kidneys. In the analysis of obstruction, using reference standard T½ MAG3 ≥ 20 min, a greater or equal than 6 min renal transit time (RTT) from fMRU showed a specificity of 94%, a sensitivity of 62%, and an AUC of 0.827. DISCUSSION AND CONCLUSIONS: The differential renal function determined by MAG3 and fMRU in children was not statistically different, therefore we concluded that it was similar and potentially equivalent. Better correlation was shown in patients who had normal split kidney function. While the tests are clinically equivalent, the variability of DRF within each clinical category (i.e., normal, mild, moderate, severe) is not surprising, because MAG3 does not clearly differentiate the dilated collecting system from the functional parenchymal tissue, while fMRU does. Using MAG3 as the gold standard, fMRU was 94.74% specific and 5% more sensitive in detecting UPJO with a RTT of 6min vs. 8min.