Quantification of vesicoureteral reflux using machine learning.

INTRODUCTION

The radiographic grading of voiding cystourethrogram (VCUG) images is often used to determine the clinical course and appropriate treatment in patients with vesicoureteral reflux (VUR). However, image-based evaluation of VUR remains highly subjective, so we developed a supervised machine learning model to automatically and objectively grade VCUG data.

STUDY DESIGN

A total of 113 VCUG images were gathered from public sources to compile the dataset for this study. For each image, VUR severity was graded by four pediatric radiologists and three pediatric urologists (low severity scored 1-3; high severity 4-5). Ground truth for each image was assigned based on the grade diagnosed by a majority of the expert assessors. Nine features were extracted from each VCUG image, then six machine learning models were trained, validated, and tested using 'leave-one-out' cross-validation. All features were compared and contrasted, with the highest-ranked then being used to train the final models.

RESULTS

F1-score is a metric that is often used to indicate performance accuracy of machine learning models. When using the highest-ranked VCUG image features, F1-scores for the support vector machine (SVM) and multi-layer perceptron (MLP) classifiers were 90.27 % and 91.14 %, respectively, indicating a high level of accuracy. When using all features combined, F1 scores were 89.37 % for SVM and 90.27 % for MLP.

DISCUSSION

These findings indicate that a distorted pattern of renal calyces is an accurate predictor of high-grade VUR. Machine learning protocols can be enhanced in future to improve objective grading of VUR.