Department of Electrical and Electronic Engineering, University of Dhaka, Dhaka, 1000, Bangladesh.
Urology Division, Surgery Department, Sidra Medicine, Qatar.
J Pediatr Urol. 2024 Apr;20(2):257-264. doi: 10.1016/j.jpurol.2023.10.030. Epub 2023 Nov 2.
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.
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.
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.
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.
在患有膀胱输尿管反流（VUR）的患者中，排空性膀胱尿道造影（VCUG）图像的放射学分级通常用于确定临床病程和适当的治疗方法。然而，VUR 的基于图像的评估仍然高度主观，因此我们开发了一个监督机器学习模型，以自动和客观地对 VCUG 数据进行分级。
本研究共从公共资源中收集了 113 张 VCUG 图像，以编制数据集。对于每张图像，四名儿科放射科医生和三名小儿泌尿科医生对 VUR 严重程度进行分级（低严重程度评分为 1-3；高严重程度评分为 4-5）。基于多数专家评估者诊断的等级为每张图像分配真实等级。从每张 VCUG 图像中提取了 9 个特征，然后使用“留一法”交叉验证训练、验证和测试了 6 个机器学习模型。比较和对比了所有特征，然后使用排名最高的特征来训练最终模型。
F1 分数是一种常用于指示机器学习模型性能准确性的指标。使用排名最高的 VCUG 图像特征时，支持向量机（SVM）和多层感知机（MLP）分类器的 F1 分数分别为 90.27%和 91.14%，表明准确性很高。当使用所有特征组合时，SVM 的 F1 分数为 89.37%，MLP 的 F1 分数为 90.27%。
这些发现表明，肾盏的扭曲模式是预测高等级 VUR 的准确指标。未来可以改进机器学习协议，以提高 VUR 的客观分级。
