文献速递儿科影像泌尿生殖技术与安全US

比较神经网络对肾超声尿路扩张的分类:与专家分类一致性的评估

Comparison of neural networks for classification of urinary tract dilation from renal ultrasounds: evaluation of agreement with expert categorization.
PubMed 文献 · Pediatr Radiol · 2025-07-04

本研究基于≤3月龄婴儿肾超声图像,由专家标注UTD分级作为参考标准,评估三种深度学习模型四折交叉验证的分类性能。右肾和左肾预测准确率分别为88.7%和80.5%,加权kappa分别为0.90和0.87;二分类为轻度(正常/P1)与重度(UTD P2/P3)后准确率升至96.3%和91.3%,一致性降至0.78和0.75。作者认为深度学习模型在婴儿肾超声UTD分类中表现出高准确性和一致性,支持其作为临床工作流程中的决策支持工具的潜力。

要点

  • 深度学习模型对婴儿肾超声UTD分级与专家分类一致性高,加权kappa右肾0.90、左肾0.87。
  • 二分类为轻度(正常/P1)与重度(UTD P2/P3)后准确率提高但一致性下降。
  • 模型预测准确率右肾88.7%、左肾80.5%,二分类后右肾96.3%、左肾91.3%。

核心结论

  • 深度学习模型在婴儿肾超声UTD分类中表现出高准确性和一致性,支持其作为临床工作流程中决策支持工具的潜力。

研究设计与样本

  • 回顾性检索影像档案中≤3月龄婴儿因产前UTD和尿路感染指征行肾超声的图像(2023年9月至2024年8月);由一名儿科泌尿放射学专家对代表性矢状面肾超声图像提供UTD分级参考标签;三种深度学习模型采用交叉熵损失训练,并以四折交叉验证评估总体性能。

诊断标准与关键数值

  • 右肾模型预测准确率88.7%(95%CI [85.8%, 91.5%]),加权kappa 0.90(95%CI [0.88, 0.91]);左肾准确率80.5%(95%CI [77.6%, 82.9%]),加权kappa 0.87(95%CI [0.82, 0.92])。二分类为轻度(正常/P1)与重度(UTD P2/P3)后,右肾准确率96.3%(95%CI [94.9%, 97.8%])、一致性0.78(95%CI [0.73, 0.82]);左肾准确率91.3%(95%CI [88.5%, 94.2%])、一致性0.75(95%CI [0.68, 0.82])。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

BACKGROUND: Urinary tract dilation (UTD) is a frequent problem in infants. Automated and objective classification of UTD from renal ultrasounds would streamline their interpretations.

OBJECTIVE: To develop and evaluate the performance of different deep learning models in predicting UTD classifications from renal ultrasound images.

MATERIALS AND METHODS: We searched our image archive to identify renal ultrasounds performed in infants ≤ 3-months-old for the clinical indications of prenatal UTD and urinary tract infection (9/2023-8/2024). An expert pediatric uroradiologist provided the ground truth UTD labels for representative sagittal sonographic renal images. Three different deep learning models trained with cross-entropy loss were adapted with four-fold cross-validation experiments to determine the overall performance.

RESULTS: Our curated database included 492 right and 487 left renal ultrasounds (mean age ± standard deviation = 1.2 ± 0.1 months for both cohorts, with 341 boys/151 girls and 339 boys/148 girls, respectively). The model prediction accuracies for the right and left kidneys were 88.7% (95% confidence interval [CI], [85.8%, 91.5%]) and 80.5% (95% CI, [77.6%, 82.9%]), with weighted kappa scores of 0.90 (95% CI, [0.88, 0.91]) and 0.87 (95% CI, [0.82, 0.92]), respectively. When predictions were binarized into mild (normal/P1) and severe (UTD P2/P3) dilation, accuracies of the right and left kidneys increased to 96.3% (95% CI, [94.9%, 97.8%]) and 91.3% (95% CI, [88.5%, 94.2%]), but agreements decreased to 0.78 (95% CI, [0.73, 0.82]) and 0.75 (95% CI, [0.68, 0.82]), respectively.

CONCLUSION: Deep learning models demonstrated high accuracy and agreement in classifying UTD from infant renal ultrasounds, supporting their potential as decision-support tools in clinical workflows.

来源:Pediatr Radiol,查看原文。版权归原作者所有。

引用

  1. Chung K, Wu S, Jeanne C, et al. Comparison of neural networks for classification of urinary tract dilation from renal ultrasounds: evaluation of agreement with expert categorization. Pediatr Radiol. 2025. PMID: 40613839. doi:10.1007/s00247-025-06311-5

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。