儿科胸片气管插管检测与定位的两阶段深度学习流程
本研究回顾性纳入单中心1000例儿科胸片(476例有气管插管,524例无),开发并评估一个ResNet分类加U-Net分割的两阶段深度学习流程。该流程对气管插管检测的AUROC为0.994,插管尖端定位的平均绝对误差为6.59 mm,而阅片者间定位变异为2.01 mm。
要点
- 两阶段流程对有无气管插管的检测AUROC达0.994,可优先用于筛查性判断。
- 加入分类阶段可将无插管胸片中的假阳性分割从17例降至3例,减少误报。
- 尖端定位误差6.59 mm大于阅片者间变异2.01 mm,提示定位仅具初步价值。
核心结论
- 两阶段深度学习流程在儿科胸片上对气管插管检测性能高,对尖端定位性能有前景但仍落后于阅片者间一致性。
研究设计与样本
- 回顾性研究,纳入单中心2021年采集的1000例儿科胸片,其中476例有气管插管、524例无气管插管。
- 分割掩膜与远端尖端坐标由受训分析员标注并经儿科放射科医生核实。
- 检测用ResNet分类模型,定位用U-Net分割模型,两者构成两阶段流程,在留出测试集上评估。
关键影像表现/征象
- 单独分割模型在无气管插管胸片上产生17例假阳性分割,加入分类阶段后降至3例。
诊断标准与关键数值
- 气管插管检测AUROC为0.994,95%CI为0.986至1.000。
- 气管插管尖端定位平均绝对误差为6.59 mm,95%CI为5.19至8.21 mm。
- 阅片者间对气管插管尖端定位的变异为2.01 mm平均绝对误差,作为定位性能参照。
临床应用与阅片要点
- 两阶段流程在儿科胸片报告中可作为气管插管有无的自动筛查工具,降低漏诊风险。
- 分类阶段可有效过滤无插管胸片上的假阳性分割,减少阅片时的无效提示。
- 当前定位误差大于阅片者间变异,定位结果用于临床决策前需人工核对尖端位置。
局限性
- 本研究为单中心初步研究,样本量为1000例儿科胸片,缺乏外部验证。
- 作者指出需在更大样本及外部儿科队列中进一步评估其泛化能力。
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: Endotracheal tubes (ETTs) are critical life-support devices for mechanically ventilated pediatric patients, yet automated ETT assessment on pediatric chest radiographs (CXRs) remains limited.
OBJECTIVE: To develop and evaluate a two-stage deep learning pipeline for automated detection and localization of ETTs on pediatric CXRs.
MATERIALS AND METHODS: This retrospective study included 1,000 pediatric CXRs (476 ETT-positive, 524 ETT-negative) acquired in 2021 at a single institution. ETT segmentation masks and distal tip coordinates were annotated by trained analysts and verified by pediatric radiologists. A two-stage pipeline consisting of a ResNet classification model followed by a U-Net segmentation model was developed for ETT detection and localization. Performance was evaluated on a held-out test set using multiple metrics, including the area under the receiver operating characteristic curve (AUROC) and the mean absolute error (MAE), with 95% confidence intervals (CI). Inter-observer variability was assessed as a reference for localization performance.
RESULTS: Inter-observer variability for ETT tip localization was 2.01 mm MAE on the held-out test set. The pipeline achieved an AUROC of 0.994 (95% CI 0.986, 1.000) for ETT detection. For localization, the pipeline achieved a MAE of 6.59 mm (95% CI 5.19, 8.21 mm). Incorporating the classification stage substantially reduced false-positive segmentations from 17 to 3 among ETT-negative CXRs compared with the standalone segmentation model.
CONCLUSION: A two-stage deep learning pipeline demonstrated high performance for automated ETT detection and promising performance for tip localization on pediatric CXRs in this single-center pilot study. Further evaluation in larger and external pediatric cohorts is needed to assess generalizability.
引用
- Li, Zhang, Somasundaram, et al. A two-stage deep learning pipeline for automated detection and localization of endotracheal tubes on pediatric chest radiographs: a pilot study. Pediatr Radiol. 2026. PMID: 42726228. doi:10.1007/s00247-026-06767-z
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。