文献速递胸部外周血管CT

三维卷积神经网络自动检测CTPA肺栓塞

Automatic detection of pulmonary embolism on computed tomography pulmonary angiogram scan using a three-dimensional convolutional neural network.
PubMed 文献 · Eur J Radiol · 2024-06-21

本研究提出EmbNet卷积神经网络用于CT肺动脉造影(CTPA)肺栓塞自动检测,使用305例连续CTPA扫描(142训练、163内部验证)及250例公共数据集外部验证,以三名放射科医生确立的金标准评估。内部验证每扫描敏感度90.9%、特异度75.4%、PPV 48.4%、NPV 97.0%;外部验证分别为88.0%、70.5%、42.7%、95.9%。结论认为EmbNet在各栓塞位置均提供高敏感度,有望用于临床初筛。

要点

  • EmbNet在内部及外部验证中每扫描敏感度均较高(90.9%、88.0%),NPV达97.0%和95.9%,适合初筛排除肺栓塞。
  • 按栓塞位置分层,叶分支栓塞敏感度最高(内部95.2%、外部93.5%),周围区域敏感度相对较低(82.6%、80.2%)。
  • 每扫描假阳性率内部验证为0.45个、外部验证为0.69个假栓塞,PPV偏低(48.4%、42.7%),需人工复核阳性结果。

诊断标准与关键数值

  • 内部验证每扫描水平敏感度90.9%、特异度75.4%、PPV 48.4%、NPV 97.0%。
  • 外部验证每扫描水平敏感度88.0%、特异度70.5%、PPV 42.7%、NPV 95.9%。
  • 内部验证每栓塞水平总体敏感度86.0%、PPV 61.3%;外部验证总体敏感度83.5%、PPV 57.5%。
  • 中央栓塞敏感度及PPV内部验证89.7%和52.0%,外部验证94.4%和43.0%;叶分支栓塞内部验证95.2%和76.9%,外部验证93.5%和72.5%;周围栓塞内部验证82.6%和61.7%,外部验证80.2%和59.4%。
  • 平均假阳性率内部验证为每扫描0.45个假栓塞,外部验证为每扫描0.69个假栓塞。

临床应用与阅片要点

  • 高敏感度和高NPV支持将EmbNet用于肺栓塞初筛,阴性结果有助于排除栓塞,但阳性结果因PPV偏低需放射科医生复核确认。
  • 阅片时关注中央动脉和叶分支栓塞,模型对叶分支敏感度最高;周围区域敏感度相对较低,需注意假阴性可能。
  • 模型每扫描约0.45–0.69个假阳性栓塞,报告时需警惕假阳性病灶,避免过度诊断。

局限性

  • 研究为单中心训练与内部验证,外部验证使用公共数据集,结论外推需谨慎。
  • PPV较低,提示假阳性较多,作为独立诊断工具的证据尚不充分。

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

OBJECTIVE: To propose a convolutional neural network (EmbNet) for automatic pulmonary embolism detection on computed tomography pulmonary angiogram (CTPA) scans and to assess its diagnostic performance.

METHODS: 305 consecutive CTPA scans between January 2019 and December 2021 were enrolled in this study (142 for training, 163 for internal validation), and 250 CTPA scans from a public dataset were used for external validation. The framework comprised a preprocessing step to segment the pulmonary vessels and the EmbNet to detect emboli. Emboli were divided into three location-based subgroups for detailed evaluation: central arteries, lobar branches, and peripheral regions. Ground truth was established by three radiologists.

RESULTS: The EmbNet's per-scan level sensitivity, specificity, positive predictive value (PPV), and negative predictive value were 90.9%, 75.4%, 48.4%, and 97.0% (internal validation) and 88.0%, 70.5%, 42.7%, and 95.9% (external validation). At the per-embolus level, the overall sensitivity and PPV of the EmbNet were 86.0% and 61.3% (internal validation), and 83.5% and 57.5% (external validation). The sensitivity and PPV of central emboli were 89.7% and 52.0% (internal validation), and 94.4% and 43.0% (external validation); of lobar emboli were 95.2% and 76.9% (internal validation), and 93.5% and 72.5% (external validation); and of peripheral emboli were 82.6% and 61.7% (internal validation), and 80.2% and 59.4% (external validation). The average false positive rate was 0.45 false emboli per scan (internal validation) and 0.69 false emboli per scan (external validation).

CONCLUSION: The EmbNet provides high sensitivity across embolus locations, suggesting its potential utility for initial screening in clinical practice.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Zhu H, Tao G, Jiang Y, et al. Automatic detection of pulmonary embolism on computed tomography pulmonary angiogram scan using a three-dimensional convolutional neural network. Eur J Radiol. 2024. PMID: 38941822. doi:10.1016/j.ejrad.2024.111586

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。