文献速递胸部技术与安全DR

卷积神经网络用于胸部X线片自动分类的评估

Assessment of Convolutional Neural Networks for Automated Classification of Chest Radiographs.
PubMed 文献 · Radiology · 2018-11-13

本回顾性研究纳入1998至2012年间获取的216 431张正面胸部X线片及关联文本报告和主治放射科医师前瞻性标签,训练卷积神经网络将胸片分类为正常或异常,并在533张由专家放射科医师手工标注的留出集上评估。使用20万张图像训练的CNN平均AUC为0.96,优于2000张图像训练的AUC 0.84(P < .005),与2万张图像训练的AUC 0.95无显著差异(P > .05);将CNN输出评分与二分类前瞻性标签平均后获得最佳分类器,AUC为0.98(P < .005)。

要点

  • 使用20万张图像训练的CNN对胸片正常/异常二分类的平均AUC为0.96。
  • CNN输出评分与前瞻性二分类标签平均后分类器性能最佳,AUC为0.98。
  • 模型分类受临床相关空间区域影响大,但不能可靠泛化至胸部疾病以外。

核心结论

  • 使用中等规模前瞻性标注胸片集合训练的CNN在胸片正常/异常分类中达到高诊断性能,该功能可能有助于异常胸片的自动优先排序。

研究设计与样本

  • 回顾性研究,获取1998至2012年间216 431张正面胸部X线片及关联文本报告和主治放射科医师前瞻性标签用于训练CNN,并在533张由专家放射科医师手工标注的留出集上评估。

关键影像表现/征象

  • CNN激活可视化显示模型分类受临床相关空间区域影响较大。
  • 模型不能可靠泛化至胸部疾病以外的分类。

诊断标准与关键数值

  • 使用20万张图像训练的CNN平均AUC为0.96。
  • 使用2000张图像训练的CNN AUC为0.84,低于20万张图像训练模型(P < .005)。
  • 使用2万张图像训练的CNN AUC为0.95,与20万张图像训练模型无显著差异(P > .05)。
  • CNN输出评分与二分类前瞻性标签平均后分类器AUC为0.98(P < .005)。

临床应用与阅片要点

  • 作者认为该CNN功能可能有助于异常胸片的自动优先排序。

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

Purpose To assess the ability of convolutional neural networks (CNNs) to enable high-performance automated binary classification of chest radiographs. Materials and Methods In a retrospective study, 216 431 frontal chest radiographs obtained between 1998 and 2012 were procured, along with associated text reports and a prospective label from the attending radiologist. This data set was used to train CNNs to classify chest radiographs as normal or abnormal before evaluation on a held-out set of 533 images hand-labeled by expert radiologists. The effects of development set size, training set size, initialization strategy, and network architecture on end performance were assessed by using standard binary classification metrics; detailed error analysis, including visualization of CNN activations, was also performed. Results Average area under the receiver operating characteristic curve (AUC) was 0.96 for a CNN trained with 200 000 images. This AUC value was greater than that observed when the same model was trained with 2000 images (AUC = 0.84, P < .005) but was not significantly different from that observed when the model was trained with 20 000 images (AUC = 0.95, P > .05). Averaging the CNN output score with the binary prospective label yielded the best-performing classifier, with an AUC of 0.98 (P < .005). Analysis of specific radiographs revealed that the model was heavily influenced by clinically relevant spatial regions but did not reliably generalize beyond thoracic disease. Conclusion CNNs trained with a modestly sized collection of prospectively labeled chest radiographs achieved high diagnostic performance in the classification of chest radiographs as normal or abnormal; this function may be useful for automated prioritization of abnormal chest radiographs. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by van Ginneken in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Dunnmon JA, Yi D, Langlotz CP, et al. Assessment of Convolutional Neural Networks for Automated Classification of Chest Radiographs. Radiology. 2018. PMID: 30422093. doi:10.1148/radiol.2018181422

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。