文献速递骨肌儿科影像DR

双输入卷积神经网络在传统X线摄影中自动检测儿童肱骨髁上骨折

Using a Dual-Input Convolutional Neural Network for Automated Detection of Pediatric Supracondylar Fracture on Conventional Radiography.
PubMed 文献 · Invest Radiol · 2020-01-01

本研究开发了一种双输入卷积神经网络深度学习算法,利用正位和侧位肘关节X线片自动检测儿童肱骨髁上骨折,并评估其可行性和诊断性能。模型在验证集、时间测试集和地理测试集上的AUC分别为0.976、0.985和0.992,诊断性能与放射科医生相当。

要点

  • 双输入CNN模型在地理测试集AUC为0.992,与放射科医生(AUC 0.977-0.997)无显著差异(P>0.05)。
  • 模型在地理测试集敏感度100%、特异度86.1%,特异度和PPV显著低于3位人类读者(P<0.05)。
  • 模型在时间测试集敏感度93.9%、特异度92.2%,NPV 97.8%,适用于骨折筛查排除。

核心结论

  • 所提出的双输入深度学习模型可同时解读正位和侧位肘关节X线片,对儿童肱骨髁上骨折提供与放射科医生相当的准确诊断。

研究设计与样本

  • 研究开发深度学习模型,使用2013年1月至2017年12月同一机构1266对正位和侧位肘关节X线片,分为训练集1012对(79.9%)和验证集254对(20.1%)。
  • 外部测试使用两种独立数据集:时间测试集为2018年同一机构258对X线片,地理测试集为2016年1月至2018年12月另一家医院95对X线片。
  • 图像经裁剪和组织均衡化预处理后输入由两个ResNet模型合并构建的双输入神经网络;在地理测试集上由放射科医生进行观察者研究。

诊断标准与关键数值

  • 模型AUC在验证集为0.976,时间测试集为0.985,地理测试集为0.992。
  • 在地理测试集,人类读者AUC范围为0.977至0.997,与模型相比P值均大于0.05。
  • 模型在时间测试集敏感度93.9%、特异度92.2%、PPV 80.5%、NPV 97.8%。
  • 模型在地理测试集敏感度100%、特异度86.1%、PPV 69.7%、NPV 100%。
  • 与模型相比,3位人类读者使用McNemar检验均显示显著差异(P值均小于0.05),模型特异度和PPV较低;但3位人类读者与模型在敏感度和NPV上无显著差异(P值均大于0.05)。

临床应用与阅片要点

  • 原文未据此给出推荐。

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

OBJECTIVES: This study aimed to develop a dual-input convolutional neural network (CNN)-based deep-learning algorithm that utilizes both anteroposterior (AP) and lateral elbow radiographs for the automated detection of pediatric supracondylar fracture in conventional radiography, and assess its feasibility and diagnostic performance.

MATERIALS AND METHODS: To develop the deep-learning model, 1266 pairs of AP and lateral elbow radiographs examined between January 2013 and December 2017 at a single institution were split into a training set (1012 pairs, 79.9%) and a validation set (254 pairs, 20.1%). We performed external tests using 2 types of distinct datasets: one temporally and the other geographically separated from the model development. We used 258 pairs of radiographs examined in 2018 at the same institution as a temporal test set and 95 examined between January 2016 and December 2018 at another hospital as a geographic test set. Images underwent preprocessing, including cropping and histogram equalization, and were input into a dual-input neural network constructed by merging 2 ResNet models. An observer study was performed by radiologists on the geographic test set. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the model and human readers were calculated and compared.

RESULTS: Our trained model showed an AUC of 0.976 in the validation set, 0.985 in the temporal test set, and 0.992 in the geographic test set. In AUC comparison, the model showed comparable results to the human readers in the geographic test set; the AUCs of human readers were in the range of 0.977 to 0.997 (P's > 0.05). The model had a sensitivity of 93.9%, a specificity of 92.2%, a PPV of 80.5%, and an NPV of 97.8% in the temporal test set, and a sensitivity of 100%, a specificity of 86.1%, a PPV of 69.7%, and an NPV of 100% in the geographic test set. Compared with the developed deep-learning model, all 3 human readers showed a significant difference (P's < 0.05) using the McNemar test, with lower specificity and PPV in the model. On the other hand, there was no significant difference (P's > 0.05) in sensitivity and NPV between all 3 human readers and the proposed model.

CONCLUSIONS: The proposed dual-input deep-learning model that interprets both AP and lateral elbow radiographs provided an accurate diagnosis of pediatric supracondylar fracture comparable to radiologists.

来源:Invest Radiol,查看原文。版权归原作者所有。

引用

  1. Choi JW, Cho YJ, Lee S, et al. Using a Dual-Input Convolutional Neural Network for Automated Detection of Pediatric Supracondylar Fracture on Conventional Radiography. Invest Radiol. 2020. PMID: 31725064. doi:10.1097/RLI.0000000000000615

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。