文献速递骨肌儿科影像技术与安全DR

新型卷积神经网络算法在正位X线片上检测发育性髋关节发育不良的诊断效能

Diagnostic Performance of a New Convolutional Neural Network Algorithm for Detecting Developmental Dysplasia of the Hip on Anteroposterior Radiographs.
PubMed 文献 · Korean J Radiol · 2020-11-26

该研究利用2601张髋关节正位X线片裁剪出的5076张单侧髋关节图像构建数据集,训练卷积神经网络算法自动检测发育性髋关节发育不良(DDH),并与3名不同经验放射科医师比较。算法诊断DDH的AUC为0.988,敏感度98.0%、特异度98.1%、阳性预测值84.5%、阴性预测值99.8%,与有儿科放射学经验医师的诊断无显著差异(p=0.180),但敏感度、特异度和阳性预测值均高于无儿科放射学经验医师(p<0.001)。

要点

  • 该深度学习算法在髋关节正位X线片上检测DDH的AUC达0.988,敏感度98.0%、特异度98.1%。
  • 算法与有儿科放射学经验医师的诊断效能无显著差异(p=0.180)。
  • 算法敏感度、特异度和阳性预测值均高于无儿科放射学经验医师(p<0.001)。

核心结论

  • 所提出的深度学习算法能在髋关节X线片上准确诊断DDH,其诊断效能与有经验的放射科医师相当。

研究设计与样本

  • 研究论文;使用2601张髋关节正位X线片裁剪出的5076张单侧髋关节关节图像构建数据集,按80%训练集、10%验证集、10%测试集划分;由3名放射科医师将髋关节图像标注为正常或DDH;比较深度学习算法与不同经验水平放射科医师的诊断效能。

诊断标准与关键数值

  • 深度学习算法诊断DDH的ROC曲线下面积为0.988,放射科医师的ROC曲线下面积为0.988-0.919;算法PRC曲线下面积为0.973,放射科医师为0.618-0.958;算法敏感度98.0%、特异度98.1%、阳性预测值84.5%、阴性预测值99.8%。

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

OBJECTIVE: To evaluate the diagnostic performance of a deep learning algorithm for the automated detection of developmental dysplasia of the hip (DDH) on anteroposterior (AP) radiographs.

MATERIALS AND METHODS: Of 2601 hip AP radiographs, 5076 cropped unilateral hip joint images were used to construct a dataset that was further divided into training (80%), validation (10%), or test sets (10%). Three radiologists were asked to label the hip images as normal or DDH. To investigate the diagnostic performance of the deep learning algorithm, we calculated the receiver operating characteristics (ROC), precision-recall curve (PRC) plots, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) and compared them with the performance of radiologists with different levels of experience.

RESULTS: The area under the ROC plot generated by the deep learning algorithm and radiologists was 0.988 and 0.988-0.919, respectively. The area under the PRC plot generated by the deep learning algorithm and radiologists was 0.973 and 0.618-0.958, respectively. The sensitivity, specificity, PPV, and NPV of the proposed deep learning algorithm were 98.0, 98.1, 84.5, and 99.8%, respectively. There was no significant difference in the diagnosis of DDH by the algorithm and the radiologist with experience in pediatric radiology (p = 0.180). However, the proposed model showed higher sensitivity, specificity, and PPV, compared to the radiologist without experience in pediatric radiology (p < 0.001).

CONCLUSION: The proposed deep learning algorithm provided an accurate diagnosis of DDH on hip radiographs, which was comparable to the diagnosis by an experienced radiologist.

来源:Korean J Radiol,查看原文。版权归原作者所有。

引用

  1. Park HS, Jeon K, Cho YJ, et al. Diagnostic Performance of a New Convolutional Neural Network Algorithm for Detecting Developmental Dysplasia of the Hip on Anteroposterior Radiographs. Korean J Radiol. 2020. PMID: 33289354. doi:10.3348/kjr.2020.0051

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。