文献速递骨肌DR

在X线平片上测量临界肩角:一种准确且可重复的深度学习模型

Measuring the critical shoulder angle on radiographs: an accurate and repeatable deep learning model.
PubMed 文献 · Skeletal Radiol · 2022-03-28

该研究基于8467张肩关节前后位X线图像及3个关键点标注,开发了卷积神经网络联合空间到数值变换(DSNT)层的深度学习模型,自动计算临界肩角(CSA)。模型三个关键点的归一化中位误差为2.9%、2.5%和2%,CSA测量中位误差在角度低于30°、30°–35°和高于35°时分别为1°、0.88°和0.99°,均低于文献报告的CSA测量标准误(大于2°)。作者认为该模型有潜力用于对可重复性要求高的临床场景。

要点

  • 模型在8467张肩关节前后位X线图像上训练,自动预测3个关键点并计算临界肩角(CSA)。
  • CSA测量中位误差在角度低于30°、30°–35°和高于35°时分别为1°、0.88°和0.99°。
  • CSA测量标准误大于2°,高于模型的中位误差,提示模型精度可能足以用于临床。

核心结论

  • 深度学习模型能自动、准确地测量临界肩角(CSA),其测量误差低于文献报告的CSA测量标准误(大于2°),有潜力用于对可重复性要求高的临床场景。

研究设计与样本

  • 研究使用8467张肩关节前后位X线图像及3个关键点标注,采用卷积神经网络联合空间到数值变换(DSNT)层预测关键点坐标并计算CSA;性能以归一化欧氏距离和与人工测量CSA的误差评估。

诊断标准与关键数值

  • 三个关键点的归一化中位误差分别为2.9%、2.5%和2%。
  • CSA测量中位误差在角度低于30°时为1°(标准差1.2°)。
  • CSA测量中位误差在角度30°–35°时为0.88°(标准差0.87°)。
  • CSA测量中位误差在角度高于35°时为0.99°(标准差1°)。

临床应用与阅片要点

  • 模型可自动计算CSA,有望用于对可重复性要求高的临床场景。
  • 模型CSA测量中位误差低于文献报告的CSA测量标准误(大于2°)。

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: Since the critical shoulder angle (CSA) is considered a risk factor for shoulder pathology and the intra- and inter-rater variabilities in its calculation are not negligible, we developed a deep learning model that calculates it automatically and accurately.

METHODS: We used a dataset of 8467 anteroposterior x-ray images of the shoulder annotated with 3 landmarks of interest. A Convolutional Neural Network model coupled with a spatial to numerical transform (DSNT) layer was used to predict the landmark coordinates from which the CSA was calculated. The performances were evaluated by calculating the Euclidean distance between the ground truth coordinates and the predicted ones normalized with respect to the distance between the first and the second points, and the error between the CSA angle measured by a human observer and the predicted one.

RESULTS: Regarding the normalized point distances, we obtained a median error of 2.9%, 2.5%, and 2% for the three points among the entire set. Considering CSA calculations, the median errors were 1° (standard deviation 1.2°), 0.88° (standard deviation 0.87°), and 0.99° (standard deviation 1°) for angles below 30°, between 30° and 35°, and above 35°, respectively.

DISCUSSION: These results demonstrate that the model has the potential to be used in clinical settings where the replicability is important. The reported standard error of the CSA measurement is greater than 2° that is above the median error of our model, indicating a potential accuracy sufficient to be used in a clinical setting.

来源:Skeletal Radiol,查看原文。版权归原作者所有。

引用

  1. Minelli, Cina, Galbusera, et al. Measuring the critical shoulder angle on radiographs: an accurate and repeatable deep learning model. Skeletal Radiol. 2022. PMID: 35347406. doi:10.1007/s00256-022-04041-5

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。