文献速递儿科影像骨肌DR

深度学习自动量化儿童下肢力线:卷积神经网络预测髋-膝-踝角

A deep learning approach to automatically quantify lower extremity alignment in children.
PubMed 文献 · Skeletal Radiol · 2021-07-13

本研究在大型儿童医院回顾性收集528张下肢全长X线片,由放射科医生手动标注六个解剖标志作为参考标准,开发并验证了一种卷积神经网络(CNN)通过热图回归间接定位标志点并计算髋-膝-踝角(HKAA)。结果显示,仅1.1%(12/1056)的HKAA预测为离群值(绝对误差>10°),排除离群值后平均绝对误差为0.94°±0.84°,组内相关系数为0.974。CNN在儿童下肢力线量化中表现出良好前景,有望作为计算机辅助诊断工具。

要点

  • CNN可自动从儿童下肢全长X线片计算HKAA,平均绝对误差0.94°。
  • 预测离群值(误差>10°)发生率低(1.1%),整体与参考标准一致性高(ICC=0.974)。
  • 方法基于热图回归间接定位股骨头中心、胫骨棘和胫骨穹窿六个标志点。

局限性

  • 单中心回顾性研究,样本来自一家儿童医院。
  • 仅纳入≤18岁儿童,未在成人或其他人群验证。
  • 原文未报告外部验证结果。

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 develop and validate a convolutional neural network (CNN) capable of predicting the anatomical landmarks used to calculate the hip-knee-ankle angles (HKAAs) from radiographs and thereby quantify lower extremity alignments in children.

MATERIALS AND METHODS: A search of the image archive at a large children's hospital was conducted to identify full-length lower extremity radiographs performed in children (≤ 18 years old) for the indication of lower extremity alignment (7/2019-10/2019). A radiologist manually labeled each radiograph's six requisite anatomical landmarks used to measure HKAAs (bilateral centers of the femoral head, tibial spine, and tibial plafond) and defined the resultant labels as ground truth. A 2D heatmap was generated for each ground truth landmark to encode the pseudo-probability of a landmark being at a particular location. A CNN was developed for indirect landmark localization by regressing across a collection of these heatmaps. The landmarks predicted from this model were used to calculate the HKAAs. Absolute prediction error and intraclass correlation were used to assess the accuracy of the HKAA estimates.

RESULTS: The study cohort consisted of 528 radiographs from 517 patients (mean age = 10.8 years, SD = 4.2 years). Evaluation of this CNN showed few HKAA prediction outliers (12/1056 [1.1%]), defined as having an absolute prediction error of > 10°. Excluding these outliers, the study cohort's mean absolute prediction error for the HKAA was 0.94° ± 0.84°, and the intraclass correlation between the ground truth and prediction was 0.974.

CONCLUSION: The proposed CNN generated promising results and offers potential for using this model as a computer-aided diagnostic tool.

来源:Skeletal Radiol,查看原文。版权归原作者所有。

引用

  1. Tsai A. A deep learning approach to automatically quantify lower extremity alignment in children. Skeletal Radiol. 2021. PMID: 34254170. doi:10.1007/s00256-021-03844-2

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。