文献速递骨肌儿科影像DR

卷积神经网络自动定位解剖标志点用于下肢不等长测量

Anatomical landmark localization via convolutional neural networks for limb-length discrepancy measurements.
PubMed 文献 · Pediatr Radiol · 2021-04-22

本研究基于504张EOS全长下肢正位X线片(359例≤21岁患者),开发卷积神经网络自动定位股骨头顶点、股骨内髁和胫骨穹窿中心六个标志点并预测骨长。结果显示标志点平均点误差0.37-0.42 cm,股骨、胫骨、肢体长度及下肢不等长的平均绝对误差为0.30-0.36 cm,预测骨长与真实值强相关。该原型网络为自动测量下肢不等长提供了潜力。

要点

  • CNN可自动定位全长下肢X线片上股骨头顶点、股骨内髁和胫骨穹窿中心。
  • 骨长和下肢不等长的平均绝对误差约0.3-0.4 cm,接近临床可接受范围。
  • 该工具目前为原型,尚不能替代人工测量,需外部验证。

核心结论

  • 原型卷积神经网络能从EOS全长下肢X线片预测骨长度和下肢不等长,结果具有前景。

研究设计与样本

  • 回顾性研究,纳入2016年2月至2019年9月一家医院EOS系统采集的504张全长下肢正位X线片,来自359例≤21岁患者。
  • 参考标准为一名儿科放射科医师手动标注的六个解剖标志点:双侧股骨头顶点、股骨内髁和胫骨穹窿中心。
  • 为每个标志点生成二维热图编码空间伪概率,卷积神经网络通过回归热图集合实现标志点定位和骨长预测。

诊断标准与关键数值

  • 股骨头顶点、股骨内髁和胫骨穹窿中心的平均点误差分别为0.37 cm、0.39 cm和0.42 cm。
  • 股骨长度、胫骨长度、肢体长度和下肢不等长的平均绝对误差分别为0.33 cm、0.30 cm、0.30 cm和0.36 cm。
  • 预测骨长度与真实值呈强相关。

临床应用与阅片要点

  • 该CNN可辅助自动定位全长下肢X线片上的关键标志点,减少手动测量时间。
  • 预测误差约0.3-0.4 cm,阅片时仍需结合临床和人工复核,尤其存在骨骼畸形或内置物时。
  • 目前为原型工具,尚未集成到临床工作流,不能直接用于报告。

局限性

  • 单中心回顾性研究,样本来自特定EOS系统。
  • 仅纳入≤21岁且有下肢不等长指征的患者,外推性有限。
  • 参考标准为单一儿科放射科医师手动标注,未评估观察者间变异。
  • 为原型CNN,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

BACKGROUND: Measurement of limb-length discrepancy (LLD) from a radiograph is a cognitively simple but time-consuming task.

OBJECTIVE: To develop a convolutional neural network (CNN) to localize anatomical landmarks from full-length lower-extremity radiographs in predicting LLD.

MATERIALS AND METHODS: The author searched a hospital's image database to identify studies performed between Feb. 1, 2016, and Sept. 30, 2019. Inclusion criteria were: (1) patients ≤21 years old, (2) study indication of LLD, (3) full-length lower-extremity anteroposterior radiographs performed on the EOS system, and (4) imaging field-of-view that included entire bilateral femurs and tibias. The six requisite ground truth anatomical landmarks for measuring LLD from each radiograph - bilateral top of femoral heads, medial femoral condyles, and center of tibial plafonds - were manually labeled by a pediatric radiologist. For each landmark, a two-dimensional heatmap was generated to encode the pseudo-probability of a landmark being at a particular spatial location. A CNN was developed that regressed across a collection of these heatmaps for landmark localization and bone length predictions.

RESULTS: The study cohort consisted of 504 full-length lower-extremity radiographs from 359 patients with wide ranging skeletal deformities and in situ hardware. Evaluation of this CNN showed that the mean point-error for the predicted top of femoral head, medial femoral condyle, and center of tibial plafond were 0.37 cm, 0.39 cm and 0.42 cm, respectively. The mean absolute error for the predicted femoral, tibial and limb lengths, and LLD were 0.33 cm, 0.30 cm, 0.30 cm, and 0.36 cm, respectively. Predicted bone lengths correlated strongly with ground truth.

CONCLUSION: This prototype CNN delivered promising results in predicting bone lengths from full-length lower-extremity radiographs and offers the potential use of a computer algorithm to predict LLD.

来源:Pediatr Radiol,查看原文。版权归原作者所有。

引用

  1. Tsai A. Anatomical landmark localization via convolutional neural networks for limb-length discrepancy measurements. Pediatr Radiol. 2021. PMID: 33885918. doi:10.1007/s00247-021-05004-z

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。