Scholarlink

Background <p>A model using stacked hourglass neural network modules was developed for automated lower limb alignment measurements in full-leg frontal radiographs. The goal was to assess whether high accuracy could be achieved with training on relatively small datasets, a common constraint in clinical research.</p> Methods <p>The model first identifies joints regions of interest (ROIs), then detects anatomical landmarks for alignment measurement within each ROI. 112 bilateral radiographs (216 annotated single-leg images) were used for training and validation, 99 (186 legs) as internal test set, and 25 (49) as external test set. Performance metrics included intraclass correlation coefficient (ICCs) and mean absolute error (MAE).</p> Results <p>The model achieved excellent agreement (ICCs &gt; 0.9) with manual annotations for all alignment parameters, except for the joint line convergence angle (ICC &lt; 0.5), which also showed poor agreement between human readers (0.73).</p> Conclusion <p>The proposed approach demonstrates high accuracy and reliability for automated lower limb alignment assessment, offering a robust solution for clinical research with limited annotated datasets.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Automated radiographic assessment of lower limb alignment using deep learning in a data-constrained clinical setting

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月4日

查看全文
  • Luca Häfliger,
  • Andrea Cina,
  • Louis Leuthard,
  • Hannes A. Rüdiger,
  • Vincent A. Stadelmann

摘要

Background

A model using stacked hourglass neural network modules was developed for automated lower limb alignment measurements in full-leg frontal radiographs. The goal was to assess whether high accuracy could be achieved with training on relatively small datasets, a common constraint in clinical research.

Methods

The model first identifies joints regions of interest (ROIs), then detects anatomical landmarks for alignment measurement within each ROI. 112 bilateral radiographs (216 annotated single-leg images) were used for training and validation, 99 (186 legs) as internal test set, and 25 (49) as external test set. Performance metrics included intraclass correlation coefficient (ICCs) and mean absolute error (MAE).

Results

The model achieved excellent agreement (ICCs > 0.9) with manual annotations for all alignment parameters, except for the joint line convergence angle (ICC < 0.5), which also showed poor agreement between human readers (0.73).

Conclusion

The proposed approach demonstrates high accuracy and reliability for automated lower limb alignment assessment, offering a robust solution for clinical research with limited annotated datasets.