文献速递脊柱外科小儿骨科

可解释机器学习模型在双平面X线影像中自动进行脊柱侧凸Cobb角分类

Automated Scoliosis Cobb Angle Classification in Biplanar Radiograph Imaging With Explainable Machine Learning Models.
PubMed 文献 · Spine (Phila Pa 1976) · 2025-02-25

本研究为回顾性队列研究,使用816张标注的脊柱正位EOS图像,通过一维特征工程和经典机器学习方法对脊柱侧凸的Cobb角范围进行分类;随机森林模型表现最佳,ROC AUC为91.8%,准确率86.1%;SHAP值增强了模型可解释性。

要点

  • 随机森林模型在Cobb角分类中表现最佳,ROC AUC为91.8%,准确率86.1%。
  • 在三种处理类别不平衡的技术中,分层采样产生的样本外结果最佳。
  • SHAP值用于前20个特征,包括脊柱弯曲长度和线性回归误差,增强模型可解释性。

核心结论

  • 使用经典机器学习方法进行特征工程,是基于Cobb角范围对脊柱侧凸严重程度进行分类的有效方法。
  • 特征在表示脊柱病理方面的高可解释性以及经典机器学习技术的易用性,使其成为开发自动工具管理复杂脊柱测量的有吸引力的解决方案。

研究设计与样本

  • 回顾性队列研究,使用816张标注的脊柱正位EOS图像,每张图像具有脊柱分割掩膜和10°多项式表示曲率。
  • 工程特征包括一阶和二阶导数、傅里叶变换和曲线能量,并归一化以增强鲁棒性;使用XGBoost选择前32个特征。
  • 模型基于Cobb角测量的曲率程度将脊柱侧凸分类为多组;采用分层采样、欠采样和过采样技术处理类别不平衡,使用10折分层K折交叉验证评估泛化性。
  • 使用自动网格搜索进行超参数优化,采用K折交叉验证(K=3)。

主要发现

  • 表现最佳的模型是随机森林,实现ROC AUC为91.8%。
  • 随机森林模型还达到准确率86.1%、精确率86.0%、召回率86.0%和F1分数85.1%。
  • 在三种处理类别不平衡的技术中,分层采样产生最佳的样本外结果。
  • 为前20个特征生成SHAP值,包括脊柱弯曲长度和线性回归误差,最具预测性的特征排名靠前,增强模型可解释性。

关键数值与推荐

  • 随机森林模型:ROC AUC 91.8%,准确率86.1%,精确率86.0%,召回率86.0%,F1分数85.1%。
  • 使用XGBoost选择前32个特征。
  • 10折分层K折交叉验证用于泛化性评估,K折交叉验证(K=3)用于超参数优化。
  • SHAP值用于前20个特征。

临床怎么用

  • 原文未据此给出推荐。

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)。

原文

STUDY DESIGN: Retrospective cohort study. OBJECTIVE: To quantify the pathology of the spine in patients with scoliosis through one-dimensional feature analysis. SUMMARY OF BACKGROUND DATA: Biplanar radiograph (EOS) imaging is a low-dose technology offering high-resolution spinal curvature measurement, crucial for assessing scoliosis severity and guiding treatment decisions. Machine learning (ML) algorithms, utilizing one-dimensional image features, can enable automated Cobb angle classification, improving accuracy and efficiency in scoliosis evaluation while reducing the need for manual measurements, thus supporting clinical decision-making. METHODS: This study used 816 annotated AP EOS spinal images with a spine segmentation mask and a 10° polynomial to represent curvature. Engineered features included the first and second derivatives, Fourier transform, and curve energy, normalized for robustness. XGBoost selected the top 32 features. The models classified scoliosis into multiple groups based on curvature degree, measured through Cobb angle. To address the class imbalance, stratified sampling, undersampling, and oversampling techniques were used, with 10-fold stratified K-fold cross-validation for generalization. An automatic grid search was used for hyperparameter optimization, with K-fold cross-validation (K=3). RESULTS: The top-performing model was Random Forest, achieving an ROC AUC of 91.8%. An accuracy of 86.1%, precision of 86.0%, recall of 86.0%, and an F1 score of 85.1% were also achieved. Of the three techniques used to address class imbalance, stratified sampling produced the best out-of-sample results. SHAP values were generated for the top 20 features, including spine curve length and linear regression error, with the most predictive features ranked at the top, enhancing model explainability. CONCLUSIONS: Feature engineering with classical ML methods offers an effective approach for classifying scoliosis severity based on Cobb angle ranges. The high interpretability of features in representing spinal pathology, along with the ease of use of classical ML techniques, makes this an attractive solution for developing automated tools to manage complex spinal measurements.

来源:Spine (Phila Pa 1976),查看原文。版权归原作者所有。

引用

  1. Yu J, Lahoti YS, McCandless KC, et al. Automated Scoliosis Cobb Angle Classification in Biplanar Radiograph Imaging With Explainable Machine Learning Models. Spine (Phila Pa 1976). 2025. PMID: 40007466. doi:10.1097/BRS.0000000000005312

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。