文献速递牙体牙髓病

基于根尖片几何与深度学习特征的自动化根管弯曲度评估

Automated Root Canal Curvature Assessment From Periapical Radiographs Using Geometric and Deep Learning Features.
PubMed 文献 · Int Endod J · 2026-09-28

本研究利用1644张下颌前磨牙根尖片,构建四阶段多模型框架自动检测、分割并分类根管弯曲度。混合特征融合模型分类准确率最高达89.60%,几何特征单独模型对重度弯曲敏感性更高,Lüiten角是最显著预测因子。二维影像限制下,该框架宜作筛查辅助工具。

要点

  • 混合特征融合模型根管弯曲分类准确率最高,达89.60%。
  • 几何特征单独模型对重度弯曲敏感性80.6%,高于融合模型69.1%。
  • Lüiten角是根管弯曲严重程度最显著预测因子。

核心结论

  • 混合特征融合模型总体分类准确率最高,为89.60%。
  • 几何特征单独模型对重度弯曲敏感性80.6%,高于融合模型的69.1%。
  • Lüiten角是弯曲严重程度最显著预测因子。
  • 受二维根尖片无法显示颊舌向弯曲限制,框架最适合作为筛查辅助工具。

研究设计与样本

  • 回顾性横断面研究,使用1644张下颌前磨牙根尖片。
  • 采用四阶段多模型框架,固定10折交叉验证划分贯穿各阶段以避免数据泄漏。
  • 目标检测模型为YOLOv8、YOLOv11和RF-DETR;分割模型为YOLOv8-seg、YOLOv11-seg和Attention U-Net。
  • 特征提取包括二值掩膜自动导出的5个几何形态特征和ResNet-50的2048个深度卷积特征。
  • 分类采用XGBoost,分层10折交叉验证,训练折内应用SMOTE和算法类别加权。

主要发现

  • 数据集包括633颗直根管、885颗中度弯曲根管和126颗重度弯曲根管。
  • RF-DETR检测前磨牙的召回率97.5%、精确率93.3%、F1分数95.4%。
  • YOLOv11-seg分割根管的Dice分数85.8%、IoU 77.5%。
  • 5个几何参数在不同严重程度组间均具有统计学显著性(p值<0.001)。
  • 混合特征融合模型准确率89.60%、召回率83.80%、F1分数86.77%;几何特征单独模型准确率88.38%;深度学习特征单独模型准确率82.42%。

关键数值与推荐

  • 根管弯曲分类定义采用XGBoost分类器,分层10折交叉验证,训练折内应用SMOTE和算法类别加权。
  • 几何特征单独模型对重度弯曲敏感性80.6%,混合特征融合模型为69.1%。
  • Lüiten角是弯曲严重程度最显著预测因子。

临床怎么用

  • 该框架可作为筛查辅助工具,帮助识别需要附加三维评估的根管。
  • 混合特征融合模型分类准确率最高,但几何特征单独模型对重度弯曲敏感性更高。
  • Lüiten角是评估弯曲严重程度的重要预测指标。

局限性

  • 二维根尖片无法显示颊舌向弯曲,限制框架诊断能力。
  • 框架最适合作为筛查辅助工具,而非替代三维评估。

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

AIM: To develop and validate a machine learning-based automated computational framework using periapical radiographs for the detection, segmentation and classification of root canal curvature in mandibular premolars with single canals, and to evaluate the contribution of geometric and deep learning features towards diagnostic performance. METHODOLOGY: A retrospective cross-sectional study was performed using 1644 periapical images of mandibular premolars. A four-stage multi-model framework was proposed using a single fixed 10-fold cross-validation partition applied consistently across all four stages to prevent data leakage between training and evaluation. The object detection models were YOLOv8, YOLOv11 and RF-DETR. For segmentation of the root canal, YOLOv8-seg, YOLOv11-seg and Attention U-Net were used. The multiparametric feature extraction included five geometric morphometric features automatically derived from a binary mask and 2048 deep convolutional neural network features from ResNet-50. Classification of curvature was defined using an eXtreme Gradient Boosting (XGBoost) classifier with stratified 10-fold cross-validation, with Synthetic Minority Over-sampling Technique (SMOTE) and algorithmic class weighting applied within the training folds of each cross-validation iteration. RESULTS: The dataset included 633 straight, 885 moderately curved and 126 severely curved canals. RF-DETR achieved a recall of 97.5%, precision of 93.3% and F1-score of 95.4% for premolar detection. The YOLOv11-seg model was successful in segmenting the root canal with a Dice score of 85.8% and an IoU of 77.5%. All five geometric parameters were statistically significant for different severity groups (p-value < 0.001). For the end-to-end curvature classification, the hybrid feature fusion model produced the highest overall metrics, achieving an accuracy of 89.60%, a recall of 83.80% and an F1-score of 86.77%, compared to the models using either geometric features (88.38% accuracy) or deep learning features alone (82.42% accuracy). CONCLUSIONS: The hybrid feature-fusion model reached the highest overall classification accuracy at 89.60%. Although the geometric-only model had higher sensitivity for severe curvature with 80.6% compared to 69.1%, Lüiten's angle was the most prominent predictor of curvature severity. Due to the limitations of two-dimensional radiographs in displaying buccolingual curvatures, this framework works best as a screening aid as it helps identify canals that need adjunctive three-dimensional evaluation.

来源:Int Endod J,查看原文。版权归原作者所有。

引用

  1. Pachaiappan B, Poorni S, Srinivasan S, et al. Automated Root Canal Curvature Assessment From Periapical Radiographs Using Geometric and Deep Learning Features. Int Endod J. 2026. PMID: 42803142. doi:10.1111/iej.70281

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。