文献速递口腔正畸儿童口腔

基于面部照片的人工智能模型分类儿童矢状骨面型

AI-based classification of pediatric sagittal skeletal patterns using multi-view facial photographs.
PubMed 文献 · J Dent · 2026-04-13

本研究回顾性收集2033例儿童患者的面部照片和头颅侧位片,开发并验证基于人工智能的模型预测矢状骨面型分类。多视角模型在独立测试集上准确率达88.30%,与高级正畸医师一致性高,为无辐射早期筛查提供可行方案。

要点

  • 多视角AI模型预测儿童矢状骨面型准确率达88.30%。
  • 模型与高级正畸医师一致性差异仅2.70%。
  • 该工具旨在辅助筛查和转诊,而非替代专家。

核心结论

  • 基于多维度面部特征的人工智能方法可高精度预测儿童矢状骨面型,为无辐射筛查奠定基础。

研究设计与样本

  • 回顾性收集2013至2023年2033例儿童患者的面部照片和头颅侧位片,分为训练集1789例和独立测试集244例。
  • 比较六种骨干网络,选择ConvNeXt-T为最优骨干,采用主辅助特征融合策略构建单视角和多视角模型。
  • 采用五折交叉验证评估性能,并用Grad-CAM可视化关键特征区域。

主要发现

  • 90°侧面模型在单视角模型中准确率最高,达86.36%。
  • 最优多视角模型准确率提升至88.30%,召回率81.79%,特异性91.22%。
  • 在独立测试集上,模型与金标准的一致性比初级正畸医师高9.25%,比中级高7.43%(均P < 0.05),与高级专家差异2.70%。
  • Grad-CAM确认模型关注鼻唇和下巴轮廓区域。

关键数值与推荐

  • 多视角模型准确率88.30%,召回率81.79%,特异性91.22%。
  • 与初级正畸医师一致性差异9.25%,中级7.43%,高级2.70%。

临床怎么用

  • 该工具可用于非临床环境的大规模早期筛查,辅助转诊决策,促进儿童口腔健康的分层管理。
  • 应强调该工具主要辅助筛查和转诊,而非替代专家工作。

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

OBJECTIVE: The increasing global demand to assess pediatric skeletal malocclusions poses a growing challenge, as current screening methods are dependent on availability of orthodontists and X-rays, which limits accessibility. This study aimed to develop and validate an artificial intelligence (AI) model based on facial photographs to predict pediatric sagittal skeletal pattern classifications and to explore its feasibility for radiation-free early screening of pediatric skeletal malocclusion. METHODS: Facial photographs and lateral cephalograms were collected retrospectively from a cohort of 2033 pediatric patients at a stomatology hospital between 2013 and 2023. The dataset was divided into a training (n = 1789) and an independent test set (n = 244). Data were annotated, preprocessed, and augmented. Six backbones were compared, and ConvNeXt-T was selected as the optimal backbone. An innovative primary- auxiliary feature fusion strategy was adopted to identify the primary feature inputs and we first trained four single-view models. Subsequently, the primary and auxiliary features from other views were fused to construct four multi-view feature fusion models. Performance was evaluated by using five-fold cross-validation, with Grad-CAM visualizing key feature areas. Finally, the optimal model was clinically validated against practicing orthodontists on the independent test set. RESULTS: The 90° profile model achieved the highest accuracy of 86.36% among all single-view models. The optimal multi-view model further improved the accuracy to 88.30% (recall=81.79%, specificity=91.22%). Using the independent test set, the model's agreement with the gold standard was 9.25% higher than junior level orthodontists and 7.43% higher than intermediate orthodontists (both P < 0.05), and closely aligns with senior professionals (difference: 2.70%). Grad-CAM confirmed focus on the nasolabial and chin contour regions. CONCLUSIONS: An innovative method was successfully established to predict pediatric sagittal skeletal patterns with high accuracy (>88%) using multi-dimensional facial characteristics. This lays the groundwork for a non-clinical, photographic screening approach for identify pediatric skeletal malocclusions. CLINICAL SIGNIFICANCE: This method provides a feasible, radiation-free solution for early large-scale screening in non-clinical settings, supporting initial referral decisions while promoting early interventions and stratified management of children's oral health. It should be emphasized that this tool is intended primarily to assist screenings and referrals, rather than replacing the essential work of expert professionals.

来源:J Dent,查看原文。版权归原作者所有。

引用

  1. Peng Y, Nan L, Chen W, et al. AI-based classification of pediatric sagittal skeletal patterns using multi-view facial photographs. J Dent. 2026. PMID: 41985735. doi:10.1016/j.jdent.2026.106697

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。